H0.3 top features

Top feature 0 in H0.3: (feature 17025)

TOP ACTIVATIONS
MAX = 1.473

Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.322
America
Token America
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.473
deb
Token deb
Feature activation+0.000
au
Tokenau
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
system
Token system
Feature activation+0.000
-
Token -
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.322
America
Token America
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.473
deb
Token deb
Feature activation+0.000
rop
Tokenrop
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
kin
Tokenkin
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.295
View
Token View
Feature activation+0.000
points
Tokenpoints
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĺ
TokenĹ
Feature activation+0.000
A
TokenA
Feature activation+0.000
officials
Token officials
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+1.230
help
Token help
Feature activation+0.000
but
Token but
Feature activation+0.000
think
Token think
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
?
Token?
Feature activation+0.000
Marx
Token Marx
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.221
and
Token and
Feature activation+0.000
K
Token K
Feature activation+0.000
rop
Tokenrop
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
kin
Tokenkin
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.214
memorial
Token memorial
Feature activation+0.000
s
Tokens
Feature activation+0.035
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
planned
Token planned
Feature activation+0.000
over
Token over
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.206
veterans
Token veterans
Feature activation+0.000
?
Token?
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
In
Token In
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.201
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
establishment
Tokenestablishment
Feature activation+0.000
sounding
Token sounding
Feature activation+0.000
rhetoric
Token rhetoric
Feature activation+0.000
carry
Token carry
Feature activation+0.000
on
Token on
Feature activation+0.000
Satoshi
Token Satoshi
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.106
dream
Token dream
Feature activation+0.000
of
Token of
Feature activation+0.000
decentral
Token decentral
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
problem
Token problem
Feature activation+0.000
isn
Token isn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+1.104
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
memory
Token memory
Feature activation+0.000
resembles
Token resembles
Feature activation+0.000
what
Token what
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.080
gone
Token gone
Feature activation+0.000
on
Token on
Feature activation+0.000
since
Token since
Feature activation+0.000
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.942
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
cont
Tokencont
Feature activation+0.000
enders
Tokenenders
Feature activation+0.000
.
Token.
Feature activation+0.000
do
Token do
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+0.837
say
Token say
Feature activation+0.000
is
Token is
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
says
Token says
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+0.551
do
Token do
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
55
Token55
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
µ
Tokenµ
Feature activation+0.000
m
Tokenm
Feature activation+0.328
pixel
Token pixel
Feature activation+0.000
size
Token size
Feature activation+0.000
)
Token)
Feature activation+0.000
with
Token with
Feature activation+0.000
laser
Token laser
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
34
Token34
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
µ
Tokenµ
Feature activation+0.000
m
Tokenm
Feature activation+0.184
pixel
Token pixel
Feature activation+0.000
size
Token size
Feature activation+0.000
)
Token)
Feature activation+0.000
with
Token with
Feature activation+0.000
O
Token O
Feature activation+0.000
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.214
memorial
Token memorial
Feature activation+0.000
s
Tokens
Feature activation+0.035
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
planned
Token planned
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
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
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
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

Top DFA by src position
MAX = 2.211

It
Token It
Feature activation-0.004
Top resid features:
Â
TokenÂ
Feature activation+0.325
Top resid features:
Ĵ
TokenĴ
Feature activation+0.075
Top resid features:
s
Tokens
Feature activation+0.463
Top resid features:
America
Token America
Feature activation+0.005
Top resid features:
Â
TokenÂ
Feature activation+1.943
Top resid features:
Ĵ
TokenĴ
Feature activation+0.234
Top resid features:
s
Tokens
Feature activation+0.496
Top resid features:
deb
Token deb
Feature activation+0.000
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation+0.000
Top resid features:
Ĵ
TokenĴ
Feature activation+0.049
Top resid features:
t
Tokent
Feature activation+0.035
Top resid features:
Trump
Token Trump
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.051
Top resid features:
It
Token It
Feature activation-0.007
Top resid features:
Â
TokenÂ
Feature activation+2.095
Top resid features:
Ĵ
TokenĴ
Feature activation+0.264
Top resid features:
s
Tokens
Feature activation+0.716
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
Â
TokenÂ
Feature activation+0.000
Top resid features:
Ĵ
TokenĴ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
K
Token K
Feature activation+0.012
Top resid features:
rop
Tokenrop
Feature activation-0.022
Top resid features:
ot
Tokenot
Feature activation+0.005
Top resid features:
kin
Tokenkin
Feature activation+0.010
Top resid features:
Â
TokenÂ
Feature activation+2.060
Top resid features:
Ĵ
TokenĴ
Feature activation+0.262
Top resid features:
s
Tokens
Feature activation+0.424
Top resid features:
View
Token View
Feature activation+0.000
Top resid features:
points
Tokenpoints
Feature activation+0.000
Top resid features:
Â
TokenÂ
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
officials
Token officials
Feature activation-0.008
Top resid features:
I
Token I
Feature activation+0.030
Top resid features:
can
Token can
Feature activation-0.022
Top resid features:
Â
TokenÂ
Feature activation+1.977
Top resid features:
Ĵ
TokenĴ
Feature activation+0.091
Top resid features:
t
Tokent
Feature activation+1.747
Top resid features:
help
Token help
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
ulation
Tokenulation
Feature activation-0.009
Top resid features:
Â
TokenÂ
Feature activation+0.362
Top resid features:
Ķ
TokenĶ
Feature activation+0.023
Top resid features:
?
Token?
Feature activation-0.000
Top resid features:
Marx
Token Marx
Feature activation+0.068
Top resid features:
Â
TokenÂ
Feature activation+1.802
Top resid features:
Ĵ
TokenĴ
Feature activation+0.208
Top resid features:
s
Tokens
Feature activation+0.568
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
K
Token K
Feature activation+0.000
Top resid features:
rop
Tokenrop
Feature activation+0.000
Top resid features:
WWII
Token WWII
Feature activation-0.082
Top resid features:
veterans
Token veterans
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
nation
Token nation
Feature activation+0.049
Top resid features:
Â
TokenÂ
Feature activation+2.141
Top resid features:
Ĵ
TokenĴ
Feature activation+0.242
Top resid features:
s
Tokens
Feature activation+1.320
Top resid features:
memorial
Token memorial
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
playing
Token playing
Feature activation+0.005
Top resid features:
politics
Token politics
Feature activation+0.001
Top resid features:
over
Token over
Feature activation-0.008
Top resid features:
our
Token our
Feature activation+0.016
Top resid features:
nation
Token nation
Feature activation+0.047
Top resid features:
Â
TokenÂ
Feature activation+2.078
Top resid features:
Ĵ
TokenĴ
Feature activation+0.214
Top resid features:
s
Tokens
Feature activation+0.537
Top resid features:
veterans
Token veterans
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Â
TokenÂ
Feature activation+0.000
Top resid features:
running
Token running
Feature activation+0.012
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
country
Token country
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.063
Top resid features:
Trump
Token Trump
Feature activation+0.008
Top resid features:
Â
TokenÂ
Feature activation+2.112
Top resid features:
Ĵ
TokenĴ
Feature activation+0.247
Top resid features:
s
Tokens
Feature activation+0.465
Top resid features:
anti
Token anti
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
establishment
Tokenestablishment
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
help
Token help
Feature activation+0.008
Top resid features:
carry
Token carry
Feature activation+0.068
Top resid features:
on
Token on
Feature activation-0.013
Top resid features:
Satoshi
Token Satoshi
Feature activation-0.063
Top resid features:
Â
TokenÂ
Feature activation+2.211
Top resid features:
Ĵ
TokenĴ
Feature activation+0.219
Top resid features:
s
Tokens
Feature activation+1.298
Top resid features:
dream
Token dream
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
decentral
Token decentral
Feature activation+0.000
Top resid features:
2015
Token2015
Feature activation+0.027
Top resid features:
.
Token.
Feature activation-0.044
Top resid features:
The
Token The
Feature activation-0.011
Top resid features:
problem
Token problem
Feature activation-0.016
Top resid features:
isn
Token isn
Feature activation+0.054
Top resid features:
Â
TokenÂ
Feature activation+1.907
Top resid features:
Ĵ
TokenĴ
Feature activation+0.070
Top resid features:
t
Tokent
Feature activation+0.654
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
Nothing
TokenNothing
Feature activation+0.016
Top resid features:
in
Token in
Feature activation-0.019
Top resid features:
memory
Token memory
Feature activation+0.003
Top resid features:
resembles
Token resembles
Feature activation-0.034
Top resid features:
what
Token what
Feature activation+0.010
Top resid features:
Â
TokenÂ
Feature activation+2.186
Top resid features:
Ĵ
TokenĴ
Feature activation+0.268
Top resid features:
s
Tokens
Feature activation+1.224
Top resid features:
gone
Token gone
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
season
Token season
Feature activation-0.030
Top resid features:
âĢ
TokenâĢ
Feature activation+0.034
Top resid features:
Ļ
TokenĻ
Feature activation+0.059
Top resid features:
Â
TokenÂ
Feature activation+0.551
Top resid features:
Ģ
TokenĢ
Feature activation+0.003
Top resid features:
Â
TokenÂ
Feature activation+1.587
Top resid features:
Ļ
TokenĻ
Feature activation+0.177
Top resid features:
s
Tokens
Feature activation+1.195
Top resid features:
non
Token non
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
cont
Tokencont
Feature activation+0.000
Top resid features:
Ĵ
TokenĴ
Feature activation-0.002
Top resid features:
t
Tokent
Feature activation+0.842
Top resid features:
do
Token do
Feature activation-0.005
Top resid features:
or
Token or
Feature activation-0.038
Top resid features:
doesn
Token doesn
Feature activation+0.046
Top resid features:
Â
TokenÂ
Feature activation+1.707
Top resid features:
Ĵ
TokenĴ
Feature activation+0.051
Top resid features:
t
Tokent
Feature activation+0.840
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
criticized
Token criticized
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.004
Top resid features:
or
Token or
Feature activation-0.036
Top resid features:
says
Token says
Feature activation+0.028
Top resid features:
or
Token or
Feature activation-0.048
Top resid features:
doesn
Token doesn
Feature activation+0.062
Top resid features:
Â
TokenÂ
Feature activation+1.707
Top resid features:
Ĵ
TokenĴ
Feature activation+0.052
Top resid features:
t
Tokent
Feature activation+1.560
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.004
Top resid features:
(
Token (
Feature activation-0.039
Top resid features:
1
Token1
Feature activation+0.026
Top resid features:
.
Token.
Feature activation-0.046
Top resid features:
55
Token55
Feature activation+0.015
Top resid features:
Â
TokenÂ
Feature activation+1.364
Top resid features:
µ
Tokenµ
Feature activation+0.018
Top resid features:
m
Tokenm
Feature activation+1.264
Top resid features:
pixel
Token pixel
Feature activation+0.000
Top resid features:
size
Token size
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
MP
TokenMP
Feature activation+0.023
Top resid features:
(
Token (
Feature activation-0.057
Top resid features:
1
Token1
Feature activation+0.022
Top resid features:
.
Token.
Feature activation-0.068
Top resid features:
34
Token34
Feature activation+0.001
Top resid features:
Â
TokenÂ
Feature activation+1.366
Top resid features:
µ
Tokenµ
Feature activation+0.015
Top resid features:
m
Tokenm
Feature activation+0.770
Top resid features:
pixel
Token pixel
Feature activation+0.000
Top resid features:
size
Token size
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
WWII
Token WWII
Feature activation-0.080
Top resid features:
veterans
Token veterans
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
nation
Token nation
Feature activation+0.013
Top resid features:
Â
TokenÂ
Feature activation+1.082
Top resid features:
Ĵ
TokenĴ
Feature activation+0.086
Top resid features:
s
Tokens
Feature activation+0.691
Top resid features:
memorial
Token memorial
Feature activation+0.032
Top resid features:
s
Tokens
Feature activation+0.693
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.144
Top resid features:
rik
Tokenrik
Feature activation-0.003
Top resid features:
ar
Tokenar
Feature activation+0.033
Top resid features:
said
Token said
Feature activation+0.051
Top resid features:
Saturday
Token Saturday
Feature activation+0.087
Top resid features:
.
Token.
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-0.014
Top resid features:
ar
Tokenar
Feature activation+0.035
Top resid features:
said
Token said
Feature activation+0.074
Top resid features:
Saturday
Token Saturday
Feature activation+0.041
Top resid features:
.
Token.
Feature activation-0.182
Top resid features:
Ċ
TokenĊ
Feature activation+0.658
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation+0.033
Top resid features:
said
Token said
Feature activation+0.096
Top resid features:
Saturday
Token Saturday
Feature activation+0.037
Top resid features:
.
Token.
Feature activation-0.148
Top resid features:
Ċ
TokenĊ
Feature activation+0.379
Top resid features:
Ċ
TokenĊ
Feature activation+0.507
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.14

Head 2: 0.03

Head 3: 0.25

Head 4: 0.10

Head 5: 0.08

Head 6: 0.06

Head 7: 0.11

Head 8: 0.04

Head 9: 0.05

Head 10: 0.07

Head 11: 0.02

Positive logits

actly3.29

--+3.23

ires3.14

ELD3.13

amples3.12

DAY3.11

inches3.08

Tac3.07

ighty2.94

============2.91

Swords2.90

˜2.88

onso2.84

`.2.82

2.82

ttp2.82

2.80

ouls2.79

Madrid2.78

Corinthians2.77

Negative logits

icter-4.75

satell-4.40

iage-4.05

wcs-3.75

contrace-3.68

brainer-3.64

yout-3.60

payoff-3.60

fined-3.55

carbohyd-3.52

certific-3.47

consolidation-3.46

synerg-3.46

enriched-3.42

raviolet-3.41

culosis-3.39

clipboard-3.36

boycot-3.35

swayed-3.34

matically-3.34

INTERVAL 1.325 - 1.473
CONTAINS 0.000%

Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.322
America
Token America
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.473
deb
Token deb
Feature activation+0.000
au
Tokenau
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
system
Token system
Feature activation+0.000
-
Token -
Feature activation+0.000

INTERVAL 1.178 - 1.325
CONTAINS 0.001%

rop
Tokenrop
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
kin
Tokenkin
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.295
View
Token View
Feature activation+0.000
points
Tokenpoints
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĺ
TokenĹ
Feature activation+0.000
A
TokenA
Feature activation+0.000
over
Token over
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.206
veterans
Token veterans
Feature activation+0.000
?
Token?
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
In
Token In
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.214
memorial
Token memorial
Feature activation+0.000
s
Tokens
Feature activation+0.035
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
planned
Token planned
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
?
Token?
Feature activation+0.000
Marx
Token Marx
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.221
and
Token and
Feature activation+0.000
K
Token K
Feature activation+0.000
rop
Tokenrop
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
kin
Tokenkin
Feature activation+0.000
officials
Token officials
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+1.230
help
Token help
Feature activation+0.000
but
Token but
Feature activation+0.000
think
Token think
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.031 - 1.178
CONTAINS 0.000%

carry
Token carry
Feature activation+0.000
on
Token on
Feature activation+0.000
Satoshi
Token Satoshi
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.106
dream
Token dream
Feature activation+0.000
of
Token of
Feature activation+0.000
decentral
Token decentral
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
,
Token,
Feature activation+0.000
memory
Token memory
Feature activation+0.000
resembles
Token resembles
Feature activation+0.000
what
Token what
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+1.080
gone
Token gone
Feature activation+0.000
on
Token on
Feature activation+0.000
since
Token since
Feature activation+0.000
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.000
The
Token The
Feature activation+0.000
problem
Token problem
Feature activation+0.000
isn
Token isn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+1.104
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000

INTERVAL 0.884 - 1.031
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.942
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
cont
Tokencont
Feature activation+0.000
enders
Tokenenders
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.736 - 0.884
CONTAINS 0.000%

do
Token do
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+0.837
say
Token say
Feature activation+0.000
is
Token is
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.589 - 0.736
CONTAINS 0.000%

INTERVAL 0.442 - 0.589
CONTAINS 0.000%

says
Token says
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
t
Tokent
Feature activation+0.551
do
Token do
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000

INTERVAL 0.295 - 0.442
CONTAINS 0.000%

1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
55
Token55
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
µ
Tokenµ
Feature activation+0.000
m
Tokenm
Feature activation+0.328
pixel
Token pixel
Feature activation+0.000
size
Token size
Feature activation+0.000
)
Token)
Feature activation+0.000
with
Token with
Feature activation+0.000
laser
Token laser
Feature activation+0.000

INTERVAL 0.147 - 0.295
CONTAINS 0.000%

1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
34
Token34
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
µ
Tokenµ
Feature activation+0.000
m
Tokenm
Feature activation+0.184
pixel
Token pixel
Feature activation+0.000
size
Token size
Feature activation+0.000
)
Token)
Feature activation+0.000
with
Token with
Feature activation+0.000
O
Token O
Feature activation+0.000

INTERVAL 0.000 - 0.147
CONTAINS 99.998%

flavor
Token flavor
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
few
Token few
Feature activation+0.000
places
Token places
Feature activation+0.000
spike
Token spike
Feature activation+0.000
it
Token it
Feature activation+0.000
with
Token with
Feature activation+0.000
liquor
Token liquor
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
commented
Token commented
Feature activation+0.000
yet
Token yet
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
possible
Token possible
Feature activation+0.000
origin
Token origin
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Quad
Token Quad
Feature activation+0.000
-
Token-
Feature activation+0.000
SP
TokenSP
Feature activation+0.000
I
TokenI
Feature activation+0.000
Flash
Token Flash
Feature activation+0.000
memory
Token memory
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Micro
Token Micro
Feature activation+0.000
SD
TokenSD
Feature activation+0.000
no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
essential
Token essential
Feature activation+0.000
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000
operation
Token operation
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Opp
TokenOpp
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
speech
Token speech
Feature activation+0.000
,
Token,
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
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 H0.3: (feature 2327)

TOP ACTIVATIONS
MAX = 1.128

of
Token of
Feature activation+0.000
drastically
Token drastically
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
government
Token government
Feature activation+0.000
programs
Token programs
Feature activation+0.000
such
Token such
Feature activation+1.128
as
Token as
Feature activation+0.000
food
Token food
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
--
Token --
Feature activation+0.000
despite
Token despite
Feature activation+0.000
urged
Token urged
Feature activation+0.000
Muslims
Token Muslims
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
follow
Token follow
Feature activation+0.000
such
Token such
Feature activation+1.126
"
Token "
Feature activation+0.000
evil
Tokenevil
Feature activation+0.000
"
Token"
Feature activation+0.000
ways
Token ways
Feature activation+0.000
at
Token at
Feature activation+0.000
ledger
Token ledger
Feature activation+0.000
and
Token and
Feature activation+0.000
payment
Token payment
Feature activation+0.000
network
Token network
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
such
Token such
Feature activation+1.120
as
Token as
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
how
Token how
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+1.061
matters
Token matters
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
Murray
Token Murray
Feature activation+0.000
has
Token has
Feature activation+0.000
simple
Token simple
Feature activation+0.000
link
Token link
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
image
Token image
Feature activation+0.000
such
Token such
Feature activation+1.055
as
Token as
Feature activation+0.000
Im
Token Im
Feature activation+0.000
gur
Tokengur
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+1.048
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
partial
Token partial
Feature activation+0.000
applied
Token applied
Feature activation+0.000
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.040
as
Token as
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
ides
Tokenides
Feature activation+0.000
,
Token,
Feature activation+0.000
expect
Token expect
Feature activation+0.000
creature
Token creature
Feature activation+0.000
com
Token com
Feature activation+0.000
forts
Tokenforts
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.039
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
72
Token 72
Feature activation+0.000
-
Token-
Feature activation+0.000
foot
Tokenfoot
Feature activation+0.000
record
Token record
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
Perth
Token Perth
Feature activation+0.000
has
Token has
Feature activation+0.000
such
Token such
Feature activation+1.021
a
Token a
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
of
Token of
Feature activation+0.000
isolation
Token isolation
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
standard
Token standard
Feature activation+0.000
playbook
Token playbook
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+1.009
operations
Token operations
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
manner
Token manner
Feature activation+0.000
of
Token of
Feature activation+0.000
death
Token death
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
categories
Token categories
Feature activation+0.000
such
Token such
Feature activation+1.003
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
natural
Tokennatural
Feature activation+0.000
cause
Token cause
Feature activation+0.000
,"
Token,"
Feature activation+0.000
000
Token000
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
such
Token such
Feature activation+1.002
any
Token any
Feature activation+0.000
stories
Token stories
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
coastline
Token coastline
Feature activation+0.000
dragon
Token dragon
Feature activation+0.000
),
Token),
Feature activation+0.000
represents
Token represents
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
such
Token such
Feature activation+0.995
discovery
Token discovery
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ar
TokenAr
Feature activation+0.000
te
Tokente
Feature activation+0.000
facts
Tokenfacts
Feature activation+0.000
such
Token such
Feature activation+0.987
as
Token as
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
,
Token,
Feature activation+0.000
sled
Token sled
Feature activation+0.000
ges
Tokenges
Feature activation+0.000
match
Token match
Feature activation+0.000
cricket
Token cricket
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.982
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
public
Token public
Feature activation+0.000
image
Token image
Feature activation+0.000
had
Token had
Feature activation+0.000
taken
Token taken
Feature activation+0.000
such
Token such
Feature activation+0.978
a
Token a
Feature activation+0.000
hit
Token hit
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
days
Token days
Feature activation+0.000
water
Token water
Feature activation+0.000
reuse
Token reuse
Feature activation+0.000
systems
Token systems
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+0.977
a
Token a
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
such
Token such
Feature activation+0.969
crude
Token crude
Feature activation+0.000
excuses
Token excuses
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
touted
Token touted
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
such
Token such
Feature activation+0.969
a
Token a
Feature activation+0.000
lucrative
Token lucrative
Feature activation+0.000
practice
Token practice
Feature activation+0.000
go
Token go
Feature activation+0.000
up
Token up
Feature activation+0.000
rain
Token rain
Feature activation+0.000
coats
Token coats
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
characters
Token characters
Feature activation+0.000
such
Token such
Feature activation+0.959
as
Token as
Feature activation+0.000
Min
Token Min
Feature activation+0.000
nie
Tokennie
Feature activation+0.000
Mouse
Token Mouse
Feature activation+0.000
stay
Token stay
Feature activation+0.000

Top DFA by src position
MAX = 8.423

of
Token of
Feature activation-0.072
Top resid features:
drastically
Token drastically
Feature activation-0.054
Top resid features:
reducing
Token reducing
Feature activation+0.015
Top resid features:
government
Token government
Feature activation+0.054
Top resid features:
programs
Token programs
Feature activation+0.072
Top resid features:
such
Token such
Feature activation+8.308
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
food
Token food
Feature activation+0.000
Top resid features:
stamps
Token stamps
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
despite
Token despite
Feature activation+0.000
Top resid features:
urged
Token urged
Feature activation-0.022
Top resid features:
Muslims
Token Muslims
Feature activation-0.109
Top resid features:
not
Token not
Feature activation+0.032
Top resid features:
to
Token to
Feature activation-0.085
Top resid features:
follow
Token follow
Feature activation-0.001
Top resid features:
such
Token such
Feature activation+8.409
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
evil
Tokenevil
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
ways
Token ways
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
ledger
Token ledger
Feature activation-0.057
Top resid features:
and
Token and
Feature activation-0.077
Top resid features:
payment
Token payment
Feature activation-0.014
Top resid features:
network
Token network
Feature activation+0.009
Top resid features:
technologies
Token technologies
Feature activation+0.187
Top resid features:
such
Token such
Feature activation+8.041
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.007
Top resid features:
liberal
Token liberal
Feature activation-0.033
Top resid features:
policymakers
Token policymakers
Feature activation-0.072
Top resid features:
think
Token think
Feature activation+0.032
Top resid features:
about
Token about
Feature activation+0.063
Top resid features:
such
Token such
Feature activation+8.023
Top resid features:
matters
Token matters
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
Murray
Token Murray
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
simple
Token simple
Feature activation-0.043
Top resid features:
link
Token link
Feature activation-0.043
Top resid features:
to
Token to
Feature activation-0.088
Top resid features:
your
Token your
Feature activation+0.027
Top resid features:
image
Token image
Feature activation-0.049
Top resid features:
such
Token such
Feature activation+8.391
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Im
Token Im
Feature activation+0.000
Top resid features:
gur
Tokengur
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.069
Top resid features:
air
Token air
Feature activation-0.022
Top resid features:
resistance
Token resistance
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.063
Top resid features:
in
Token in
Feature activation-0.090
Top resid features:
such
Token such
Feature activation+8.355
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
partial
Token partial
Feature activation+0.000
Top resid features:
applied
Token applied
Feature activation-0.044
Top resid features:
to
Token to
Feature activation-0.088
Top resid features:
biological
Token biological
Feature activation-0.006
Top resid features:
compounds
Token compounds
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.043
Top resid features:
such
Token such
Feature activation+6.776
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
nucle
Token nucle
Feature activation+0.000
Top resid features:
ot
Tokenot
Feature activation+0.000
Top resid features:
ides
Tokenides
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
expect
Token expect
Feature activation-0.056
Top resid features:
creature
Token creature
Feature activation-0.126
Top resid features:
com
Token com
Feature activation+0.093
Top resid features:
forts
Tokenforts
Feature activation-0.039
Top resid features:
,
Token,
Feature activation-0.045
Top resid features:
such
Token such
Feature activation+8.320
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
72
Token 72
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
foot
Tokenfoot
Feature activation+0.000
Top resid features:
record
Token record
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
And
Token And
Feature activation+0.005
Top resid features:
Perth
Token Perth
Feature activation-0.062
Top resid features:
has
Token has
Feature activation-0.111
Top resid features:
such
Token such
Feature activation+8.294
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
feeling
Token feeling
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
isolation
Token isolation
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.124
Top resid features:
a
Token a
Feature activation-0.076
Top resid features:
standard
Token standard
Feature activation-0.074
Top resid features:
playbook
Token playbook
Feature activation-0.114
Top resid features:
for
Token for
Feature activation-0.018
Top resid features:
such
Token such
Feature activation+8.423
Top resid features:
operations
Token operations
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
manner
Token manner
Feature activation-0.009
Top resid features:
of
Token of
Feature activation-0.067
Top resid features:
death
Token death
Feature activation-0.036
Top resid features:
beyond
Token beyond
Feature activation+0.067
Top resid features:
categories
Token categories
Feature activation-0.001
Top resid features:
such
Token such
Feature activation+8.154
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
natural
Tokennatural
Feature activation+0.000
Top resid features:
cause
Token cause
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
000
Token000
Feature activation-0.029
Top resid features:
years
Token years
Feature activation-0.041
Top resid features:
ago
Token ago
Feature activation-0.044
Top resid features:
and
Token and
Feature activation-0.068
Top resid features:
as
Token as
Feature activation+0.122
Top resid features:
such
Token such
Feature activation+8.043
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
coastline
Token coastline
Feature activation+0.000
Top resid features:
dragon
Token dragon
Feature activation-0.062
Top resid features:
),
Token),
Feature activation+0.081
Top resid features:
represents
Token represents
Feature activation-0.090
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
third
Token third
Feature activation-0.050
Top resid features:
such
Token such
Feature activation+6.811
Top resid features:
discovery
Token discovery
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.049
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
Ar
TokenAr
Feature activation+0.011
Top resid features:
te
Tokente
Feature activation-0.005
Top resid features:
facts
Tokenfacts
Feature activation-0.077
Top resid features:
such
Token such
Feature activation+8.389
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
clothes
Token clothes
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
sled
Token sled
Feature activation+0.000
Top resid features:
ges
Tokenges
Feature activation+0.000
Top resid features:
match
Token match
Feature activation-0.044
Top resid features:
cricket
Token cricket
Feature activation-0.116
Top resid features:
in
Token in
Feature activation-0.066
Top resid features:
front
Token front
Feature activation-0.059
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
such
Token such
Feature activation+8.337
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
large
Token large
Feature activation+0.000
Top resid features:
crowd
Token crowd
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.041
Top resid features:
public
Token public
Feature activation-0.028
Top resid features:
image
Token image
Feature activation-0.042
Top resid features:
had
Token had
Feature activation-0.120
Top resid features:
taken
Token taken
Feature activation-0.052
Top resid features:
such
Token such
Feature activation+8.411
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hit
Token hit
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
recent
Token recent
Feature activation+0.000
Top resid features:
days
Token days
Feature activation+0.000
Top resid features:
water
Token water
Feature activation-0.063
Top resid features:
reuse
Token reuse
Feature activation-0.040
Top resid features:
systems
Token systems
Feature activation+0.018
Top resid features:
necessary
Token necessary
Feature activation+0.026
Top resid features:
for
Token for
Feature activation+0.073
Top resid features:
such
Token such
Feature activation+7.889
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
project
Token project
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
etc
Token etc
Feature activation-0.090
Top resid features:
.
Token.
Feature activation-0.064
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
Other
TokenOther
Feature activation-0.025
Top resid features:
such
Token such
Feature activation+8.301
Top resid features:
crude
Token crude
Feature activation+0.000
Top resid features:
excuses
Token excuses
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
touted
Token touted
Feature activation+0.000
Top resid features:
too
Token too
Feature activation-0.043
Top resid features:
much
Token much
Feature activation-0.015
Top resid features:
money
Token money
Feature activation-0.037
Top resid features:
to
Token to
Feature activation-0.120
Top resid features:
let
Token let
Feature activation-0.037
Top resid features:
such
Token such
Feature activation+8.309
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lucrative
Token lucrative
Feature activation+0.000
Top resid features:
practice
Token practice
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
rain
Token rain
Feature activation-0.076
Top resid features:
coats
Token coats
Feature activation-0.078
Top resid features:
,
Token,
Feature activation-0.051
Top resid features:
and
Token and
Feature activation-0.060
Top resid features:
characters
Token characters
Feature activation-0.001
Top resid features:
such
Token such
Feature activation+8.220
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Min
Token Min
Feature activation+0.000
Top resid features:
nie
Tokennie
Feature activation+0.000
Top resid features:
Mouse
Token Mouse
Feature activation+0.000
Top resid features:
stay
Token stay
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.22

Head 2: 0.02

Head 3: 0.25

Head 4: 0.08

Head 5: 0.14

Head 6: 0.03

Head 7: 0.05

Head 8: 0.03

Head 9: 0.07

Head 10: 0.06

Head 11: 0.03

Positive logits

azeera3.45

carbohyd3.20

worldly3.19

vae3.09

unnecess3.06

��2.97

localized2.88

etheless2.88

merce2.85

raviolet2.82

アル2.74

redistributed2.73

endars2.72

ancies2.71

profits2.70

permissible2.67

oğan2.67

recourse2.66

abundantly2.63

predec2.62

Negative logits

Crush-2.91

Cambodia-2.84

Bohem-2.79

Ridge-2.67

Drum-2.51

Beach-2.47

Claw-2.46

Champ-2.43

Gorge-2.42

Jarvis-2.41

Rou-2.40

Pier-2.40

Wheel-2.39

Chrys-2.37

Cyn-2.37

Bunny-2.36

Fr-2.35

ston-2.31

Franc-2.30

Hearth-2.30

INTERVAL 1.015 - 1.128
CONTAINS 0.001%

the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+1.048
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
partial
Token partial
Feature activation+0.000
expect
Token expect
Feature activation+0.000
creature
Token creature
Feature activation+0.000
com
Token com
Feature activation+0.000
forts
Tokenforts
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.039
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
72
Token 72
Feature activation+0.000
-
Token-
Feature activation+0.000
foot
Tokenfoot
Feature activation+0.000
applied
Token applied
Feature activation+0.000
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.040
as
Token as
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
ides
Tokenides
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+1.061
matters
Token matters
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
Murray
Token Murray
Feature activation+0.000
has
Token has
Feature activation+0.000
of
Token of
Feature activation+0.000
drastically
Token drastically
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
government
Token government
Feature activation+0.000
programs
Token programs
Feature activation+0.000
such
Token such
Feature activation+1.128
as
Token as
Feature activation+0.000
food
Token food
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
--
Token --
Feature activation+0.000
despite
Token despite
Feature activation+0.000

INTERVAL 0.902 - 1.015
CONTAINS 0.003%

rain
Token rain
Feature activation+0.000
coats
Token coats
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
characters
Token characters
Feature activation+0.000
such
Token such
Feature activation+0.959
as
Token as
Feature activation+0.000
Min
Token Min
Feature activation+0.000
nie
Tokennie
Feature activation+0.000
Mouse
Token Mouse
Feature activation+0.000
stay
Token stay
Feature activation+0.000
manner
Token manner
Feature activation+0.000
of
Token of
Feature activation+0.000
death
Token death
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
categories
Token categories
Feature activation+0.000
such
Token such
Feature activation+1.003
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
natural
Tokennatural
Feature activation+0.000
cause
Token cause
Feature activation+0.000
,"
Token,"
Feature activation+0.000
000
Token000
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
such
Token such
Feature activation+1.002
any
Token any
Feature activation+0.000
stories
Token stories
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
coastline
Token coastline
Feature activation+0.000
also
Token also
Feature activation+0.000
taking
Token taking
Feature activation+0.000
offline
Token offline
Feature activation+0.000
critical
Token critical
Feature activation+0.000
systems
Token systems
Feature activation+0.000
such
Token such
Feature activation+0.957
as
Token as
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
response
Token response
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
psychotic
Token psychotic
Feature activation+0.000
disorders
Token disorders
Feature activation+0.000
such
Token such
Feature activation+0.912
as
Token as
Feature activation+0.000
schizophrenia
Token schizophrenia
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
However
Token However
Feature activation+0.000

INTERVAL 0.789 - 0.902
CONTAINS 0.002%

IP
TokenIP
Feature activation+0.000
documents
Token documents
Feature activation+0.000
,
Token,
Feature activation+0.000
GMOs
Token GMOs
Feature activation+0.000
are
Token are
Feature activation+0.000
such
Token such
Feature activation+0.848
a
Token a
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
area
Token area
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
of
Token of
Feature activation+0.000
eternity
Token eternity
Feature activation+0.000
.
Token.
Feature activation+0.000
Training
Token Training
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.885
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
misinterpret
Token misinterpret
Feature activation+0.000
an
Token an
Feature activation+0.000
airliner
Token airliner
Feature activation+0.000
at
Token at
Feature activation+0.000
such
Token such
Feature activation+0.879
height
Token height
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
threat
Token threat
Feature activation+0.000
,
Token,
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
shame
Token shame
Feature activation+0.000
if
Token if
Feature activation+0.000
such
Token such
Feature activation+0.898
an
Token an
Feature activation+0.000
important
Token important
Feature activation+0.000
question
Token question
Feature activation+0.000
gets
Token gets
Feature activation+0.000
caught
Token caught
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
dare
Token dare
Feature activation+0.000
calling
Token calling
Feature activation+0.000
it
Token it
Feature activation+0.000
such
Token such
Feature activation+0.869
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
story
Token story
Feature activation+0.000
began
Token began
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.677 - 0.789
CONTAINS 0.001%

know
Token know
Feature activation+0.000
was
Token was
Feature activation+0.000
why
Token why
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
such
Token such
Feature activation+0.710
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
deal
Token deal
Feature activation+0.000
in
Token in
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
city
Token city
Feature activation+0.000
ordinance
Token ordinance
Feature activation+0.000
for
Token for
Feature activation+0.000
card
Token card
Feature activation+0.000
holders
Tokenholders
Feature activation+0.000
such
Token such
Feature activation+0.786
as
Token as
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
factors
Token factors
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
blame
Token blame
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.764
as
Token as
Feature activation+0.000
electromagnetic
Token electromagnetic
Feature activation+0.000
solar
Token solar
Feature activation+0.000
activity
Token activity
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
my
Token my
Feature activation+0.000
dreams
Token dreams
Feature activation+0.000
at
Token at
Feature activation+0.000
such
Token such
Feature activation+0.690
a
Token a
Feature activation+0.000
prestigious
Token prestigious
Feature activation+0.000
University
Token University
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+0.000
private
Token private
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.785
as
Token as
Feature activation+0.000
Yam
Token Yam
Feature activation+0.000
cha
Tokencha
Feature activation+0.000
saying
Token saying
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.564 - 0.677
CONTAINS 0.002%

based
Tokenbased
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
reach
Token reach
Feature activation+0.000
such
Token such
Feature activation+0.566
an
Token an
Feature activation+0.000
altitude
Token altitude
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
options
Token options
Feature activation+0.000
for
Token for
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.653
as
Token as
Feature activation+0.000
other
Token other
Feature activation+0.000
locations
Token locations
Feature activation+0.000
in
Token in
Feature activation+0.000
or
Token or
Feature activation+0.000
Chip
Token Chip
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
,
Token,
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
such
Token such
Feature activation+0.610
conspiracy
Token conspiracy
Feature activation+0.000
theory
Token theory
Feature activation+0.000
feeds
Token feeds
Feature activation+0.000
a
Token a
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
Union
Token Union
Feature activation+0.000
in
Token in
Feature activation+0.000
connection
Token connection
Feature activation+0.000
with
Token with
Feature activation+0.000
any
Token any
Feature activation+0.000
such
Token such
Feature activation+0.652
futile
Token futile
Feature activation+0.000
visit
Token visit
Feature activation+0.000
shall
Token shall
Feature activation+0.000
be
Token be
Feature activation+0.000
paid
Token paid
Feature activation+0.000
',
Token',
Feature activation+0.000
but
Token but
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+0.633
equivalent
Token equivalent
Feature activation+0.000
in
Token in
Feature activation+0.000
English
Token English
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 0.451 - 0.564
CONTAINS 0.001%

icit
Tokenicit
Feature activation+0.000
or
Token or
Feature activation+0.000
illegitimate
Token illegitimate
Feature activation+0.000
ends
Token ends
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.493
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
theft
Token theft
Feature activation+0.000
of
Token of
Feature activation+0.000
trade
Token trade
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+0.469
thing
Token thing
Feature activation+0.000
as
Token as
Feature activation+0.000
bisexual
Token bisexual
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
."
Token."
Feature activation+0.000
sex
Token sex
Feature activation+0.000
shall
Token shall
Feature activation+0.000
be
Token be
Feature activation+0.000
comparable
Token comparable
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+0.477
facilities
Token facilities
Feature activation+0.000
provided
Token provided
Feature activation+0.000
for
Token for
Feature activation+0.000
students
Token students
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
observ
Token observ
Feature activation+0.000
atories
Tokenatories
Feature activation+0.000
(
Token (
Feature activation+0.000
such
Tokensuch
Feature activation+0.457
as
Token as
Feature activation+0.000
Plan
Token Plan
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
and
Token and
Feature activation+0.000
WM
Token WM
Feature activation+0.000
aws
Tokenaws
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
kingdom
Token kingdom
Feature activation+0.000
enforcing
Token enforcing
Feature activation+0.000
such
Token such
Feature activation+0.499
restrictions
Token restrictions
Feature activation+0.000
on
Token on
Feature activation+0.000
women
Token women
Feature activation+0.000
"
Token "
Feature activation+0.000
are
Tokenare
Feature activation+0.000

INTERVAL 0.338 - 0.451
CONTAINS 0.001%

belief
Token belief
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.445
force
Token force
Feature activation+0.000
poses
Token poses
Feature activation+0.000
an
Token an
Feature activation+0.000
imminent
Token imminent
Feature activation+0.000
danger
Token danger
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
provide
Token provide
Feature activation+0.000
us
Token us
Feature activation+0.000
with
Token with
Feature activation+0.000
such
Token such
Feature activation+0.446
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Examples
TokenExamples
Feature activation+0.000
:
Token:
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
and
Token and
Feature activation+0.000
thinkers
Token thinkers
Feature activation+0.000
from
Token from
Feature activation+0.000
companies
Token companies
Feature activation+0.000
such
Token such
Feature activation+0.425
as
Token as
Feature activation+0.000
Frog
Token Frog
Feature activation+0.000
,
Token,
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
te
Tokente
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token -
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.391
as
Token as
Feature activation+0.000
rou
Token rou
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
and
Token and
Feature activation+0.000
gou
Token gou
Feature activation+0.000
in
Token in
Feature activation+0.000
Oklahoma
Token Oklahoma
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
such
Token such
Feature activation+0.388
visit
Token visit
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
president
Token president
Feature activation+0.000

INTERVAL 0.226 - 0.338
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
such
Token such
Feature activation+0.332
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
N
Token N
Feature activation+0.000
convention
Token convention
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
such
Token such
Feature activation+0.311
changes
Token changes
Feature activation+0.000
are
Token are
Feature activation+0.000
made
Token made
Feature activation+0.000
nightly
Token nightly
Feature activation+0.000
by
Token by
Feature activation+0.000
and
Token and
Feature activation+0.000
homemade
Token homemade
Feature activation+0.000
su
Token su
Feature activation+0.000
gary
Tokengary
Feature activation+0.000
drinks
Token drinks
Feature activation+0.000
such
Token such
Feature activation+0.314
as
Token as
Feature activation+0.000
fres
Token fres
Feature activation+0.000
cas
Tokencas
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
could
Token could
Feature activation+0.000
energy
Token energy
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
such
Token such
Feature activation+0.297
as
Token as
Feature activation+0.000
wind
Token wind
Feature activation+0.000
and
Token and
Feature activation+0.000
solar
Token solar
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.000
directed
Token directed
Feature activation+0.000
Fer
Token Fer
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.285
comedy
Token comedy
Feature activation+0.000
classics
Token classics
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.113 - 0.226
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Psychic
Token Psychic
Feature activation+0.000
medium
Token medium
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.177
as
Token as
Feature activation+0.000
Tyler
Token Tyler
Feature activation+0.000
Henry
Token Henry
Feature activation+0.000
,
Token,
Feature activation+0.000
John
Token John
Feature activation+0.000
credible
Token credible
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
efficacy
Token efficacy
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.204
as
Token as
Feature activation+0.000
home
Token home
Feature activation+0.000
opathic
Tokenopathic
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.000
s
Tokens
Feature activation+0.000
case
Token case
Feature activation+0.000
take
Token take
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.223
injust
Token injust
Feature activation+0.000
ices
Tokenices
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
typically
Token typically
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
such
Token such
Feature activation+0.176
a
Token a
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
environment
Token environment
Feature activation+0.000
on
Token on
Feature activation+0.000
college
Token college
Feature activation+0.000
That
Token That
Feature activation+0.000
track
Token track
Feature activation+0.000
pad
Tokenpad
Feature activation+0.000
supports
Token supports
Feature activation+0.000
gestures
Token gestures
Feature activation+0.000
such
Token such
Feature activation+0.183
as
Token as
Feature activation+0.000
swipe
Token swipe
Feature activation+0.000
and
Token and
Feature activation+0.000
double
Token double
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.000 - 0.113
CONTAINS 99.985%

Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
commodity
Token commodity
Feature activation+0.000
like
Token like
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+0.000
natural
Token natural
Feature activation+0.000
gas
Token gas
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
like
Token like
Feature activation+0.000
there
Token there
Feature activation+0.000
tagged
Token tagged
Feature activation+0.000
him
Token him
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
they
Token they
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
tackle
Token tackle
Feature activation+0.000
store
Tokenstore
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
chain
Token chain
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
lineup
Token lineup
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
a
Token a
Feature activation+0.000
willingness
Token willingness
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
risks
Token risks
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
the
Token the
Feature activation+0.000
concept
Token concept
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 H0.3: (feature 181)

TOP ACTIVATIONS
MAX = 1.768

"
Token "
Feature activation+0.000
el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+1.768
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
large
Tokenlarge
Feature activation+0.000
deer
Token deer
Feature activation+0.000
"
Token"
Feature activation+0.000
coins
Tokencoins
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
referred
Token referred
Feature activation+1.704
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
The
Token The
Feature activation+0.000
document
Token document
Feature activation+0.000
referred
Token referred
Feature activation+1.699
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
seven
Token seven
Feature activation+0.000
gifts
Token gifts
Feature activation+0.000
someone
Token someone
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+0.000
this
Token this
Feature activation+0.000
word
Token word
Feature activation+0.000
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+1.676
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
of
Token of
Feature activation+0.000
music
Token music
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
also
Token also
Feature activation+0.000
referred
Token referred
Feature activation+1.648
to
Token to
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
security
Token security
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
sparked
Token sparked
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
press
Token press
Feature activation+0.000
would
Token would
Feature activation+0.000
literally
Token literally
Feature activation+0.000
refer
Token refer
Feature activation+1.647
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
delivering
Token delivering
Feature activation+0.000
what
Token what
Feature activation+0.000
Everton
Token Everton
Feature activation+0.000
FC
Token FC
Feature activation+0.000
refer
Token refer
Feature activation+1.637
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Ros
Token Ros
Feature activation+0.000
k
Tokenk
Feature activation+0.000
am
Tokenam
Feature activation+0.000
is
Token is
Feature activation+0.000
often
Token often
Feature activation+0.000
referred
Token referred
Feature activation+1.634
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
king
Token king
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
referred
Token referred
Feature activation+1.624
to
Token to
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
verses
Token verses
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
ordinary
Token ordinary
Feature activation+0.000
English
Token English
Feature activation+0.000
to
Token to
Feature activation+0.000
collectively
Token collectively
Feature activation+0.000
refer
Token refer
Feature activation+1.615
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
Euph
Token Euph
Feature activation+0.000
the
Token the
Feature activation+0.000
remaining
Token remaining
Feature activation+0.000
territory
Token territory
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
referred
Token referred
Feature activation+1.614
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
East
Token East
Feature activation+0.000
Gh
Token Gh
Feature activation+0.000
out
Tokenout
Feature activation+0.000
including
Token including
Feature activation+0.000
surgical
Token surgical
Feature activation+0.000
removal
Token removal
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
referred
Token referred
Feature activation+1.599
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
partial
Token partial
Feature activation+0.000
hep
Token hep
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
ill
Token ill
Feature activation+0.000
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
phrases
Token phrases
Feature activation+0.000
referred
Token referred
Feature activation+1.589
to
Token to
Feature activation+0.000
Keystone
Token Keystone
Feature activation+0.000
XL
Token XL
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
direction
Token direction
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
refer
Token refer
Feature activation+1.577
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Director
Token Director
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
who
Token who
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
said
Token said
Feature activation+0.000
referred
Token referred
Feature activation+1.565
U
Token U
Feature activation+0.000
rets
Tokenrets
Feature activation+0.000
ky
Tokenky
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
prosecute
Token prosecute
Feature activation+0.000
Mull
Token Mull
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
and
Token and
Feature activation+0.000
referred
Token referred
Feature activation+1.555
the
Token the
Feature activation+0.000
case
Token case
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
Secondly
TokenSecondly
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
is
Token is
Feature activation+0.000
referred
Token referred
Feature activation+1.517
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
La
TokenLa
Feature activation+0.000
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+0.000
referred
Token referred
Feature activation+1.490
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
Dis
Token Dis
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
refer
Token refer
Feature activation+1.476
new
Token new
Feature activation+0.000
land
Token land
Feature activation+0.000
owners
Token owners
Feature activation+0.000
.
Token.
Feature activation+0.000
Know
Token Know
Feature activation+0.000
adv
Tokenadv
Feature activation+0.000
yd
Tokenyd
Feature activation+0.000
as
Tokenas
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
refers
Token refers
Feature activation+1.434
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 4.218

"
Token "
Feature activation+0.006
Top resid features:
el
Tokenel
Feature activation+0.001
Top resid features:
k
Tokenk
Feature activation+0.005
Top resid features:
"
Token"
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
refer
Token refer
Feature activation+4.138
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
large
Tokenlarge
Feature activation+0.000
Top resid features:
deer
Token deer
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
coins
Tokencoins
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
com
Tokencom
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
referred
Token referred
Feature activation+4.145
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
definition
Token definition
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
The
Token The
Feature activation+0.028
Top resid features:
document
Token document
Feature activation+0.059
Top resid features:
referred
Token referred
Feature activation+4.007
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.000
Top resid features:
gifts
Token gifts
Feature activation+0.000
Top resid features:
someone
Token someone
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.007
Top resid features:
used
Token used
Feature activation+0.019
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
word
Token word
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
refer
Token refer
Feature activation+4.171
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
music
Token music
Feature activation+0.000
Top resid features:
."
Token."
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
He
TokenHe
Feature activation+0.038
Top resid features:
also
Token also
Feature activation+0.042
Top resid features:
referred
Token referred
Feature activation+4.124
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
renewed
Token renewed
Feature activation+0.000
Top resid features:
security
Token security
Feature activation+0.000
Top resid features:
concerns
Token concerns
Feature activation+0.000
Top resid features:
sparked
Token sparked
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.002
Top resid features:
the
Tokenthe
Feature activation+0.008
Top resid features:
press
Token press
Feature activation-0.005
Top resid features:
would
Token would
Feature activation+0.076
Top resid features:
literally
Token literally
Feature activation+0.121
Top resid features:
refer
Token refer
Feature activation+4.007
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation+0.007
Top resid features:
delivering
Token delivering
Feature activation-0.013
Top resid features:
what
Token what
Feature activation+0.008
Top resid features:
Everton
Token Everton
Feature activation-0.038
Top resid features:
FC
Token FC
Feature activation-0.008
Top resid features:
refer
Token refer
Feature activation+4.218
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
Ros
Token Ros
Feature activation-0.003
Top resid features:
k
Tokenk
Feature activation+0.004
Top resid features:
am
Tokenam
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.039
Top resid features:
often
Token often
Feature activation+0.127
Top resid features:
referred
Token referred
Feature activation+3.934
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
king
Token king
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
United
Token United
Feature activation-0.001
Top resid features:
States
Token States
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
They
Token They
Feature activation+0.029
Top resid features:
referred
Token referred
Feature activation+4.121
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
numerous
Token numerous
Feature activation+0.000
Top resid features:
verses
Token verses
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
ordinary
Token ordinary
Feature activation+0.034
Top resid features:
English
Token English
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
collectively
Token collectively
Feature activation+0.028
Top resid features:
refer
Token refer
Feature activation+3.951
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Euph
Token Euph
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
remaining
Token remaining
Feature activation+0.003
Top resid features:
territory
Token territory
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
also
Token also
Feature activation+0.044
Top resid features:
referred
Token referred
Feature activation+4.127
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
East
Token East
Feature activation+0.000
Top resid features:
Gh
Token Gh
Feature activation+0.000
Top resid features:
out
Tokenout
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.013
Top resid features:
surgical
Token surgical
Feature activation-0.043
Top resid features:
removal
Token removal
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
also
Token also
Feature activation+0.042
Top resid features:
referred
Token referred
Feature activation+4.112
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
partial
Token partial
Feature activation+0.000
Top resid features:
hep
Token hep
Feature activation+0.000
Top resid features:
ate
Tokenate
Feature activation+0.000
Top resid features:
ill
Token ill
Feature activation+0.011
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
f
Tokenf
Feature activation+0.003
Top resid features:
ated
Tokenated
Feature activation+0.002
Top resid features:
phrases
Token phrases
Feature activation+0.010
Top resid features:
referred
Token referred
Feature activation+4.105
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Keystone
Token Keystone
Feature activation+0.000
Top resid features:
XL
Token XL
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
different
Token different
Feature activation-0.005
Top resid features:
direction
Token direction
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.012
Top resid features:
what
Token what
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.020
Top resid features:
refer
Token refer
Feature activation+4.095
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
Director
Token Director
Feature activation-0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.020
Top resid features:
who
Token who
Feature activation+0.016
Top resid features:
Bernie
Token Bernie
Feature activation-0.002
Top resid features:
said
Token said
Feature activation-0.006
Top resid features:
referred
Token referred
Feature activation+4.094
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
rets
Tokenrets
Feature activation+0.000
Top resid features:
ky
Tokenky
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
prosecute
Token prosecute
Feature activation+0.021
Top resid features:
Mull
Token Mull
Feature activation+0.006
Top resid features:
igan
Tokenigan
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
referred
Token referred
Feature activation+3.850
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
City
Token City
Feature activation+0.000
Top resid features:
Secondly
TokenSecondly
Feature activation+0.069
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
hotel
Token hotel
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.052
Top resid features:
referred
Token referred
Feature activation+4.024
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
media
Token media
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
La
TokenLa
Feature activation+0.011
Top resid features:
H
TokenH
Feature activation+0.004
Top resid features:
ood
Tokenood
Feature activation+0.000
Top resid features:
referred
Token referred
Feature activation+3.888
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Texas
Token Texas
Feature activation+0.000
Top resid features:
Dis
Token Dis
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
people
Token people
Feature activation+0.016
Top resid features:
who
Token who
Feature activation+0.040
Top resid features:
refer
Token refer
Feature activation+3.835
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
land
Token land
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Know
Token Know
Feature activation+0.000
Top resid features:
adv
Tokenadv
Feature activation+0.037
Top resid features:
yd
Tokenyd
Feature activation-0.002
Top resid features:
as
Tokenas
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
refers
Token refers
Feature activation+3.933
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
2001
Token 2001
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.20

Head 2: 0.02

Head 3: 0.24

Head 4: 0.13

Head 5: 0.13

Head 6: 0.03

Head 7: 0.05

Head 8: 0.04

Head 9: 0.04

Head 10: 0.07

Head 11: 0.03

Positive logits

rences4.70

��4.60

4.56

charact3.74

ogly3.73

entious3.72

3.68

warr3.67

flows3.66

umni3.60

="#3.59

xual3.57

ebted3.48

="/3.47

3.47

interstitial3.44

tenance3.43

ames3.40

irection3.39

ragon3.37

Negative logits

aido-3.78

Dome-3.54

artney-3.48

bern-3.38

alach-3.37

Bees-3.37

estern-3.36

Philly-3.27

owered-3.26

aiman-3.13

Nationals-3.11

cffff-3.11

ntil-3.10

Bed-3.08

zanne-3.06

apo-3.05

rolet-3.03

ortium-3.00

Helsinki-3.00

asted-3.00

INTERVAL 1.591 - 1.768
CONTAINS 0.001%

.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
The
Token The
Feature activation+0.000
document
Token document
Feature activation+0.000
referred
Token referred
Feature activation+1.699
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
seven
Token seven
Feature activation+0.000
gifts
Token gifts
Feature activation+0.000
someone
Token someone
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
delivering
Token delivering
Feature activation+0.000
what
Token what
Feature activation+0.000
Everton
Token Everton
Feature activation+0.000
FC
Token FC
Feature activation+0.000
refer
Token refer
Feature activation+1.637
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+0.000
this
Token this
Feature activation+0.000
word
Token word
Feature activation+0.000
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+1.676
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
of
Token of
Feature activation+0.000
music
Token music
Feature activation+0.000
including
Token including
Feature activation+0.000
surgical
Token surgical
Feature activation+0.000
removal
Token removal
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
referred
Token referred
Feature activation+1.599
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
partial
Token partial
Feature activation+0.000
hep
Token hep
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
"
Token "
Feature activation+0.000
el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+1.768
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
large
Tokenlarge
Feature activation+0.000
deer
Token deer
Feature activation+0.000
"
Token"
Feature activation+0.000

INTERVAL 1.414 - 1.591
CONTAINS 0.001%

talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
compromise
Token compromise
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
referred
Token referred
Feature activation+1.433
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
footnote
Token footnote
Feature activation+0.000
to
Token to
Feature activation+0.000
ill
Token ill
Feature activation+0.000
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
phrases
Token phrases
Feature activation+0.000
referred
Token referred
Feature activation+1.589
to
Token to
Feature activation+0.000
Keystone
Token Keystone
Feature activation+0.000
XL
Token XL
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
Director
Token Director
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
who
Token who
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
said
Token said
Feature activation+0.000
referred
Token referred
Feature activation+1.565
U
Token U
Feature activation+0.000
rets
Tokenrets
Feature activation+0.000
ky
Tokenky
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
adv
Tokenadv
Feature activation+0.000
yd
Tokenyd
Feature activation+0.000
as
Tokenas
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
refers
Token refers
Feature activation+1.434
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
refer
Token refer
Feature activation+1.476
new
Token new
Feature activation+0.000
land
Token land
Feature activation+0.000
owners
Token owners
Feature activation+0.000
.
Token.
Feature activation+0.000
Know
Token Know
Feature activation+0.000

INTERVAL 1.237 - 1.414
CONTAINS 0.001%

HRC
Token HRC
Feature activation+0.000
stated
Token stated
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
referred
Token referred
Feature activation+1.337
to
Token to
Feature activation+0.000
prisoners
Token prisoners
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
wide
Tokenwide
Feature activation+0.000
or
Token or
Feature activation+0.000
striking
Token striking
Feature activation+0.000
avatar
Token avatar
Feature activation+0.000
to
Token to
Feature activation+0.000
easily
Token easily
Feature activation+0.000
refer
Token refer
Feature activation+1.403
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
failed
Token failed
Feature activation+0.000
coup
Token coup
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
.
Token.
Feature activation+0.000
Turkey
Token Turkey
Feature activation+0.000
refers
Token refers
Feature activation+1.261
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
H
Token H
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
met
Tokenmet
Feature activation+0.000
The
Token The
Feature activation+0.000
name
Token name
Feature activation+0.000
d
Token d
Feature activation+0.000
iox
Tokeniox
Feature activation+0.000
in
Tokenin
Feature activation+0.000
refers
Token refers
Feature activation+1.358
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
highly
Token highly
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
rape
Token rape
Feature activation+0.000
culture
Token culture
Feature activation+0.000
that
Token that
Feature activation+0.000
refers
Token refers
Feature activation+1.325
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 1.061 - 1.237
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
refer
Token refer
Feature activation+1.184
to
Token to
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
losses
Token losses
Feature activation+0.000
in
Token in
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+0.000
refers
Token refers
Feature activation+1.221
to
Token to
Feature activation+0.000
military
Token military
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
destroyed
Token destroyed
Feature activation+0.000
during
Token during
Feature activation+0.000
authors
Token authors
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
.
Token.
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
ware
Tokenware
Feature activation+0.000
refers
Token refers
Feature activation+1.122
to
Token to
Feature activation+0.000
software
Token software
Feature activation+0.000
that
Token that
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
displays
Token displays
Feature activation+0.000
most
Token most
Feature activation+0.000
general
Token general
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
refers
Token refers
Feature activation+1.092
to
Token to
Feature activation+0.000
any
Token any
Feature activation+0.000
action
Token action
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
presumably
Token presumably
Feature activation+0.000
refers
Token refers
Feature activation+1.228
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bit
Token bit
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.884 - 1.061
CONTAINS 0.001%

he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Refer
TokenRefer
Feature activation+1.023
ring
Tokenring
Feature activation+0.000
to
Token to
Feature activation+0.000
J
Token J
Feature activation+0.000
ammu
Tokenammu
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
referred
Token referred
Feature activation+1.021
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
investigated
Token investigated
Feature activation+0.000
;
Token;
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
be
Token be
Feature activation+0.000
animated
Token animated
Feature activation+0.000
.
Token.
Feature activation+0.000
Refer
Token Refer
Feature activation+0.919
to
Token to
Feature activation+0.000
CSS
Token CSS
Feature activation+0.000
3
Token3
Feature activation+0.000
Transition
Token Transition
Feature activation+0.000
Property
Token Property
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+1.054
Roberts
Token Roberts
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
court
Token court
Feature activation+0.000
opposing
Token opposing
Feature activation+0.000
the
Token the
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
referred
Token referred
Feature activation+0.948
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
struggles
Token struggles
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.707 - 0.884
CONTAINS 0.001%

excruciating
Token excruciating
Feature activation+0.000
severity
Token severity
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
often
Token often
Feature activation+0.000
referred
Token referred
Feature activation+0.833
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
break
Token break
Feature activation+0.000
bone
Tokenbone
Feature activation+0.000
fever
Token fever
Feature activation+0.000
ON
TokenON
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Transfer
TokenTransfer
Feature activation+0.000
pricing
Token pricing
Feature activation+0.000
refers
Token refers
Feature activation+0.720
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
prices
Token prices
Feature activation+0.000
multinational
Token multinational
Feature activation+0.000
s
Tokens
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
referred
Token referred
Feature activation+0.883
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
documents
Token documents
Feature activation+0.000
as
Token as
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
alluded
Token alluded
Feature activation+0.789
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
Batman
Token Batman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
humanoid
Token humanoid
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
refers
Token refers
Feature activation+0.783
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
supreme
Token supreme
Feature activation+0.000
being
Token being
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.530 - 0.707
CONTAINS 0.000%

French
Token French
Feature activation+0.000
translation
Token translation
Feature activation+0.000
of
Token of
Feature activation+0.000
moon
Token moon
Feature activation+0.000
and
Token and
Feature activation+0.000
refers
Token refers
Feature activation+0.674
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
user
Token user
Feature activation+0.000
interface
Token interface
Feature activation+0.000
we
Token we
Feature activation+0.000
Church
Token Church
Feature activation+0.000
Fathers
Token Fathers
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
alluded
Token alluded
Feature activation+0.662
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bible
Token Bible
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.354 - 0.530
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
can
Token can
Feature activation+0.000
relate
Token relate
Feature activation+0.442
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
because
Token because
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.000
really
Token really
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
relate
Token relate
Feature activation+0.421
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
of
Token of
Feature activation+0.000
low
Token low
Feature activation+0.000

INTERVAL 0.177 - 0.354
CONTAINS 0.000%

consciousness
Token consciousness
Feature activation+0.000
is
Token is
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
relates
Token relates
Feature activation+0.247
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
non
Token non
Feature activation+0.000
conscious
Tokenconscious
Feature activation+0.000
,
Token,
Feature activation+0.000
unless
Token unless
Feature activation+0.000
such
Token such
Feature activation+0.000
Act
Token Act
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
relates
Token relates
Feature activation+0.208
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
of
Token of
Feature activation+0.000
insurance
Token insurance
Feature activation+0.000

INTERVAL 0.000 - 0.177
CONTAINS 99.994%

ideas
Token ideas
Feature activation+0.000
for
Token for
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
thanked
Token thanked
Feature activation+0.000
European
Token European
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
President
Token President
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
-
Token-
Feature activation+0.000
located
Token located
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
digging
Token digging
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
trunk
Token trunk
Feature activation+0.000
of
Token of
Feature activation+0.000
underwear
Token underwear
Feature activation+0.000
.
Token.
Feature activation+0.000
''
Token ''
Feature activation+0.000
Nick
TokenNick
Feature activation+0.000
not
Token not
Feature activation+0.000
groceries
Token groceries
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
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
have
Token have
Feature activation+0.000
anything
Token anything
Feature activation+0.000
on
Token on
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
collapse
Token collapse
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
desperately
Token desperately
Feature activation+0.000
short
Token short
Feature activation+0.000
supply
Token supply
Feature activation+0.000
.
Token.
Feature activation+0.000
Others
Token Others
Feature activation+0.000
should
Token should
Feature activation+0.000
follow
Token follow
Feature activation+0.000
this
Token this
Feature activation+0.000
lead
Token lead
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 H0.3: (feature 15501)

TOP ACTIVATIONS
MAX = 1.513

stable
Token stable
Feature activation+0.000
and
Token and
Feature activation+0.000
readily
Token readily
Feature activation+0.000
preserved
Token preserved
Feature activation+0.000
proteins
Token proteins
Feature activation+0.000
such
Token such
Feature activation+1.513
as
Token as
Feature activation+0.000
act
Token act
Feature activation+0.000
in
Tokenin
Feature activation+0.000
and
Token and
Feature activation+0.000
tub
Token tub
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
such
Token such
Feature activation+1.502
a
Token a
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
environment
Token environment
Feature activation+0.000
on
Token on
Feature activation+0.000
college
Token college
Feature activation+0.000
el
Tokenel
Feature activation+0.000
explain
Token explain
Feature activation+0.000
.
Token.
Feature activation+0.000
Outside
Token Outside
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+1.479
settings
Token settings
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
which
Token which
Feature activation+0.000
combine
Token combine
Feature activation+0.000
glucose
Token glucose
Feature activation+0.000
and
Token and
Feature activation+0.000
fructose
Token fructose
Feature activation+0.000
such
Token such
Feature activation+1.478
as
Token as
Feature activation+0.000
soft
Token soft
Feature activation+0.000
drinks
Token drinks
Feature activation+0.000
,
Token,
Feature activation+0.000
processed
Token processed
Feature activation+0.000
compressed
Token compressed
Feature activation+0.000
natural
Token natural
Feature activation+0.000
gas
Token gas
Feature activation+0.000
applications
Token applications
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.459
as
Token as
Feature activation+0.000
transportation
Token transportation
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+1.458
super
Token super
Feature activation+0.000
-
Token-
Feature activation+0.000
agers
Tokenagers
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
official
Token official
Feature activation+0.000
term
Token term
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+1.447
a
Token a
Feature activation+0.000
hybrid
Token hybrid
Feature activation+0.000
of
Token of
Feature activation+0.000
beer
Token beer
Feature activation+0.000
and
Token and
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
at
Token at
Feature activation+0.000
such
Token such
Feature activation+1.445
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
credible
Token credible
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
efficacy
Token efficacy
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.436
as
Token as
Feature activation+0.000
home
Token home
Feature activation+0.000
opathic
Tokenopathic
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
could
Token could
Feature activation+0.000
energy
Token energy
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
such
Token such
Feature activation+1.435
as
Token as
Feature activation+0.000
wind
Token wind
Feature activation+0.000
and
Token and
Feature activation+0.000
solar
Token solar
Feature activation+0.000
(
Token (
Feature activation+0.000
includes
Token includes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
such
Token such
Feature activation+1.262
colleges
Token colleges
Feature activation+0.000
such
Token such
Feature activation+1.413
as
Token as
Feature activation+0.000
U
Token U
Feature activation+0.000
H
TokenH
Feature activation+0.000
West
Token West
Feature activation+0.000
O
Token O
Feature activation+0.000
),
Token),
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
rejected
Token rejected
Feature activation+0.000
such
Token such
Feature activation+1.410
a
Token a
Feature activation+0.000
path
Token path
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
lucky
Token lucky
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
such
Token such
Feature activation+1.401
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
spot
Token spot
Feature activation+0.000
just
Token just
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
government
Token government
Feature activation+0.000
with
Token with
Feature activation+0.000
10
Token 10
Feature activation+0.000
such
Token such
Feature activation+1.399
fug
Token fug
Feature activation+0.000
itives
Tokenitives
Feature activation+0.000
still
Token still
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
defense
Token defense
Feature activation+0.000
against
Token against
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
biological
Token biological
Feature activation+0.000
agents
Token agents
Feature activation+0.000
such
Token such
Feature activation+1.395
as
Token as
Feature activation+0.000
anth
Token anth
Feature activation+0.000
rax
Tokenrax
Feature activation+0.000
,
Token,
Feature activation+0.000
plague
Token plague
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
wish
Token wish
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.379
as
Token as
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
shark
Token shark
Feature activation+0.000
tunnel
Token tunnel
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
such
Token such
Feature activation+1.376
as
Token as
Feature activation+0.000
ME
Token ME
Feature activation+0.000
,
Token,
Feature activation+0.000
fib
Token fib
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
sex
Token sex
Feature activation+0.000
shall
Token shall
Feature activation+0.000
be
Token be
Feature activation+0.000
comparable
Token comparable
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+1.371
facilities
Token facilities
Feature activation+0.000
provided
Token provided
Feature activation+0.000
for
Token for
Feature activation+0.000
students
Token students
Feature activation+0.000
of
Token of
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
such
Token such
Feature activation+1.358
lawmakers
Token lawmakers
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
they
Token they
Feature activation+0.000
see
Token see
Feature activation+0.000
monitored
Token monitored
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.357
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 6.962

stable
Token stable
Feature activation+0.091
Top resid features:
and
Token and
Feature activation+0.213
Top resid features:
readily
Token readily
Feature activation+0.186
Top resid features:
preserved
Token preserved
Feature activation+0.172
Top resid features:
proteins
Token proteins
Feature activation+0.208
Top resid features:
such
Token such
Feature activation+6.872
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
act
Token act
Feature activation+0.000
Top resid features:
in
Tokenin
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
tub
Token tub
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.148
Top resid features:
been
Token been
Feature activation+0.095
Top resid features:
allowed
Token allowed
Feature activation+0.091
Top resid features:
to
Token to
Feature activation+0.244
Top resid features:
create
Token create
Feature activation+0.287
Top resid features:
such
Token such
Feature activation+6.914
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
toxic
Token toxic
Feature activation+0.000
Top resid features:
environment
Token environment
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
college
Token college
Feature activation+0.000
Top resid features:
el
Tokenel
Feature activation+0.042
Top resid features:
explain
Token explain
Feature activation+0.138
Top resid features:
.
Token.
Feature activation+0.175
Top resid features:
Outside
Token Outside
Feature activation+0.117
Top resid features:
of
Token of
Feature activation+0.310
Top resid features:
such
Token such
Feature activation+6.889
Top resid features:
settings
Token settings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
capabilities
Token capabilities
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.144
Top resid features:
combine
Token combine
Feature activation+0.068
Top resid features:
glucose
Token glucose
Feature activation+0.108
Top resid features:
and
Token and
Feature activation+0.331
Top resid features:
fructose
Token fructose
Feature activation+0.071
Top resid features:
such
Token such
Feature activation+6.892
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
soft
Token soft
Feature activation+0.000
Top resid features:
drinks
Token drinks
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
processed
Token processed
Feature activation+0.000
Top resid features:
compressed
Token compressed
Feature activation+0.045
Top resid features:
natural
Token natural
Feature activation+0.073
Top resid features:
gas
Token gas
Feature activation+0.120
Top resid features:
applications
Token applications
Feature activation+0.152
Top resid features:
,
Token,
Feature activation+0.264
Top resid features:
such
Token such
Feature activation+6.845
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
transportation
Token transportation
Feature activation+0.000
Top resid features:
fuel
Token fuel
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Once
Token Once
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.046
Top resid features:
,
Token,
Feature activation+0.137
Top resid features:
the
Token the
Feature activation+0.153
Top resid features:
numbers
Token numbers
Feature activation+0.118
Top resid features:
of
Token of
Feature activation+0.273
Top resid features:
such
Token such
Feature activation+6.913
Top resid features:
super
Token super
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
agers
Tokenagers
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.183
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
official
Token official
Feature activation+0.063
Top resid features:
term
Token term
Feature activation+0.077
Top resid features:
for
Token for
Feature activation+0.268
Top resid features:
such
Token such
Feature activation+6.884
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hybrid
Token hybrid
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
beer
Token beer
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
enforcement
Token enforcement
Feature activation+0.087
Top resid features:
of
Token of
Feature activation+0.148
Top resid features:
the
Token the
Feature activation+0.149
Top resid features:
sentence
Token sentence
Feature activation+0.105
Top resid features:
at
Token at
Feature activation+0.262
Top resid features:
such
Token such
Feature activation+4.553
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
credible
Token credible
Feature activation+0.095
Top resid features:
evidence
Token evidence
Feature activation+0.094
Top resid features:
of
Token of
Feature activation+0.177
Top resid features:
efficacy
Token efficacy
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.259
Top resid features:
such
Token such
Feature activation+6.811
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
opathic
Tokenopathic
Feature activation+0.000
Top resid features:
products
Token products
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.105
Top resid features:
as
Token as
Feature activation+0.169
Top resid features:
could
Token could
Feature activation+0.276
Top resid features:
energy
Token energy
Feature activation+0.051
Top resid features:
technologies
Token technologies
Feature activation+0.173
Top resid features:
such
Token such
Feature activation+6.782
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
wind
Token wind
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
solar
Token solar
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
includes
Token includes
Feature activation+0.146
Top resid features:
not
Token not
Feature activation+0.100
Top resid features:
only
Token only
Feature activation+0.129
Top resid features:
such
Token such
Feature activation+3.116
Top resid features:
colleges
Token colleges
Feature activation+0.137
Top resid features:
such
Token such
Feature activation+4.021
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
West
Token West
Feature activation+0.000
Top resid features:
O
Token O
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.088
Top resid features:
however
Token however
Feature activation+0.154
Top resid features:
,
Token,
Feature activation+0.176
Top resid features:
have
Token have
Feature activation+0.256
Top resid features:
rejected
Token rejected
Feature activation+0.226
Top resid features:
such
Token such
Feature activation+6.719
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
path
Token path
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
lucky
Token lucky
Feature activation+0.080
Top resid features:
they
Token they
Feature activation+0.094
Top resid features:
are
Token are
Feature activation+0.165
Top resid features:
to
Token to
Feature activation+0.207
Top resid features:
have
Token have
Feature activation+0.286
Top resid features:
such
Token such
Feature activation+6.754
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
beautiful
Token beautiful
Feature activation+0.000
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.108
Top resid features:
Mexican
Token Mexican
Feature activation+0.057
Top resid features:
government
Token government
Feature activation+0.109
Top resid features:
with
Token with
Feature activation+0.212
Top resid features:
10
Token 10
Feature activation+0.167
Top resid features:
such
Token such
Feature activation+6.740
Top resid features:
fug
Token fug
Feature activation+0.000
Top resid features:
itives
Tokenitives
Feature activation+0.000
Top resid features:
still
Token still
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
defense
Token defense
Feature activation+0.050
Top resid features:
against
Token against
Feature activation+0.073
Top resid features:
deadly
Token deadly
Feature activation+0.192
Top resid features:
biological
Token biological
Feature activation+0.115
Top resid features:
agents
Token agents
Feature activation+0.150
Top resid features:
such
Token such
Feature activation+6.962
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
anth
Token anth
Feature activation+0.000
Top resid features:
rax
Tokenrax
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
plague
Token plague
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
if
Token if
Feature activation+0.136
Top resid features:
they
Token they
Feature activation+0.131
Top resid features:
wish
Token wish
Feature activation+0.076
Top resid features:
,
Token,
Feature activation+0.260
Top resid features:
such
Token such
Feature activation+6.879
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
shark
Token shark
Feature activation+0.000
Top resid features:
tunnel
Token tunnel
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.134
Top resid features:
are
Token are
Feature activation+0.158
Top resid features:
hard
Token hard
Feature activation+0.083
Top resid features:
to
Token to
Feature activation+0.245
Top resid features:
confirm
Token confirm
Feature activation+0.131
Top resid features:
such
Token such
Feature activation+6.907
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
ME
Token ME
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fib
Token fib
Feature activation+0.000
Top resid features:
ro
Tokenro
Feature activation+0.000
Top resid features:
sex
Token sex
Feature activation+0.067
Top resid features:
shall
Token shall
Feature activation+0.085
Top resid features:
be
Token be
Feature activation+0.118
Top resid features:
comparable
Token comparable
Feature activation+0.308
Top resid features:
to
Token to
Feature activation+0.246
Top resid features:
such
Token such
Feature activation+4.240
Top resid features:
facilities
Token facilities
Feature activation+0.000
Top resid features:
provided
Token provided
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
students
Token students
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.083
Top resid features:
tax
Token tax
Feature activation+0.071
Top resid features:
plan
Token plan
Feature activation+0.102
Top resid features:
.
Token.
Feature activation+0.187
Top resid features:
Yet
Token Yet
Feature activation+0.227
Top resid features:
such
Token such
Feature activation+6.957
Top resid features:
lawmakers
Token lawmakers
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
shown
Token shown
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
monitored
Token monitored
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.134
Top resid features:
while
Token while
Feature activation+0.176
Top resid features:
others
Token others
Feature activation+0.122
Top resid features:
,
Token,
Feature activation+0.248
Top resid features:
such
Token such
Feature activation+6.872
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
arrested
Token arrested
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.22

Head 2: 0.02

Head 3: 0.24

Head 4: 0.07

Head 5: 0.13

Head 6: 0.03

Head 7: 0.06

Head 8: 0.03

Head 9: 0.08

Head 10: 0.06

Head 11: 0.03

Positive logits

etheless3.59

��3.45

worldly3.41

unnecess3.40

merce3.21

carbohyd3.11

azeera3.04

localized3.02

reconc2.89

raviolet2.88

severe2.82

ancies2.79

NetMessage2.78

quartered2.76

qualitative2.72

vae2.72

recourse2.67

oğan2.66

abundantly2.66

cumbers2.65

Negative logits

Bohem-2.88

Ridge-2.84

Champ-2.81

Cambodia-2.79

Crush-2.61

Beach-2.59

halla-2.58

Drum-2.58

Rou-2.55

Harbor-2.50

Dock-2.47

Wheel-2.47

Pier-2.47

Lake-2.45

eers-2.45

Bunny-2.45

Bot-2.45

holm-2.41

ilet-2.38

Bung-2.38

INTERVAL 1.362 - 1.513
CONTAINS 0.002%

lucky
Token lucky
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
such
Token such
Feature activation+1.401
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
spot
Token spot
Feature activation+0.000
just
Token just
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
government
Token government
Feature activation+0.000
with
Token with
Feature activation+0.000
10
Token 10
Feature activation+0.000
such
Token such
Feature activation+1.399
fug
Token fug
Feature activation+0.000
itives
Tokenitives
Feature activation+0.000
still
Token still
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
defense
Token defense
Feature activation+0.000
against
Token against
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
biological
Token biological
Feature activation+0.000
agents
Token agents
Feature activation+0.000
such
Token such
Feature activation+1.395
as
Token as
Feature activation+0.000
anth
Token anth
Feature activation+0.000
rax
Tokenrax
Feature activation+0.000
,
Token,
Feature activation+0.000
plague
Token plague
Feature activation+0.000
),
Token),
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
rejected
Token rejected
Feature activation+0.000
such
Token such
Feature activation+1.410
a
Token a
Feature activation+0.000
path
Token path
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
includes
Token includes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
such
Token such
Feature activation+1.262
colleges
Token colleges
Feature activation+0.000
such
Token such
Feature activation+1.413
as
Token as
Feature activation+0.000
U
Token U
Feature activation+0.000
H
TokenH
Feature activation+0.000
West
Token West
Feature activation+0.000
O
Token O
Feature activation+0.000

INTERVAL 1.211 - 1.362
CONTAINS 0.003%

we
Tokenwe
Feature activation+0.000
now
Token now
Feature activation+0.000
have
Token have
Feature activation+0.000
pathogens
Token pathogens
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.324
as
Token as
Feature activation+0.000
strains
Token strains
Feature activation+0.000
of
Token of
Feature activation+0.000
My
Token My
Feature activation+0.000
c
Tokenc
Feature activation+0.000
assign
Token assign
Feature activation+0.000
ee
Tokenee
Feature activation+0.000
and
Token and
Feature activation+0.000
take
Token take
Feature activation+0.000
actions
Token actions
Feature activation+0.000
such
Token such
Feature activation+1.220
as
Token as
Feature activation+0.000
restart
Token restart
Feature activation+0.000
ing
Tokening
Feature activation+0.000
a
Token a
Feature activation+0.000
match
Token match
Feature activation+0.000
in
Token in
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
TPP
TokenTPP
Feature activation+0.000
countries
Token countries
Feature activation+0.000
such
Token such
Feature activation+1.302
as
Token as
Feature activation+0.000
China
Token China
Feature activation+0.000
and
Token and
Feature activation+0.000
Thailand
Token Thailand
Feature activation+0.000
to
Token to
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
such
Token such
Feature activation+1.358
lawmakers
Token lawmakers
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
they
Token they
Feature activation+0.000
see
Token see
Feature activation+0.000
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000
elector
Token elector
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.282
as
Token as
Feature activation+0.000
W
Token W
Feature activation+0.000
ills
Tokenills
Feature activation+0.000
in
Token in
Feature activation+0.000
Victoria
Token Victoria
Feature activation+0.000

INTERVAL 1.059 - 1.211
CONTAINS 0.001%

security
Token security
Feature activation+0.000
motivations
Token motivations
Feature activation+0.000
to
Token to
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
contemplate
Token contemplate
Feature activation+0.000
such
Token such
Feature activation+1.099
an
Token an
Feature activation+0.000
option
Token option
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
other
Token other
Feature activation+0.000
-
Token-
Feature activation+0.000
part
Tokenpart
Feature activation+0.000
questionnaire
Token questionnaire
Feature activation+0.000
includes
Token includes
Feature activation+0.000
questions
Token questions
Feature activation+0.000
such
Token such
Feature activation+1.158
as
Token as
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Koran
Token Koran
Feature activation+0.000
,
Token,
Feature activation+0.000
694
Token694
Feature activation+0.000
Senior
Token Senior
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.074
as
Token as
Feature activation+0.000
ward
Token ward
Feature activation+0.000
sister
Token sister
Feature activation+0.000
/
Token /
Feature activation+0.000
team
Token team
Feature activation+0.000
g
Tokeng
Feature activation+0.000
usting
Tokenusting
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
such
Token such
Feature activation+1.194
acts
Token acts
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
outlawed
Token outlawed
Feature activation+0.000
GPA
Token GPA
Feature activation+0.000
scores
Token scores
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
with
Token with
Feature activation+0.000
such
Token such
Feature activation+1.197
scores
Token scores
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

INTERVAL 0.908 - 1.059
CONTAINS 0.001%

am
Token am
Feature activation+0.000
now
Token now
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
70
Token 70
Feature activation+0.000
such
Token such
Feature activation+0.973
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
listed
Token listed
Feature activation+0.000
higher
Token higher
Feature activation+0.000
staff
Token staff
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
following
Token following
Feature activation+0.000
scandals
Token scandals
Feature activation+0.000
such
Token such
Feature activation+0.972
as
Token as
Feature activation+0.000
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
s
Tokens
Feature activation+0.000
water
Token water
Feature activation+0.000
reuse
Token reuse
Feature activation+0.000
systems
Token systems
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+0.924
a
Token a
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
8
Token8
Feature activation+0.000
76
Token76
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.039
as
Token as
Feature activation+0.000
theatre
Token theatre
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
7
Token 7
Feature activation+0.000
£
Token £
Feature activation+0.000
jurisdictions
Token jurisdictions
Feature activation+0.000
by
Token by
Feature activation+0.000
over
Token over
Feature activation+0.000
charging
Tokencharging
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+1.043
services
Token services
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.757 - 0.908
CONTAINS 0.002%

in
Token in
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
psychotic
Token psychotic
Feature activation+0.000
disorders
Token disorders
Feature activation+0.000
such
Token such
Feature activation+0.841
as
Token as
Feature activation+0.000
schizophrenia
Token schizophrenia
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
However
Token However
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
such
Token such
Feature activation+0.877
as
Token as
Feature activation+0.000
PTSD
Token PTSD
Feature activation+0.000
and
Token and
Feature activation+0.000
depression
Token depression
Feature activation+0.000
.
Token.
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
eliminate
Token eliminate
Feature activation+0.000
or
Token or
Feature activation+0.000
control
Token control
Feature activation+0.000
such
Token such
Feature activation+0.794
potential
Token potential
Feature activation+0.000
failures
Token failures
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
during
Token during
Feature activation+0.000
rec
Token rec
Feature activation+0.000
essions
Tokenessions
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
things
Token things
Feature activation+0.000
such
Token such
Feature activation+0.815
as
Token as
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
In
TokenIn
Feature activation+0.000
races
Token races
Feature activation+0.000
with
Token with
Feature activation+0.000
slim
Token slim
Feature activation+0.000
margins
Token margins
Feature activation+0.000
such
Token such
Feature activation+0.765
as
Token as
Feature activation+0.000
these
Token these
Feature activation+0.000
,
Token,
Feature activation+0.000
recounts
Token recounts
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000

INTERVAL 0.605 - 0.757
CONTAINS 0.001%

different
Token different
Feature activation+0.000
solutions
Token solutions
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.687
solutions
Token solutions
Feature activation+0.000
are
Token are
Feature activation+0.000
simply
Token simply
Feature activation+0.000
not
Token not
Feature activation+0.000
available
Token available
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
energy
Token energy
Feature activation+0.000
that
Token that
Feature activation+0.000
such
Token such
Feature activation+0.725
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
could
Token could
Feature activation+0.000
imb
Token imb
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
LCD
Token LCD
Feature activation+0.000
screen
Token screen
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.733
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
keep
Token keep
Feature activation+0.000
improving
Token improving
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
such
Token such
Feature activation+0.740
varied
Token varied
Feature activation+0.000
species
Token species
Feature activation+0.000
as
Token as
Feature activation+0.000
har
Token har
Feature activation+0.000
le
Tokenle
Feature activation+0.000
ledger
Token ledger
Feature activation+0.000
and
Token and
Feature activation+0.000
payment
Token payment
Feature activation+0.000
network
Token network
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
such
Token such
Feature activation+0.694
as
Token as
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.454 - 0.605
CONTAINS 0.001%

how
Token how
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+0.565
matters
Token matters
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
Murray
Token Murray
Feature activation+0.000
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
sure
Token sure
Feature activation+0.000
such
Token such
Feature activation+0.598
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.000
existed
Token existed
Feature activation+0.000
and
Token and
Feature activation+0.000
examined
Token examined
Feature activation+0.000
rain
Token rain
Feature activation+0.000
coats
Token coats
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
characters
Token characters
Feature activation+0.000
such
Token such
Feature activation+0.461
as
Token as
Feature activation+0.000
Min
Token Min
Feature activation+0.000
nie
Tokennie
Feature activation+0.000
Mouse
Token Mouse
Feature activation+0.000
stay
Token stay
Feature activation+0.000
to
Token to
Feature activation+0.000
misinterpret
Token misinterpret
Feature activation+0.000
an
Token an
Feature activation+0.000
airliner
Token airliner
Feature activation+0.000
at
Token at
Feature activation+0.000
such
Token such
Feature activation+0.531
height
Token height
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
threat
Token threat
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
firms
Token firms
Feature activation+0.000
to
Token to
Feature activation+0.000
retain
Token retain
Feature activation+0.000
such
Token such
Feature activation+0.548
privileges
Token privileges
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
pass
Tokenpass
Feature activation+0.000

INTERVAL 0.303 - 0.454
CONTAINS 0.001%

match
Token match
Feature activation+0.000
cricket
Token cricket
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.424
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
on
Token on
Feature activation+0.000
several
Token several
Feature activation+0.000
connected
Token connected
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
such
Token such
Feature activation+0.320
as
Token as
Feature activation+0.000
translator
Token translator
Feature activation+0.000
Hit
Token Hit
Feature activation+0.000
oshi
Tokenoshi
Feature activation+0.000
I
Token I
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
observ
Token observ
Feature activation+0.000
atories
Tokenatories
Feature activation+0.000
(
Token (
Feature activation+0.000
such
Tokensuch
Feature activation+0.452
as
Token as
Feature activation+0.000
Plan
Token Plan
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
and
Token and
Feature activation+0.000
WM
Token WM
Feature activation+0.000
manner
Token manner
Feature activation+0.000
of
Token of
Feature activation+0.000
death
Token death
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
categories
Token categories
Feature activation+0.000
such
Token such
Feature activation+0.445
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
natural
Tokennatural
Feature activation+0.000
cause
Token cause
Feature activation+0.000
,"
Token,"
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
such
Token such
Feature activation+0.419
bonds
Token bonds
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
pension
Token pension
Feature activation+0.000

INTERVAL 0.151 - 0.303
CONTAINS 0.002%

about
Token about
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
inquiries
Token inquiries
Feature activation+0.000
such
Token such
Feature activation+0.220
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
Do
TokenDo
Feature activation+0.000
you
Token you
Feature activation+0.000
beat
Token beat
Feature activation+0.000
register
Token register
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+0.000
,
Token,
Feature activation+0.000
whenever
Token whenever
Feature activation+0.000
such
Token such
Feature activation+0.214
instruction
Token instruction
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
we
Token we
Feature activation+0.000
log
Token log
Feature activation+0.000
interrupt
Token interrupt
Feature activation+0.000
their
Token their
Feature activation+0.000
careers
Token careers
Feature activation+0.000
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
such
Token such
Feature activation+0.260
as
Token as
Feature activation+0.000
child
Token child
Feature activation+0.000
care
Token care
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
mornings
Token mornings
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+0.183
famous
Token famous
Feature activation+0.000
races
Token races
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Windsor
Token Windsor
Feature activation+0.000
off
Token off
Feature activation+0.000
crude
Token crude
Feature activation+0.000
mock
Token mock
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.257
a
Token a
Feature activation+0.000
timeline
Token timeline
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.151
CONTAINS 99.987%

way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
peak
Token peak
Feature activation+0.000
Wo
Token Wo
Feature activation+0.000
W
TokenW
Feature activation+0.000
maintained
Token maintained
Feature activation+0.000
climb
Token climb
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
garden
Token garden
Feature activation+0.000
hose
Token hose
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
gave
Token gave
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
h
Tokenh
Feature activation+0.000
Johnson
Token Johnson
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
meeting
Token meeting
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
said
Token said
Feature activation+0.000
2
Token2
Feature activation+0.000
muscle
Token muscle
Feature activation+0.000
fib
Token fib
Feature activation+0.000
res
Tokenres
Feature activation+0.000
goes
Token goes
Feature activation+0.000
down
Token down
Feature activation+0.000
.
Token.
Feature activation+0.000
Strength
Token Strength
Feature activation+0.000
training
Token training
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
delay
Token delay
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Government
TokenGovernment
Feature activation+0.000
ministers
Token ministers
Feature activation+0.000
have
Token have
Feature activation+0.000
flat
Token flat
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
answer
Token answer
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 H0.3: (feature 22589)

TOP ACTIVATIONS
MAX = 1.690

you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
caveats
Token caveats
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
detract
Token detract
Feature activation+1.556
from
Token from
Feature activation+0.782
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
detract
Token detract
Feature activation+1.534
from
Token from
Feature activation+1.001
the
Token the
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
might
Token might
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
all
Token all
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
detract
Token detract
Feature activation+1.534
from
Token from
Feature activation+1.001
the
Token the
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
way
Token way
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
detract
Token detract
Feature activation+1.556
from
Token from
Feature activation+0.782
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
all
Token all
Feature activation+0.000
to
Token to
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
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
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
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
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
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
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
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
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
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

Top DFA by src position
MAX = 4.700

you
Token you
Feature activation-0.004
Top resid features:
might
Token might
Feature activation-0.013
Top resid features:
wonder
Token wonder
Feature activation+0.039
Top resid features:
if
Token if
Feature activation-0.030
Top resid features:
it
Token it
Feature activation+0.007
Top resid features:
detract
Token detract
Feature activation+4.635
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
lured
Token lured
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
caveats
Token caveats
Feature activation-0.063
Top resid features:
don
Token don
Feature activation-0.103
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
t
Tokent
Feature activation-0.037
Top resid features:
detract
Token detract
Feature activation+4.700
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
certainly
Token certainly
Feature activation+0.011
Top resid features:
doesn
Token doesn
Feature activation-0.079
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
t
Tokent
Feature activation-0.041
Top resid features:
detract
Token detract
Feature activation+4.393
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
mouse
Token mouse
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.010
Top resid features:
might
Token might
Feature activation-0.040
Top resid features:
wonder
Token wonder
Feature activation+0.018
Top resid features:
if
Token if
Feature activation-0.012
Top resid features:
it
Token it
Feature activation-0.005
Top resid features:
detract
Token detract
Feature activation+3.927
Top resid features:
s
Tokens
Feature activation-0.015
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
lured
Token lured
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
certainly
Token certainly
Feature activation+0.013
Top resid features:
doesn
Token doesn
Feature activation-0.059
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
t
Tokent
Feature activation-0.012
Top resid features:
detract
Token detract
Feature activation+3.330
Top resid features:
from
Token from
Feature activation+0.133
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
mouse
Token mouse
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
caveats
Token caveats
Feature activation-0.083
Top resid features:
don
Token don
Feature activation-0.035
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.027
Top resid features:
t
Tokent
Feature activation-0.016
Top resid features:
detract
Token detract
Feature activation+3.692
Top resid features:
from
Token from
Feature activation-0.143
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.016
Top resid features:
might
Token might
Feature activation-0.023
Top resid features:
wonder
Token wonder
Feature activation+0.007
Top resid features:
if
Token if
Feature activation-0.032
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
detract
Token detract
Feature activation+3.383
Top resid features:
s
Tokens
Feature activation+0.023
Top resid features:
from
Token from
Feature activation-0.112
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
lured
Token lured
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation-0.151
Top resid features:
by
Token by
Feature activation-0.031
Top resid features:
V
Token V
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.130
Top resid features:
K
TokenK
Feature activation-0.192
Top resid features:
.
Token.
Feature activation+0.245
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.068
Top resid features:
defence
Token defence
Feature activation-0.012
Top resid features:
ministry
Token ministry
Feature activation-0.210
Top resid features:
committee
Token committee
Feature activation+0.050
Top resid features:
headed
Token headed
Feature activation-0.338
Top resid features:
by
Token by
Feature activation+0.651
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation-0.041
Top resid features:
ministry
Token ministry
Feature activation-0.192
Top resid features:
committee
Token committee
Feature activation+0.013
Top resid features:
headed
Token headed
Feature activation-0.122
Top resid features:
by
Token by
Feature activation-0.053
Top resid features:
V
Token V
Feature activation+0.038
Top resid features:
.
Token.
Feature activation-0.149
Top resid features:
K
TokenK
Feature activation-0.385
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation-0.043
Top resid features:
ministry
Token ministry
Feature activation-0.301
Top resid features:
committee
Token committee
Feature activation+0.006
Top resid features:
headed
Token headed
Feature activation-0.042
Top resid features:
by
Token by
Feature activation-0.066
Top resid features:
V
Token V
Feature activation+0.508
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation-0.165
Top resid features:
committee
Token committee
Feature activation+0.011
Top resid features:
headed
Token headed
Feature activation-0.181
Top resid features:
by
Token by
Feature activation+0.028
Top resid features:
V
Token V
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.330
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.121
Top resid features:
Ċ
TokenĊ
Feature activation-0.124
Top resid features:
The
TokenThe
Feature activation-0.093
Top resid features:
defence
Token defence
Feature activation+0.029
Top resid features:
ministry
Token ministry
Feature activation-0.139
Top resid features:
committee
Token committee
Feature activation+0.138
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.139
Top resid features:
Ċ
TokenĊ
Feature activation-0.136
Top resid features:
Ċ
TokenĊ
Feature activation-0.141
Top resid features:
The
TokenThe
Feature activation-0.048
Top resid features:
defence
Token defence
Feature activation+0.132
Top resid features:
ministry
Token ministry
Feature activation+0.236
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.143
Top resid features:
Ċ
TokenĊ
Feature activation-0.147
Top resid features:
The
TokenThe
Feature activation-0.064
Top resid features:
defence
Token defence
Feature activation-0.014
Top resid features:
ministry
Token ministry
Feature activation-0.212
Top resid features:
committee
Token committee
Feature activation+0.052
Top resid features:
headed
Token headed
Feature activation-0.726
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.136
Top resid features:
rik
Tokenrik
Feature activation-0.062
Top resid features:
ar
Tokenar
Feature activation-0.054
Top resid features:
said
Token said
Feature activation-0.031
Top resid features:
Saturday
Token Saturday
Feature activation-0.213
Top resid features:
.
Token.
Feature activation+0.318
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation-0.086
Top resid features:
.
Token.
Feature activation-0.130
Top resid features:
Ċ
TokenĊ
Feature activation-0.189
Top resid features:
Ċ
TokenĊ
Feature activation-0.204
Top resid features:
The
TokenThe
Feature activation-0.078
Top resid features:
defence
Token defence
Feature activation+0.727
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.086
Top resid features:
Saturday
Token Saturday
Feature activation-0.162
Top resid features:
.
Token.
Feature activation-0.118
Top resid features:
Ċ
TokenĊ
Feature activation-0.238
Top resid features:
Ċ
TokenĊ
Feature activation-0.267
Top resid features:
The
TokenThe
Feature activation+0.957
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-0.044
Top resid features:
ar
Tokenar
Feature activation-0.045
Top resid features:
said
Token said
Feature activation-0.103
Top resid features:
Saturday
Token Saturday
Feature activation-0.175
Top resid features:
.
Token.
Feature activation-0.163
Top resid features:
Ċ
TokenĊ
Feature activation+0.692
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-0.041
Top resid features:
ar
Tokenar
Feature activation-0.039
Top resid features:
said
Token said
Feature activation-0.105
Top resid features:
Saturday
Token Saturday
Feature activation-0.167
Top resid features:
.
Token.
Feature activation-0.163
Top resid features:
Ċ
TokenĊ
Feature activation+0.317
Top resid features:
Ċ
TokenĊ
Feature activation+0.287
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.10

Head 2: 0.03

Head 3: 0.24

Head 4: 0.24

Head 5: 0.07

Head 6: 0.05

Head 7: 0.07

Head 8: 0.04

Head 9: 0.04

Head 10: 0.06

Head 11: 0.03

Positive logits

detract4.99

ados4.69

MENTS4.57

enance4.51

attRot4.44

SourceFile4.40

ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ4.15

edin4.13

4.05

TextColor4.02

��4.02

ments3.99

glers3.88

MENT3.82

Marginal3.68

awei3.63

mented3.61

3.58

3.57

�士3.55

Negative logits

opic-3.69

elsius-3.68

Alps-3.60

aido-3.49

iping-3.42

���-3.41

ammy-3.38

king-3.37

succession-3.10

kered-3.09

Pant-3.07

utral-3.05

iphate-3.04

elf-2.95

Trial-2.95

aptic-2.93

avery-2.92

ccording-2.90

eat-2.86

prus-2.83

INTERVAL 1.521 - 1.690
CONTAINS 0.000%

you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
detract
Token detract
Feature activation+1.534
from
Token from
Feature activation+1.001
the
Token the
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
caveats
Token caveats
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
detract
Token detract
Feature activation+1.556
from
Token from
Feature activation+0.782
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.352 - 1.521
CONTAINS 0.000%

INTERVAL 1.183 - 1.352
CONTAINS 0.000%

INTERVAL 1.014 - 1.183
CONTAINS 0.000%

might
Token might
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 0.845 - 1.014
CONTAINS 0.000%

doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
detract
Token detract
Feature activation+1.534
from
Token from
Feature activation+1.001
the
Token the
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
way
Token way
Feature activation+0.000

INTERVAL 0.676 - 0.845
CONTAINS 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
detract
Token detract
Feature activation+1.556
from
Token from
Feature activation+0.782
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.507 - 0.676
CONTAINS 0.000%

wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+1.690
s
Tokens
Feature activation+1.181
from
Token from
Feature activation+0.616
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
all
Token all
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.338 - 0.507
CONTAINS 0.000%

INTERVAL 0.169 - 0.338
CONTAINS 0.000%

INTERVAL 0.000 - 0.169
CONTAINS 99.999%

club
Token club
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Major
Token Major
Feature activation+0.000
League
Token League
Feature activation+0.000
Soccer
Token Soccer
Feature activation+0.000
R
Token R
Feature activation+0.000
oster
Tokenoster
Feature activation+0.000
,
Token,
Feature activation+0.000
pending
Token pending
Feature activation+0.000
football
Token football
Feature activation+0.000
and
Token and
Feature activation+0.000
wrestling
Token wrestling
Feature activation+0.000
coach
Token coach
Feature activation+0.000
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
invent
Token invent
Feature activation+0.000
ing
Tokening
Feature activation+0.000
alternate
Token alternate
Feature activation+0.000
realities
Token realities
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
developed
Token developed
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
presenting
Token presenting
Feature activation+0.000
recipes
Token recipes
Feature activation+0.000
Wire
Token Wire
Feature activation+0.000
removes
Token removes
Feature activation+0.000
his
Token his
Feature activation+0.000
sunglasses
Token sunglasses
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
going
Token going
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
Bin
Token Bin
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ame
Tokename
Feature activation+0.000
en
Tokenen
Feature activation+0.000
,
Token,
Feature activation+0.000
Hann
Token Hann
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 H0.3: (feature 12978)

TOP ACTIVATIONS
MAX = 0.920

has
Token has
Feature activation+0.000
always
Token always
Feature activation+0.000
--
Token --
Feature activation+0.000
let
Token let
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.920
put
Token put
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
--
Token --
Feature activation+0.000
AY
TokenAY
Feature activation+0.000
.
Token.
Feature activation+0.000
SO
Token SO
Feature activation+0.000
THERE
Token THERE
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.805
NOT
Token NOT
Feature activation+0.000
GO
Token GO
Feature activation+0.000
ING
TokenING
Feature activation+0.000
TO
Token TO
Feature activation+0.000
BE
Token BE
Feature activation+0.000
GO
Token GO
Feature activation+0.000
VER
TokenVER
Feature activation+0.000
N
TokenN
Feature activation+0.000
MENT
TokenMENT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.795
INTER
Token INTER
Feature activation+0.000
EST
TokenEST
Feature activation+0.000
IN
Token IN
Feature activation+0.000
DEF
Token DEF
Feature activation+0.000
END
TokenEND
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
.
Token.
Feature activation+0.000
SO
Token SO
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.759
PRO
Token PRO
Feature activation+0.000
BA
TokenBA
Feature activation+0.000
BL
TokenBL
Feature activation+0.000
Y
TokenY
Feature activation+0.000
GO
Token GO
Feature activation+0.000
Fury
Token Fury
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Xer
Token Xer
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.717
ai
Tokenai
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
ury
Tokenury
Feature activation+0.000
,
Token,
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
what
Token what
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.577
happening
Token happening
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
half
Token half
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
(
Token (
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
F
TokenF
Feature activation+0.000
)'
Token)'
Feature activation+0.000
s
Tokens
Feature activation+0.560
official
Token official
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
definition
Token definition
Feature activation+0.000
mark
Token mark
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.'
Token.'
Feature activation+0.000
s
Tokens
Feature activation+0.555
debut
Token debut
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
"
Token "
Feature activation+0.000
SN
TokenSN
Feature activation+0.000
universal
Token universal
Feature activation+0.000
music
Token music
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
I
TokenI
Feature activation+0.000
´
Token´
Feature activation+0.000
m
Tokenm
Feature activation+0.540
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
relations
Token relations
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.501
two
Token two
Feature activation+0.000
largest
Token largest
Feature activation+0.000
economies
Token economies
Feature activation+0.000
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.000
these
Token these
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
that
Token that
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
`
Token`
Feature activation+0.000
t
Tokent
Feature activation+0.324
allow
Token allow
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.000
ES
TokenES
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
DON
Token DON
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.287
CC
Token CC
Feature activation+0.000
THE
Token THE
Feature activation+0.000
WORLD
Token WORLD
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
IF
Token IF
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
DON
Token DON
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.262
KNOW
Token KNOW
Feature activation+0.000
HOW
Token HOW
Feature activation+0.000
,
Token,
Feature activation+0.000
CALL
Token CALL
Feature activation+0.000
HEL
Token HEL
Feature activation+0.000
India
Token India
Feature activation+0.000
produces
Token produces
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
���
Token���
Feature activation+0.000
s
Tokens
Feature activation+0.204
most
Token most
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
films
Token films
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
????
Token????
Feature activation+0.000
I
Token I
Feature activation+0.000
'
Token'
Feature activation+0.000
M
TokenM
Feature activation+0.161
NOT
Token NOT
Feature activation+0.000
A
Token A
Feature activation+0.000
SH
Token SH
Feature activation+0.000
EM
TokenEM
Feature activation+0.000
ALE
TokenALE
Feature activation+0.000
PRODUCT
Token PRODUCT
Feature activation+0.000
IVE
TokenIVE
Feature activation+0.000
.
Token.
Feature activation+0.000
WHAT
Token WHAT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.066
H
Token H
Feature activation+0.000
APP
TokenAPP
Feature activation+0.000
EN
TokenEN
Feature activation+0.000
ED
TokenED
Feature activation+0.000
RIGHT
Token RIGHT
Feature activation+0.000
I
Token I
Feature activation+0.000
TH
Token TH
Feature activation+0.000
INK
TokenINK
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.055
D
Token D
Feature activation+0.000
UE
TokenUE
Feature activation+0.000
ON
Token ON
Feature activation+0.000
FR
Token FR
Feature activation+0.000
ID
TokenID
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
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
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

Top DFA by src position
MAX = 1.523

Congress
TokenCongress
Feature activation+0.127
Top resid features:
has
Token has
Feature activation+0.022
Top resid features:
always
Token always
Feature activation+0.020
Top resid features:
--
Token --
Feature activation+0.015
Top resid features:
let
Token let
Feature activation-0.009
Top resid features:
`
Token`
Feature activation+1.500
Top resid features:
s
Tokens
Feature activation+0.924
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
perspective
Token perspective
Feature activation+0.000
Top resid features:
ID
TokenID
Feature activation-0.002
Top resid features:
AY
TokenAY
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
SO
Token SO
Feature activation+0.000
Top resid features:
THERE
Token THERE
Feature activation+0.089
Top resid features:
'
Token'
Feature activation+1.491
Top resid features:
S
TokenS
Feature activation+0.442
Top resid features:
NOT
Token NOT
Feature activation+0.000
Top resid features:
GO
Token GO
Feature activation+0.000
Top resid features:
ING
TokenING
Feature activation+0.000
Top resid features:
TO
Token TO
Feature activation+0.000
Top resid features:
THE
Token THE
Feature activation+0.036
Top resid features:
GO
Token GO
Feature activation+0.096
Top resid features:
VER
TokenVER
Feature activation+0.013
Top resid features:
N
TokenN
Feature activation+0.016
Top resid features:
MENT
TokenMENT
Feature activation-0.029
Top resid features:
'
Token'
Feature activation+1.452
Top resid features:
S
TokenS
Feature activation+1.311
Top resid features:
INTER
Token INTER
Feature activation+0.000
Top resid features:
EST
TokenEST
Feature activation+0.000
Top resid features:
IN
Token IN
Feature activation+0.000
Top resid features:
DEF
Token DEF
Feature activation+0.000
Top resid features:
TO
Token TO
Feature activation+0.017
Top resid features:
THAT
Token THAT
Feature activation+0.061
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
SO
Token SO
Feature activation+0.008
Top resid features:
THAT
Token THAT
Feature activation+0.136
Top resid features:
'
Token'
Feature activation+1.340
Top resid features:
S
TokenS
Feature activation+0.760
Top resid features:
PRO
Token PRO
Feature activation+0.000
Top resid features:
BA
TokenBA
Feature activation+0.000
Top resid features:
BL
TokenBL
Feature activation+0.000
Top resid features:
Y
TokenY
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.036
Top resid features:
Fury
Token Fury
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
Xer
Token Xer
Feature activation-0.053
Top resid features:
'
Token'
Feature activation+1.388
Top resid features:
S
TokenS
Feature activation+0.929
Top resid features:
ai
Tokenai
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
F
TokenF
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
look
Token look
Feature activation+0.013
Top resid features:
at
Token at
Feature activation+0.030
Top resid features:
what
Token what
Feature activation+0.025
Top resid features:
`
Token`
Feature activation+1.364
Top resid features:
s
Tokens
Feature activation+1.419
Top resid features:
happening
Token happening
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
Foundation
Token Foundation
Feature activation-0.006
Top resid features:
(
Token (
Feature activation+0.028
Top resid features:
FS
TokenFS
Feature activation-0.023
Top resid features:
F
TokenF
Feature activation+0.003
Top resid features:
)'
Token)'
Feature activation+1.188
Top resid features:
s
Tokens
Feature activation+1.519
Top resid features:
official
Token official
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
point
Tokenpoint
Feature activation+0.000
Top resid features:
definition
Token definition
Feature activation+0.000
Top resid features:
mark
Token mark
Feature activation+0.031
Top resid features:
C
Token C
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
K
TokenK
Feature activation+0.044
Top resid features:
.'
Token.'
Feature activation+1.270
Top resid features:
s
Tokens
Feature activation+1.424
Top resid features:
debut
Token debut
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
SN
TokenSN
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
universal
Token universal
Feature activation-0.009
Top resid features:
music
Token music
Feature activation+0.028
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.076
Top resid features:
I
TokenI
Feature activation+0.060
Top resid features:
´
Token´
Feature activation+1.240
Top resid features:
m
Tokenm
Feature activation+0.882
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
try
Token try
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
relations
Token relations
Feature activation-0.019
Top resid features:
between
Token between
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
world
Token world
Feature activation+0.019
Top resid features:
`
Token`
Feature activation+1.380
Top resid features:
s
Tokens
Feature activation+1.436
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
largest
Token largest
Feature activation+0.000
Top resid features:
economies
Token economies
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
these
Token these
Feature activation-0.019
Top resid features:
hospitals
Token hospitals
Feature activation-0.057
Top resid features:
that
Token that
Feature activation-0.009
Top resid features:
doesn
Token doesn
Feature activation+0.115
Top resid features:
`
Token`
Feature activation+1.523
Top resid features:
t
Tokent
Feature activation+1.141
Top resid features:
allow
Token allow
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
PD
TokenPD
Feature activation-0.016
Top resid features:
ES
TokenES
Feature activation+0.013
Top resid features:
K
TokenK
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
DON
Token DON
Feature activation+0.114
Top resid features:
'
Token'
Feature activation+1.140
Top resid features:
T
TokenT
Feature activation+0.607
Top resid features:
CC
Token CC
Feature activation+0.000
Top resid features:
THE
Token THE
Feature activation+0.000
Top resid features:
WORLD
Token WORLD
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
OB
TokenOB
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
IF
Token IF
Feature activation+0.087
Top resid features:
YOU
Token YOU
Feature activation+0.020
Top resid features:
DON
Token DON
Feature activation+0.117
Top resid features:
'
Token'
Feature activation+1.158
Top resid features:
T
TokenT
Feature activation+1.049
Top resid features:
KNOW
Token KNOW
Feature activation+0.000
Top resid features:
HOW
Token HOW
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
CALL
Token CALL
Feature activation+0.000
Top resid features:
India
Token India
Feature activation+0.036
Top resid features:
produces
Token produces
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
world
Token world
Feature activation+0.015
Top resid features:
���
Token���
Feature activation+0.794
Top resid features:
s
Tokens
Feature activation+1.478
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
films
Token films
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.056
Top resid features:
am
Token am
Feature activation+0.024
Top resid features:
????
Token????
Feature activation+0.066
Top resid features:
I
Token I
Feature activation+0.076
Top resid features:
'
Token'
Feature activation+1.070
Top resid features:
M
TokenM
Feature activation+1.090
Top resid features:
NOT
Token NOT
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
SH
Token SH
Feature activation+0.000
Top resid features:
EM
TokenEM
Feature activation+0.000
Top resid features:
ALE
TokenALE
Feature activation+0.000
Top resid features:
EN
TokenEN
Feature activation+0.027
Top resid features:
PRODUCT
Token PRODUCT
Feature activation-0.117
Top resid features:
IVE
TokenIVE
Feature activation-0.057
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
WHAT
Token WHAT
Feature activation+0.151
Top resid features:
'
Token'
Feature activation+1.240
Top resid features:
S
TokenS
Feature activation+1.031
Top resid features:
H
Token H
Feature activation+0.000
Top resid features:
APP
TokenAPP
Feature activation+0.000
Top resid features:
EN
TokenEN
Feature activation+0.000
Top resid features:
ED
TokenED
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
I
Token I
Feature activation+0.029
Top resid features:
TH
Token TH
Feature activation-0.003
Top resid features:
INK
TokenINK
Feature activation-0.156
Top resid features:
THAT
Token THAT
Feature activation+0.108
Top resid features:
'
Token'
Feature activation+0.874
Top resid features:
S
TokenS
Feature activation+0.565
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
UE
TokenUE
Feature activation+0.000
Top resid features:
ON
Token ON
Feature activation+0.000
Top resid features:
FR
Token FR
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.534
Top resid features:
rik
Tokenrik
Feature activation+0.031
Top resid features:
ar
Tokenar
Feature activation+0.038
Top resid features:
said
Token said
Feature activation-0.081
Top resid features:
Saturday
Token Saturday
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.133
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation+0.035
Top resid features:
ar
Tokenar
Feature activation+0.021
Top resid features:
said
Token said
Feature activation-0.215
Top resid features:
Saturday
Token Saturday
Feature activation-0.048
Top resid features:
.
Token.
Feature activation+0.166
Top resid features:
Ċ
TokenĊ
Feature activation+0.373
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation+0.015
Top resid features:
said
Token said
Feature activation-0.229
Top resid features:
Saturday
Token Saturday
Feature activation-0.052
Top resid features:
.
Token.
Feature activation+0.095
Top resid features:
Ċ
TokenĊ
Feature activation+0.183
Top resid features:
Ċ
TokenĊ
Feature activation+0.394
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.18

Head 2: 0.04

Head 3: 0.24

Head 4: 0.07

Head 5: 0.10

Head 6: 0.05

Head 7: 0.11

Head 8: 0.04

Head 9: 0.05

Head 10: 0.07

Head 11: 0.03

Positive logits

enegger3.61

ELF3.47

ometime3.28

DAY3.21

OUND3.13

AND2.92

TERN2.92

ALLY2.86

atorial2.83

OUN2.83

WRITE2.81

OME2.80

isy2.80

UTION2.78

_-2.78

ERAL2.75

uckland2.74

ETHOD2.73

Interstitial2.73

omes2.72

Negative logits

mast-4.00

masters-3.37

minecraft-3.01

milo-2.99

-2.97

artisan-2.92

inctions-2.91

matically-2.88

��-2.81

cies-2.81

llor-2.80

imity-2.78

��-2.78

washing-2.77

fish-2.76

css-2.75

girls-2.74

��-2.72

lapt-2.72

master-2.70

INTERVAL 0.828 - 0.920
CONTAINS 0.000%

has
Token has
Feature activation+0.000
always
Token always
Feature activation+0.000
--
Token --
Feature activation+0.000
let
Token let
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.920
put
Token put
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
--
Token --
Feature activation+0.000

INTERVAL 0.736 - 0.828
CONTAINS 0.000%

THAT
Token THAT
Feature activation+0.000
.
Token.
Feature activation+0.000
SO
Token SO
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.759
PRO
Token PRO
Feature activation+0.000
BA
TokenBA
Feature activation+0.000
BL
TokenBL
Feature activation+0.000
Y
TokenY
Feature activation+0.000
GO
Token GO
Feature activation+0.000
AY
TokenAY
Feature activation+0.000
.
Token.
Feature activation+0.000
SO
Token SO
Feature activation+0.000
THERE
Token THERE
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.805
NOT
Token NOT
Feature activation+0.000
GO
Token GO
Feature activation+0.000
ING
TokenING
Feature activation+0.000
TO
Token TO
Feature activation+0.000
BE
Token BE
Feature activation+0.000
GO
Token GO
Feature activation+0.000
VER
TokenVER
Feature activation+0.000
N
TokenN
Feature activation+0.000
MENT
TokenMENT
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.795
INTER
Token INTER
Feature activation+0.000
EST
TokenEST
Feature activation+0.000
IN
Token IN
Feature activation+0.000
DEF
Token DEF
Feature activation+0.000
END
TokenEND
Feature activation+0.000

INTERVAL 0.644 - 0.736
CONTAINS 0.000%

Fury
Token Fury
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Xer
Token Xer
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.717
ai
Tokenai
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
ury
Tokenury
Feature activation+0.000

INTERVAL 0.552 - 0.644
CONTAINS 0.000%

mark
Token mark
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.'
Token.'
Feature activation+0.000
s
Tokens
Feature activation+0.555
debut
Token debut
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
"
Token "
Feature activation+0.000
SN
TokenSN
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
(
Token (
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
F
TokenF
Feature activation+0.000
)'
Token)'
Feature activation+0.000
s
Tokens
Feature activation+0.560
official
Token official
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
definition
Token definition
Feature activation+0.000
,
Token,
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
what
Token what
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.577
happening
Token happening
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
half
Token half
Feature activation+0.000

INTERVAL 0.460 - 0.552
CONTAINS 0.000%

universal
Token universal
Feature activation+0.000
music
Token music
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
I
TokenI
Feature activation+0.000
´
Token´
Feature activation+0.000
m
Tokenm
Feature activation+0.540
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
relations
Token relations
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.501
two
Token two
Feature activation+0.000
largest
Token largest
Feature activation+0.000
economies
Token economies
Feature activation+0.000
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.000

INTERVAL 0.368 - 0.460
CONTAINS 0.000%

INTERVAL 0.276 - 0.368
CONTAINS 0.000%

ES
TokenES
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
DON
Token DON
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.287
CC
Token CC
Feature activation+0.000
THE
Token THE
Feature activation+0.000
WORLD
Token WORLD
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
these
Token these
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
that
Token that
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
`
Token`
Feature activation+0.000
t
Tokent
Feature activation+0.324
allow
Token allow
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.184 - 0.276
CONTAINS 0.000%

.
Token.
Feature activation+0.000
IF
Token IF
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
DON
Token DON
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.262
KNOW
Token KNOW
Feature activation+0.000
HOW
Token HOW
Feature activation+0.000
,
Token,
Feature activation+0.000
CALL
Token CALL
Feature activation+0.000
HEL
Token HEL
Feature activation+0.000
India
Token India
Feature activation+0.000
produces
Token produces
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
���
Token���
Feature activation+0.000
s
Tokens
Feature activation+0.204
most
Token most
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
films
Token films
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.092 - 0.184
CONTAINS 0.000%

I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
????
Token????
Feature activation+0.000
I
Token I
Feature activation+0.000
'
Token'
Feature activation+0.000
M
TokenM
Feature activation+0.161
NOT
Token NOT
Feature activation+0.000
A
Token A
Feature activation+0.000
SH
Token SH
Feature activation+0.000
EM
TokenEM
Feature activation+0.000
ALE
TokenALE
Feature activation+0.000

INTERVAL 0.000 - 0.092
CONTAINS 99.998%

checked
Token checked
Feature activation+0.000
for
Token for
Feature activation+0.000
up
Token up
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
date
Tokendate
Feature activation+0.000
firearms
Token firearms
Feature activation+0.000
licenses
Token licenses
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
pundits
Token pundits
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
,
Token,
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
size
Token size
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
mortgage
Token mortgage
Feature activation+0.000
and
Token and
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
the
Token the
Feature activation+0.000
tides
Token tides
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
teams
Token teams
Feature activation+0.000
have
Token have
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+0.000
bu
Token bu
Feature activation+0.000
oys
Tokenoys
Feature activation+0.000
that
Token that
Feature activation+0.000
generate
Token generate
Feature activation+0.000
As
TokenAs
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
lucky
Token lucky
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
witness
Token witness
Feature activation+0.000
this
Token this
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 H0.3: (feature 14082)

TOP ACTIVATIONS
MAX = 1.362

GST
Token GST
Feature activation+0.000
on
Token on
Feature activation+0.000
imported
Token imported
Feature activation+0.000
digital
Token digital
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+1.362
as
Token as
Feature activation+0.000
Netflix
Token Netflix
Feature activation+0.000
and
Token and
Feature activation+0.000
Spotify
Token Spotify
Feature activation+0.000
and
Token and
Feature activation+0.000
citing
Token citing
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
that
Token that
Feature activation+0.000
insist
Token insist
Feature activation+0.000
such
Token such
Feature activation+1.319
programs
Token programs
Feature activation+0.000
drive
Token drive
Feature activation+0.000
inequality
Token inequality
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
human
Token human
Feature activation+0.000
eye
Token eye
Feature activation+0.000
--
Token --
Feature activation+0.000
longer
Token longer
Feature activation+0.000
wavelengths
Token wavelengths
Feature activation+0.000
such
Token such
Feature activation+1.215
as
Token as
Feature activation+0.000
infrared
Token infrared
Feature activation+0.000
light
Token light
Feature activation+0.000
pass
Token pass
Feature activation+0.000
through
Token through
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
pre
Tokenpre
Feature activation+0.000
pared
Tokenpared
Feature activation+0.000
items
Token items
Feature activation+0.000
such
Token such
Feature activation+1.177
as
Token as
Feature activation+0.000
sandwiches
Token sandwiches
Feature activation+0.000
,
Token,
Feature activation+0.000
salads
Token salads
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
lifestyle
Token lifestyle
Feature activation+0.000
behaviors
Token behaviors
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.080
as
Token as
Feature activation+0.000
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
exercise
Token exercise
Feature activation+0.000
and
Token and
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
words
Token words
Feature activation+0.000
such
Token such
Feature activation+1.055
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
un
Tokenun
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
affluent
Token affluent
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.055
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
eastern
Token eastern
Feature activation+0.000
suburbs
Token suburbs
Feature activation+0.000
and
Token and
Feature activation+0.000
crises
Token crises
Feature activation+0.000
have
Token have
Feature activation+0.000
affected
Token affected
Feature activation+0.000
social
Token social
Feature activation+0.000
indicators
Token indicators
Feature activation+0.000
such
Token such
Feature activation+1.041
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
listed
Token listed
Feature activation+0.000
above
Token above
Feature activation+0.000
(
Token (
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
from
Token from
Feature activation+0.000
legendary
Token legendary
Feature activation+0.000
audio
Token audio
Feature activation+0.000
companies
Token companies
Feature activation+0.000
such
Token such
Feature activation+1.032
as
Token as
Feature activation+0.000
Ne
Token Ne
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
and
Token and
Feature activation+0.000
Avalon
Token Avalon
Feature activation+0.000
discouraged
Token discouraged
Feature activation+0.000
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
ingredients
Token ingredients
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.030
as
Token as
Feature activation+0.000
ep
Token ep
Feature activation+0.000
hed
Tokenhed
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
critical
Token critical
Feature activation+0.000
metals
Token metals
Feature activation+0.000
for
Token for
Feature activation+0.000
batteries
Token batteries
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.000
as
Token as
Feature activation+0.000
cob
Token cob
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
and
Token and
Feature activation+0.000
lithium
Token lithium
Feature activation+0.000
front
Token front
Feature activation+0.000
ed
Tokened
Feature activation+0.000
by
Token by
Feature activation+0.000
famous
Token famous
Feature activation+0.000
faces
Token faces
Feature activation+0.000
such
Token such
Feature activation+0.988
as
Token as
Feature activation+0.000
Dame
Token Dame
Feature activation+0.000
Helen
Token Helen
Feature activation+0.000
Mir
Token Mir
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
require
Token require
Feature activation+0.000
investment
Token investment
Feature activation+0.000
by
Token by
Feature activation+0.000
service
Token service
Feature activation+0.000
providers
Token providers
Feature activation+0.000
such
Token such
Feature activation+0.973
as
Token as
Feature activation+0.000
itself
Token itself
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
official
Token official
Feature activation+0.000
.
Token.
Feature activation+0.000
Critics
Token Critics
Feature activation+0.000
say
Token say
Feature activation+0.000
such
Token such
Feature activation+0.969
trips
Token trips
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
Current
Token Current
Feature activation+0.000
laws
Token laws
Feature activation+0.000
permit
Token permit
Feature activation+0.000
such
Token such
Feature activation+0.954
citizenship
Token citizenship
Feature activation+0.000
status
Token status
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
practice
Token practice
Feature activation+0.000
,
Token,
Feature activation+0.000
routinely
Token routinely
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
such
Token such
Feature activation+0.949
as
Token as
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
.
Token.
Feature activation+0.000
par
Tokenpar
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
can
Token can
Feature activation+0.000
involve
Token involve
Feature activation+0.000
tasks
Token tasks
Feature activation+0.000
such
Token such
Feature activation+0.917
as
Token as
Feature activation+0.000
reviewing
Token reviewing
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
companies
Token companies
Feature activation+0.000
with
Token with
Feature activation+0.000
growth
Token growth
Feature activation+0.000
potential
Token potential
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.914
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
environment
Token environment
Feature activation+0.000
important
Token important
Feature activation+0.000
French
Token French
Feature activation+0.000
grammar
Token grammar
Feature activation+0.000
rules
Token rules
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.909
as
Token as
Feature activation+0.000
ignoring
Token ignoring
Feature activation+0.000
accents
Token accents
Feature activation+0.000
on
Token on
Feature activation+0.000
capital
Token capital
Feature activation+0.000
market
Token market
Feature activation+0.000
countries
Token countries
Feature activation+0.000
'
Token'
Feature activation+0.000
currencies
Token currencies
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.903
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
yuan
Token yuan
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000

Top DFA by src position
MAX = 5.910

GST
Token GST
Feature activation+0.084
Top resid features:
on
Token on
Feature activation-0.090
Top resid features:
imported
Token imported
Feature activation+0.155
Top resid features:
digital
Token digital
Feature activation+0.128
Top resid features:
services
Token services
Feature activation+0.340
Top resid features:
such
Token such
Feature activation+4.385
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Netflix
Token Netflix
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Spotify
Token Spotify
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
citing
Token citing
Feature activation+0.142
Top resid features:
multiple
Token multiple
Feature activation-0.001
Top resid features:
agencies
Token agencies
Feature activation+0.137
Top resid features:
that
Token that
Feature activation-0.179
Top resid features:
insist
Token insist
Feature activation+0.140
Top resid features:
such
Token such
Feature activation+5.855
Top resid features:
programs
Token programs
Feature activation+0.000
Top resid features:
drive
Token drive
Feature activation+0.000
Top resid features:
inequality
Token inequality
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.051
Top resid features:
eye
Token eye
Feature activation+0.038
Top resid features:
--
Token --
Feature activation-0.001
Top resid features:
longer
Token longer
Feature activation+0.030
Top resid features:
wavelengths
Token wavelengths
Feature activation+0.232
Top resid features:
such
Token such
Feature activation+5.838
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
infrared
Token infrared
Feature activation+0.000
Top resid features:
light
Token light
Feature activation+0.000
Top resid features:
pass
Token pass
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
pre
Token pre
Feature activation+0.039
Top resid features:
-
Token-
Feature activation-0.039
Top resid features:
pre
Tokenpre
Feature activation+0.016
Top resid features:
pared
Tokenpared
Feature activation+0.017
Top resid features:
items
Token items
Feature activation+0.177
Top resid features:
such
Token such
Feature activation+5.910
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
sandwiches
Token sandwiches
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
salads
Token salads
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.074
Top resid features:
other
Token other
Feature activation+0.019
Top resid features:
lifestyle
Token lifestyle
Feature activation+0.158
Top resid features:
behaviors
Token behaviors
Feature activation+0.204
Top resid features:
,
Token,
Feature activation-0.118
Top resid features:
such
Token such
Feature activation+5.808
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
diet
Token diet
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
exercise
Token exercise
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.025
Top resid features:
the
Token the
Feature activation-0.118
Top resid features:
use
Token use
Feature activation+0.065
Top resid features:
of
Token of
Feature activation-0.140
Top resid features:
words
Token words
Feature activation+0.148
Top resid features:
such
Token such
Feature activation+5.880
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation+0.000
Top resid features:
ke
Tokenke
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.082
Top resid features:
more
Token more
Feature activation-0.031
Top resid features:
affluent
Token affluent
Feature activation+0.205
Top resid features:
areas
Token areas
Feature activation+0.103
Top resid features:
,
Token,
Feature activation-0.125
Top resid features:
such
Token such
Feature activation+5.840
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
eastern
Token eastern
Feature activation+0.000
Top resid features:
suburbs
Token suburbs
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
crises
Token crises
Feature activation+0.123
Top resid features:
have
Token have
Feature activation-0.112
Top resid features:
affected
Token affected
Feature activation+0.073
Top resid features:
social
Token social
Feature activation+0.139
Top resid features:
indicators
Token indicators
Feature activation+0.132
Top resid features:
such
Token such
Feature activation+4.699
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
listed
Token listed
Feature activation+0.000
Top resid features:
above
Token above
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
equipment
Token equipment
Feature activation+0.131
Top resid features:
from
Token from
Feature activation-0.089
Top resid features:
legendary
Token legendary
Feature activation+0.108
Top resid features:
audio
Token audio
Feature activation+0.235
Top resid features:
companies
Token companies
Feature activation+0.236
Top resid features:
such
Token such
Feature activation+5.698
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Ne
Token Ne
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Avalon
Token Avalon
Feature activation+0.000
Top resid features:
discouraged
Token discouraged
Feature activation+0.082
Top resid features:
-
Token-
Feature activation-0.044
Top resid features:
use
Tokenuse
Feature activation+0.028
Top resid features:
ingredients
Token ingredients
Feature activation+0.157
Top resid features:
,
Token,
Feature activation-0.118
Top resid features:
such
Token such
Feature activation+4.902
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
ep
Token ep
Feature activation+0.000
Top resid features:
hed
Tokenhed
Feature activation+0.000
Top resid features:
ra
Tokenra
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
critical
Token critical
Feature activation+0.034
Top resid features:
metals
Token metals
Feature activation+0.087
Top resid features:
for
Token for
Feature activation-0.132
Top resid features:
batteries
Token batteries
Feature activation+0.039
Top resid features:
,
Token,
Feature activation-0.142
Top resid features:
such
Token such
Feature activation+5.767
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
cob
Token cob
Feature activation+0.000
Top resid features:
alt
Tokenalt
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
lithium
Token lithium
Feature activation+0.000
Top resid features:
front
Token front
Feature activation+0.016
Top resid features:
ed
Tokened
Feature activation-0.023
Top resid features:
by
Token by
Feature activation-0.099
Top resid features:
famous
Token famous
Feature activation+0.145
Top resid features:
faces
Token faces
Feature activation+0.034
Top resid features:
such
Token such
Feature activation+5.779
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Dame
Token Dame
Feature activation+0.000
Top resid features:
Helen
Token Helen
Feature activation+0.000
Top resid features:
Mir
Token Mir
Feature activation+0.000
Top resid features:
ren
Tokenren
Feature activation+0.000
Top resid features:
require
Token require
Feature activation+0.080
Top resid features:
investment
Token investment
Feature activation+0.074
Top resid features:
by
Token by
Feature activation-0.124
Top resid features:
service
Token service
Feature activation+0.207
Top resid features:
providers
Token providers
Feature activation+0.218
Top resid features:
such
Token such
Feature activation+5.711
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
itself
Token itself
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
intelligence
Token intelligence
Feature activation+0.097
Top resid features:
official
Token official
Feature activation+0.067
Top resid features:
.
Token.
Feature activation-0.122
Top resid features:
Critics
Token Critics
Feature activation+0.201
Top resid features:
say
Token say
Feature activation+0.002
Top resid features:
such
Token such
Feature activation+5.840
Top resid features:
trips
Token trips
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
provided
Token provided
Feature activation+0.000
Top resid features:
diplomatic
Token diplomatic
Feature activation+0.000
Top resid features:
credibility
Token credibility
Feature activation+0.000
Top resid features:
no
Token no
Feature activation-0.056
Top resid features:
.
Token.
Feature activation-0.111
Top resid features:
Current
Token Current
Feature activation+0.038
Top resid features:
laws
Token laws
Feature activation+0.174
Top resid features:
permit
Token permit
Feature activation+0.132
Top resid features:
such
Token such
Feature activation+5.865
Top resid features:
citizenship
Token citizenship
Feature activation+0.000
Top resid features:
status
Token status
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
practice
Token practice
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.100
Top resid features:
routinely
Token routinely
Feature activation+0.108
Top resid features:
monitor
Token monitor
Feature activation+0.056
Top resid features:
social
Token social
Feature activation+0.142
Top resid features:
media
Token media
Feature activation+0.222
Top resid features:
such
Token such
Feature activation+5.376
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Facebook
Token Facebook
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Twitter
Token Twitter
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
par
Tokenpar
Feature activation+0.022
Top resid features:
ation
Tokenation
Feature activation-0.001
Top resid features:
can
Token can
Feature activation-0.071
Top resid features:
involve
Token involve
Feature activation+0.240
Top resid features:
tasks
Token tasks
Feature activation+0.137
Top resid features:
such
Token such
Feature activation+5.789
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
reviewing
Token reviewing
Feature activation+0.000
Top resid features:
opponent
Token opponent
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
companies
Token companies
Feature activation+0.148
Top resid features:
with
Token with
Feature activation-0.093
Top resid features:
growth
Token growth
Feature activation+0.072
Top resid features:
potential
Token potential
Feature activation+0.060
Top resid features:
,
Token,
Feature activation-0.125
Top resid features:
such
Token such
Feature activation+5.850
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
environment
Token environment
Feature activation+0.000
Top resid features:
important
Token important
Feature activation+0.008
Top resid features:
French
Token French
Feature activation+0.047
Top resid features:
grammar
Token grammar
Feature activation+0.140
Top resid features:
rules
Token rules
Feature activation+0.126
Top resid features:
,
Token,
Feature activation-0.135
Top resid features:
such
Token such
Feature activation+4.896
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
ignoring
Token ignoring
Feature activation+0.000
Top resid features:
accents
Token accents
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
capital
Token capital
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.113
Top resid features:
countries
Token countries
Feature activation+0.160
Top resid features:
'
Token'
Feature activation-0.020
Top resid features:
currencies
Token currencies
Feature activation+0.230
Top resid features:
,
Token,
Feature activation-0.124
Top resid features:
such
Token such
Feature activation+5.622
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
yuan
Token yuan
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.22

Head 2: 0.03

Head 3: 0.24

Head 4: 0.07

Head 5: 0.13

Head 6: 0.03

Head 7: 0.06

Head 8: 0.03

Head 9: 0.07

Head 10: 0.05

Head 11: 0.03

Positive logits

azeera3.25

アル3.03

��2.99

predec2.93

worldly2.91

ancies2.85

allery2.85

requent2.73

omal2.72

prominently2.69

senal2.64

enriched2.63

tymology2.63

ocating2.63

vae2.62

permissible2.61

redistributed2.60

profits2.57

ahime2.57

periodic2.56

Negative logits

Claw-2.75

Cyn-2.60

Tray-2.60

wards-2.60

Orn-2.54

Helic-2.53

Ridge-2.43

Hood-2.42

Grill-2.41

hesda-2.40

Briggs-2.38

Crush-2.38

Drum-2.33

Potato-2.32

scient-2.31

bell-2.31

Beach-2.30

Hearth-2.30

Freak-2.30

Chal-2.29

INTERVAL 1.226 - 1.362
CONTAINS 0.000%

GST
Token GST
Feature activation+0.000
on
Token on
Feature activation+0.000
imported
Token imported
Feature activation+0.000
digital
Token digital
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+1.362
as
Token as
Feature activation+0.000
Netflix
Token Netflix
Feature activation+0.000
and
Token and
Feature activation+0.000
Spotify
Token Spotify
Feature activation+0.000
and
Token and
Feature activation+0.000
citing
Token citing
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
that
Token that
Feature activation+0.000
insist
Token insist
Feature activation+0.000
such
Token such
Feature activation+1.319
programs
Token programs
Feature activation+0.000
drive
Token drive
Feature activation+0.000
inequality
Token inequality
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.090 - 1.226
CONTAINS 0.000%

pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
pre
Tokenpre
Feature activation+0.000
pared
Tokenpared
Feature activation+0.000
items
Token items
Feature activation+0.000
such
Token such
Feature activation+1.177
as
Token as
Feature activation+0.000
sandwiches
Token sandwiches
Feature activation+0.000
,
Token,
Feature activation+0.000
salads
Token salads
Feature activation+0.000
,
Token,
Feature activation+0.000
human
Token human
Feature activation+0.000
eye
Token eye
Feature activation+0.000
--
Token --
Feature activation+0.000
longer
Token longer
Feature activation+0.000
wavelengths
Token wavelengths
Feature activation+0.000
such
Token such
Feature activation+1.215
as
Token as
Feature activation+0.000
infrared
Token infrared
Feature activation+0.000
light
Token light
Feature activation+0.000
pass
Token pass
Feature activation+0.000
through
Token through
Feature activation+0.000

INTERVAL 0.954 - 1.090
CONTAINS 0.001%

no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
Current
Token Current
Feature activation+0.000
laws
Token laws
Feature activation+0.000
permit
Token permit
Feature activation+0.000
such
Token such
Feature activation+0.954
citizenship
Token citizenship
Feature activation+0.000
status
Token status
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
practice
Token practice
Feature activation+0.000
crises
Token crises
Feature activation+0.000
have
Token have
Feature activation+0.000
affected
Token affected
Feature activation+0.000
social
Token social
Feature activation+0.000
indicators
Token indicators
Feature activation+0.000
such
Token such
Feature activation+1.041
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
listed
Token listed
Feature activation+0.000
above
Token above
Feature activation+0.000
(
Token (
Feature activation+0.000
front
Token front
Feature activation+0.000
ed
Tokened
Feature activation+0.000
by
Token by
Feature activation+0.000
famous
Token famous
Feature activation+0.000
faces
Token faces
Feature activation+0.000
such
Token such
Feature activation+0.988
as
Token as
Feature activation+0.000
Dame
Token Dame
Feature activation+0.000
Helen
Token Helen
Feature activation+0.000
Mir
Token Mir
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
critical
Token critical
Feature activation+0.000
metals
Token metals
Feature activation+0.000
for
Token for
Feature activation+0.000
batteries
Token batteries
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.000
as
Token as
Feature activation+0.000
cob
Token cob
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
and
Token and
Feature activation+0.000
lithium
Token lithium
Feature activation+0.000
require
Token require
Feature activation+0.000
investment
Token investment
Feature activation+0.000
by
Token by
Feature activation+0.000
service
Token service
Feature activation+0.000
providers
Token providers
Feature activation+0.000
such
Token such
Feature activation+0.973
as
Token as
Feature activation+0.000
itself
Token itself
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.817 - 0.954
CONTAINS 0.001%

of
Token of
Feature activation+0.000
joint
Token joint
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
ventures
Token ventures
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.869
as
Token as
Feature activation+0.000
between
Token between
Feature activation+0.000
Pun
Token Pun
Feature activation+0.000
j
Tokenj
Feature activation+0.000
Lloyd
Token Lloyd
Feature activation+0.000
market
Token market
Feature activation+0.000
countries
Token countries
Feature activation+0.000
'
Token'
Feature activation+0.000
currencies
Token currencies
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.903
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
yuan
Token yuan
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
important
Token important
Feature activation+0.000
French
Token French
Feature activation+0.000
grammar
Token grammar
Feature activation+0.000
rules
Token rules
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.909
as
Token as
Feature activation+0.000
ignoring
Token ignoring
Feature activation+0.000
accents
Token accents
Feature activation+0.000
on
Token on
Feature activation+0.000
capital
Token capital
Feature activation+0.000
Vegan
Token Vegan
Feature activation+0.000
category
Token category
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
dishes
Token dishes
Feature activation+0.000
such
Token such
Feature activation+0.860
as
Token as
Feature activation+0.000
corn
Token corn
Feature activation+0.000
ch
Token ch
Feature activation+0.000
owder
Tokenowder
Feature activation+0.000
and
Token and
Feature activation+0.000
Byron
Token Byron
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
writers
Token writers
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.893
as
Token as
Feature activation+0.000
his
Token his
Feature activation+0.000
friend
Token friend
Feature activation+0.000
Hob
Token Hob
Feature activation+0.000
house
Tokenhouse
Feature activation+0.000

INTERVAL 0.681 - 0.817
CONTAINS 0.001%

Americans
Token Americans
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
spiritual
Token spiritual
Feature activation+0.000
practices
Token practices
Feature activation+0.000
such
Token such
Feature activation+0.720
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ghost
Tokenghost
Feature activation+0.000
dancing
Token dancing
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
gam
Token gam
Feature activation+0.000
ified
Tokenified
Feature activation+0.000
such
Token such
Feature activation+0.814
basic
Token basic
Feature activation+0.000
pursuits
Token pursuits
Feature activation+0.000
as
Token as
Feature activation+0.000
going
Token going
Feature activation+0.000
outside
Token outside
Feature activation+0.000
is
Token is
Feature activation+0.000
imp
Token imp
Feature activation+0.000
eded
Tokeneded
Feature activation+0.000
by
Token by
Feature activation+0.000
trends
Token trends
Feature activation+0.000
such
Token such
Feature activation+0.712
as
Token as
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
other
Token other
Feature activation+0.000
teenagers
Token teenagers
Feature activation+0.000
using
Token using
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
such
Token such
Feature activation+0.685
as
Token as
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
will
Token will
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
many
Token many
Feature activation+0.000
substances
Token substances
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.805
as
Token as
Feature activation+0.000
chlorine
Token chlorine
Feature activation+0.000
,
Token,
Feature activation+0.000
iodine
Token iodine
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.545 - 0.681
CONTAINS 0.002%

as
Token as
Feature activation+0.000
Free
Token Free
Feature activation+0.000
Software
Token Software
Feature activation+0.000
solutions
Token solutions
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.571
as
Token as
Feature activation+0.000
Arch
Token Arch
Feature activation+0.000
ival
Tokenival
Feature activation+0.000
and
Token and
Feature activation+0.000
Backup
Token Backup
Feature activation+0.000
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
locating
Token locating
Feature activation+0.000
such
Token such
Feature activation+0.639
episodes
Token episodes
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
observing
Token observing
Feature activation+0.000
what
Token what
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+0.000
comments
Token comments
Feature activation+0.000
such
Token such
Feature activation+0.566
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
liked
Token liked
Feature activation+0.000
work
Tokenwork
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
for
Token for
Feature activation+0.000
employees
Token employees
Feature activation+0.000
such
Token such
Feature activation+0.631
as
Token as
Feature activation+0.000
trades
Token trades
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
who
Token who
Feature activation+0.000
do
Token do
Feature activation+0.000
help
Token help
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Academic
Token Academic
Feature activation+0.000
institutions
Token institutions
Feature activation+0.000
such
Token such
Feature activation+0.652
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Poverty
Token Poverty
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000

INTERVAL 0.409 - 0.545
CONTAINS 0.002%

has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
offer
Token offer
Feature activation+0.000
.
Token.
Feature activation+0.000
Individuals
Token Individuals
Feature activation+0.000
such
Token such
Feature activation+0.439
as
Token as
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
F
Token F
Feature activation+0.000
isch
Tokenisch
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
on
Token on
Feature activation+0.000
solving
Token solving
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
problems
Token problems
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.457
as
Token as
Feature activation+0.000
employee
Token employee
Feature activation+0.000
exams
Token exams
Feature activation+0.000
and
Token and
Feature activation+0.000
testing
Token testing
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
warn
Token warn
Feature activation+0.000
owners
Token owners
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+0.425
a
Token a
Feature activation+0.000
pit
Token pit
Feature activation+0.000
fall
Tokenfall
Feature activation+0.000
.
Token.
Feature activation+0.000
According
Token According
Feature activation+0.000
users
Token users
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
such
Token such
Feature activation+0.448
intimidation
Token intimidation
Feature activation+0.000
;
Token;
Feature activation+0.000
a
Token a
Feature activation+0.000
third
Token third
Feature activation+0.000
say
Token say
Feature activation+0.000
susp
Token susp
Feature activation+0.000
ends
Tokenends
Feature activation+0.000
employees
Token employees
Feature activation+0.000
while
Token while
Feature activation+0.000
investigating
Token investigating
Feature activation+0.000
such
Token such
Feature activation+0.421
cases
Token cases
Feature activation+0.000
.)
Token.)
Feature activation+0.000
His
Token His
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.272 - 0.409
CONTAINS 0.003%

.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
never
Token never
Feature activation+0.000
heard
Token heard
Feature activation+0.000
such
Token such
Feature activation+0.380
a
Token a
Feature activation+0.000
tir
Token tir
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
mercenaries
Token mercenaries
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
received
Token received
Feature activation+0.000
such
Token such
Feature activation+0.318
payments
Token payments
Feature activation+0.000
complained
Token complained
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
electoral
Token electoral
Feature activation+0.000
tally
Token tally
Feature activation+0.000
,
Token,
Feature activation+0.000
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
such
Token such
Feature activation+0.403
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
household
Token household
Feature activation+0.000
names
Token names
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.359
fake
Token fake
Feature activation+0.000
service
Token service
Feature activation+0.000
providers
Token providers
Feature activation+0.000
have
Token have
Feature activation+0.000
around
Token around
Feature activation+0.000
area
Token area
Feature activation+0.000
was
Token was
Feature activation+0.000
primed
Token primed
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
such
Token such
Feature activation+0.300
an
Token an
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
event
Token event
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000

INTERVAL 0.136 - 0.272
CONTAINS 0.003%

party
Token party
Feature activation+0.000
shares
Token shares
Feature activation+0.000
these
Token these
Feature activation+0.000
receipts
Token receipts
Feature activation+0.000
with
Token with
Feature activation+0.000
such
Token such
Feature activation+0.231
groups
Token groups
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Hamilton
Token Hamilton
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
fabricated
Token fabricated
Feature activation+0.000
the
Token the
Feature activation+0.000
events
Token events
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.265
detail
Token detail
Feature activation+0.000
and
Token and
Feature activation+0.000
were
Token were
Feature activation+0.000
likely
Token likely
Feature activation+0.000
telling
Token telling
Feature activation+0.000
fifth
Tokenfifth
Feature activation+0.000
Army
Token Army
Feature activation+0.000
Group
Token Group
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
such
Token such
Feature activation+0.214
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
speed
Token speed
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
negative
Token negative
Feature activation+0.000
emotions
Token emotions
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.233
as
Token as
Feature activation+0.000
fear
Token fear
Feature activation+0.000
or
Token or
Feature activation+0.000
grief
Token grief
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
legislators
Token legislators
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
such
Token such
Feature activation+0.180
appointments
Token appointments
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.136
CONTAINS 99.987%

integral
Token integral
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
corporate
Token corporate
Feature activation+0.000
model
Token model
Feature activation+0.000
of
Token of
Feature activation+0.000
higher
Token higher
Feature activation+0.000
education
Token education
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
microphones
Token microphones
Feature activation+0.000
were
Token were
Feature activation+0.000
on
Token on
Feature activation+0.000
in
Token in
Feature activation+0.000
reference
Token reference
Feature activation+0.000
to
Token to
Feature activation+0.000
Mrs
Token Mrs
Feature activation+0.000
Kir
Token Kir
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
and
Token and
Feature activation+0.000
wood
Token wood
Feature activation+0.000
products
Token products
Feature activation+0.000
industry
Token industry
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
billion
Token billion
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
is
Token is
Feature activation+0.000
incorrect
Token incorrect
Feature activation+0.000
,"
Token,"
Feature activation+0.000
St
Token St
Feature activation+0.000
rief
Tokenrief
Feature activation+0.000
said
Token said
Feature activation+0.000
Ray
Token Ray
Feature activation+0.000
Allen
Token Allen
Feature activation+0.000
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
talents
Token talents
Feature activation+0.000
to
Token to
Feature activation+0.000
South
Token South
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Big
Token Big
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 H0.3: (feature 15142)

TOP ACTIVATIONS
MAX = 1.918

V
TokenV
Feature activation+0.000
,
Token,
Feature activation+0.000
January
Token January
Feature activation+0.000
25
Token 25
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+1.918
put
Tokenput
Feature activation+0.000
nik
Tokennik
Feature activation+0.000
)
Token)
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
The
Token The
Feature activation+0.000
u
Token u
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
his
Token his
Feature activation+0.000
Z
Token Z
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.908
wing
Tokenwing
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Observatory
Token Observatory
Feature activation+0.000
for
Token for
Feature activation+0.000
Human
Token Human
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+1.894
OH
TokenOH
Feature activation+0.000
R
TokenR
Feature activation+0.000
)
Token)
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.893
ew
Tokenew
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
the
Token the
Feature activation+0.000
E
Token E
Feature activation+0.000
's
Token's
Feature activation+0.000
Garden
Token Garden
Feature activation+0.000
Center
Token Center
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.870
ud
Tokenud
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
Nurs
Token Nurs
Feature activation+0.000
eries
Tokeneries
Feature activation+0.000
West
Token West
Feature activation+0.000
-
Token-
Feature activation+0.000
human
Tokenhuman
Feature activation+0.000
oid
Tokenoid
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
(
Token(
Feature activation+0.000
S
TokenS
Feature activation+1.844
aul
Tokenaul
Feature activation+0.000
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
/
Token/
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.761
.,
Token.,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
says
Token says
Feature activation+0.000
one
Token one
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
wholesale
Token wholesale
Feature activation+0.000
M
Token M
Feature activation+0.000
(
Token(
Feature activation+0.000
S
TokenS
Feature activation+1.731
)
Token)
Feature activation+0.000
P
TokenP
Feature activation+0.000
expenses
Token expenses
Feature activation+0.000
scandal
Token scandal
Feature activation+0.000
?
Token?
Feature activation+0.000
Nurs
Token Nurs
Feature activation+0.000
eries
Tokeneries
Feature activation+0.000
West
Token West
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.724
yl
Tokenyl
Feature activation+0.000
van
Tokenvan
Feature activation+0.000
Nurs
Token Nurs
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Industry
Token Industry
Feature activation+0.000
for
Token for
Feature activation+0.000
National
Token National
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+1.723
AST
TokenAST
Feature activation+0.000
IND
TokenIND
Feature activation+0.000
)
Token)
Feature activation+0.000
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Stra
Token Stra
Feature activation+0.000
fe
Tokenfe
Feature activation+0.000
,
Token,
Feature activation+0.000
Seven
Token Seven
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.694
ided
Tokenided
Feature activation+0.000
Strike
Token Strike
Feature activation+0.000
,
Token,
Feature activation+0.000
Se
Token Se
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
him
Token him
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.694
olis
Tokenolis
Feature activation+0.000
was
Token was
Feature activation+0.000
notified
Token notified
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
s
Tokens
Feature activation+0.000
lowered
Token lowered
Feature activation+0.000
his
Token his
Feature activation+0.000
O
Token O
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.683
wing
Tokenwing
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
u
Token u
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
essler
Tokenessler
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+0.000
Marc
TokenMarc
Feature activation+0.000
S
TokenS
Feature activation+1.677
essler
Tokenessler
Feature activation+0.000
NFL
TokenNFL
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Roberts
TokenRoberts
Feature activation+0.000
for
Token for
Feature activation+0.000
espionage
Token espionage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.673
ale
Tokenale
Feature activation+0.000
h
Tokenh
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
did
Token did
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.655
ect
Tokenect
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
colon
Token colon
Feature activation+0.000
leading
Token leading
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.654
amples
Tokenamples
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
little
Token little
Feature activation+0.000
known
Token known
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
PR
Token PR
Feature activation+0.000
S
TokenS
Feature activation+1.643
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
widely
Token widely
Feature activation+0.000
utilized
Token utilized
Feature activation+0.000
Po
Token Po
Feature activation+0.000
S
TokenS
Feature activation+1.642
system
Token system
Feature activation+0.000
Air
Token Air
Feature activation+0.000
RE
TokenRE
Feature activation+0.000
GI
TokenGI
Feature activation+0.000
.
Token.
Feature activation+0.000
o
Tokeno
Feature activation+0.000
at
Token at
Feature activation+0.000
Ottawa
Token Ottawa
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.632
agin
Tokenagin
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
St
Token St
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 8.033

V
TokenV
Feature activation+0.082
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
January
Token January
Feature activation+0.119
Top resid features:
25
Token 25
Feature activation+0.063
Top resid features:
(
Token (
Feature activation+0.254
Top resid features:
S
TokenS
Feature activation+7.865
Top resid features:
put
Tokenput
Feature activation+0.000
Top resid features:
nik
Tokennik
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
u
Token u
Feature activation+0.106
Top resid features:
pped
Tokenpped
Feature activation+0.043
Top resid features:
his
Token his
Feature activation+0.029
Top resid features:
Z
Token Z
Feature activation+0.181
Top resid features:
-
Token-
Feature activation+0.153
Top resid features:
S
TokenS
Feature activation+5.799
Top resid features:
wing
Tokenwing
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Observatory
Token Observatory
Feature activation+0.054
Top resid features:
for
Token for
Feature activation+0.062
Top resid features:
Human
Token Human
Feature activation+0.087
Top resid features:
Rights
Token Rights
Feature activation+0.107
Top resid features:
(
Token (
Feature activation+0.265
Top resid features:
S
TokenS
Feature activation+7.847
Top resid features:
OH
TokenOH
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.147
Top resid features:
âĢ
TokenâĢ
Feature activation+0.099
Top resid features:
Ŀ
TokenĿ
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation+0.113
Top resid features:
Ċ
TokenĊ
Feature activation+0.117
Top resid features:
S
TokenS
Feature activation+8.005
Top resid features:
ew
Tokenew
Feature activation+0.000
Top resid features:
ard
Tokenard
Feature activation+0.000
Top resid features:
insisted
Token insisted
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
E
Token E
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.140
Top resid features:
Garden
Token Garden
Feature activation+0.044
Top resid features:
Center
Token Center
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.095
Top resid features:
Ċ
TokenĊ
Feature activation+0.087
Top resid features:
S
TokenS
Feature activation+8.033
Top resid features:
ud
Tokenud
Feature activation+0.000
Top resid features:
bury
Tokenbury
Feature activation+0.000
Top resid features:
Nurs
Token Nurs
Feature activation+0.000
Top resid features:
eries
Tokeneries
Feature activation+0.000
Top resid features:
West
Token West
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.080
Top resid features:
human
Tokenhuman
Feature activation+0.040
Top resid features:
oid
Tokenoid
Feature activation+0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.550
Top resid features:
(
Token(
Feature activation+0.986
Top resid features:
S
TokenS
Feature activation+7.157
Top resid features:
aul
Tokenaul
Feature activation+0.000
Top resid features:
Lo
Token Lo
Feature activation+0.000
Top resid features:
eb
Tokeneb
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
AFP
TokenAFP
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.060
Top resid features:
of
Token of
Feature activation+0.080
Top resid features:
that
Token that
Feature activation+0.070
Top resid features:
B
Token B
Feature activation+0.288
Top resid features:
.
Token.
Feature activation+0.296
Top resid features:
S
TokenS
Feature activation+7.642
Top resid features:
.,
Token.,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.056
Top resid features:
a
Token a
Feature activation+0.085
Top resid features:
wholesale
Token wholesale
Feature activation+0.050
Top resid features:
M
Token M
Feature activation+0.249
Top resid features:
(
Token(
Feature activation+0.919
Top resid features:
S
TokenS
Feature activation+7.167
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
P
TokenP
Feature activation+0.000
Top resid features:
expenses
Token expenses
Feature activation+0.000
Top resid features:
scandal
Token scandal
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Nurs
Token Nurs
Feature activation+0.052
Top resid features:
eries
Tokeneries
Feature activation+0.014
Top resid features:
West
Token West
Feature activation+0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
S
TokenS
Feature activation+5.851
Top resid features:
yl
Tokenyl
Feature activation+0.000
Top resid features:
van
Tokenvan
Feature activation+0.000
Top resid features:
Nurs
Token Nurs
Feature activation+0.000
Top resid features:
ery
Tokenery
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Industry
Token Industry
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.069
Top resid features:
National
Token National
Feature activation+0.081
Top resid features:
Defense
Token Defense
Feature activation+0.064
Top resid features:
(
Token (
Feature activation+0.265
Top resid features:
S
TokenS
Feature activation+6.512
Top resid features:
AST
TokenAST
Feature activation+0.000
Top resid features:
IND
TokenIND
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
reveals
Token reveals
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Stra
Token Stra
Feature activation+0.050
Top resid features:
fe
Tokenfe
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.097
Top resid features:
Seven
Token Seven
Feature activation+0.095
Top resid features:
-
Token-
Feature activation+0.154
Top resid features:
S
TokenS
Feature activation+6.134
Top resid features:
ided
Tokenided
Feature activation+0.000
Top resid features:
Strike
Token Strike
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Se
Token Se
Feature activation+0.000
Top resid features:
ism
Tokenism
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.050
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.098
Top resid features:
.
Token.
Feature activation+0.191
Top resid features:
Ċ
TokenĊ
Feature activation+0.113
Top resid features:
Ċ
TokenĊ
Feature activation+0.108
Top resid features:
S
TokenS
Feature activation+7.947
Top resid features:
olis
Tokenolis
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
notified
Token notified
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.110
Top resid features:
lowered
Token lowered
Feature activation+0.028
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
O
Token O
Feature activation+0.187
Top resid features:
-
Token-
Feature activation+0.117
Top resid features:
S
TokenS
Feature activation+7.775
Top resid features:
wing
Tokenwing
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
u
Token u
Feature activation+0.000
Top resid features:
pped
Tokenpped
Feature activation+0.000
Top resid features:
essler
Tokenessler
Feature activation-0.038
Top resid features:
on
Token on
Feature activation+0.072
Top resid features:
Twitter
Token Twitter
Feature activation+0.060
Top resid features:
@
Token @
Feature activation+0.115
Top resid features:
Marc
TokenMarc
Feature activation+0.014
Top resid features:
S
TokenS
Feature activation+5.850
Top resid features:
essler
Tokenessler
Feature activation+0.000
Top resid features:
NFL
TokenNFL
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
Roberts
TokenRoberts
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.057
Top resid features:
espionage
Token espionage
Feature activation+0.077
Top resid features:
.
Token.
Feature activation+0.187
Top resid features:
Ċ
TokenĊ
Feature activation+0.107
Top resid features:
Ċ
TokenĊ
Feature activation+0.112
Top resid features:
S
TokenS
Feature activation+7.884
Top resid features:
ale
Tokenale
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
[
Token [
Feature activation+0.122
Top resid features:
edit
Token edit
Feature activation+0.001
Top resid features:
]
Token ]
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.103
Top resid features:
Ċ
TokenĊ
Feature activation+0.095
Top resid features:
S
TokenS
Feature activation+5.848
Top resid features:
ect
Tokenect
Feature activation+0.000
Top resid features:
ions
Tokenions
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
colon
Token colon
Feature activation+0.000
Top resid features:
leading
Token leading
Feature activation+0.026
Top resid features:
role
Token role
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.194
Top resid features:
Ċ
TokenĊ
Feature activation+0.126
Top resid features:
Ċ
TokenĊ
Feature activation+0.134
Top resid features:
S
TokenS
Feature activation+7.780
Top resid features:
amples
Tokenamples
Feature activation+0.000
Top resid features:
[
Token [
Feature activation+0.000
Top resid features:
edit
Token edit
Feature activation+0.000
Top resid features:
]
Token ]
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
little
Token little
Feature activation+0.055
Top resid features:
known
Token known
Feature activation+0.055
Top resid features:
about
Token about
Feature activation+0.071
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
PR
Token PR
Feature activation+0.054
Top resid features:
S
TokenS
Feature activation+7.967
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
most
Token most
Feature activation+0.063
Top resid features:
widely
Token widely
Feature activation+0.034
Top resid features:
utilized
Token utilized
Feature activation+0.061
Top resid features:
Po
Token Po
Feature activation+0.017
Top resid features:
S
TokenS
Feature activation+7.809
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
Air
Token Air
Feature activation+0.000
Top resid features:
RE
TokenRE
Feature activation+0.000
Top resid features:
GI
TokenGI
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation+0.086
Top resid features:
at
Token at
Feature activation+0.053
Top resid features:
Ottawa
Token Ottawa
Feature activation+0.117
Top resid features:
Ċ
TokenĊ
Feature activation+0.104
Top resid features:
Ċ
TokenĊ
Feature activation+0.108
Top resid features:
S
TokenS
Feature activation+7.810
Top resid features:
agin
Tokenagin
Feature activation+0.000
Top resid features:
aw
Tokenaw
Feature activation+0.000
Top resid features:
Valley
Token Valley
Feature activation+0.000
Top resid features:
St
Token St
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.25

Head 2: 0.02

Head 3: 0.24

Head 4: 0.07

Head 5: 0.13

Head 6: 0.02

Head 7: 0.07

Head 8: 0.02

Head 9: 0.06

Head 10: 0.08

Head 11: 0.03

Positive logits

amm3.79

AG3.63

ADA3.60

ustainable3.60

inking3.60

ensitivity3.58

ledge3.58

ITH3.55

atal3.53

igma3.52

ink3.43

aving3.42

ustain3.41

ESSION3.39

ixty3.38

natureconservancy3.36

RS3.35

outheast3.33

omon3.30

AND3.26

Negative logits

DragonMagazine-4.32

��-3.97

��-3.87

EStream-3.80

ça-3.50

actionGroup-3.46

20439-3.46

dylib-3.43

��-3.38

enance-3.26

luaj-3.15

EStreamFrame-3.13

assador-3.11

-3.08

inois-3.06

-3.01

geoning-3.00

easing-2.91

guiActiveUn-2.91

serving-2.90

INTERVAL 1.726 - 1.918
CONTAINS 0.001%

-
Token-
Feature activation+0.000
human
Tokenhuman
Feature activation+0.000
oid
Tokenoid
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
(
Token(
Feature activation+0.000
S
TokenS
Feature activation+1.844
aul
Tokenaul
Feature activation+0.000
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
/
Token/
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
u
Token u
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
his
Token his
Feature activation+0.000
Z
Token Z
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.908
wing
Tokenwing
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
V
TokenV
Feature activation+0.000
,
Token,
Feature activation+0.000
January
Token January
Feature activation+0.000
25
Token 25
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+1.918
put
Tokenput
Feature activation+0.000
nik
Tokennik
Feature activation+0.000
)
Token)
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
The
Token The
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
wholesale
Token wholesale
Feature activation+0.000
M
Token M
Feature activation+0.000
(
Token(
Feature activation+0.000
S
TokenS
Feature activation+1.731
)
Token)
Feature activation+0.000
P
TokenP
Feature activation+0.000
expenses
Token expenses
Feature activation+0.000
scandal
Token scandal
Feature activation+0.000
?
Token?
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.761
.,
Token.,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
says
Token says
Feature activation+0.000
one
Token one
Feature activation+0.000

INTERVAL 1.534 - 1.726
CONTAINS 0.002%

water
Token water
Feature activation+0.000
flux
Token flux
Feature activation+0.000
es
Tokenes
Feature activation+0.000
through
Token through
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+1.618
2
Token 2
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
far
Token far
Feature activation+0.000
ce
Tokence
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.536
ri
Tokenri
Feature activation+0.000
K
Token K
Feature activation+0.000
av
Tokenav
Feature activation+0.000
uru
Tokenuru
Feature activation+0.000
,
Token,
Feature activation+0.000
leading
Token leading
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.654
amples
Tokenamples
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
too
Token too
Feature activation+0.000
surprising
Token surprising
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.630
ega
Tokenega
Feature activation+0.000
has
Token has
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
a
Token a
Feature activation+0.000
string
Token string
Feature activation+0.000
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
D
Token D
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
S
TokenS
Feature activation+1.558
ou
Tokenou
Feature activation+0.000
za
Tokenza
Feature activation+0.000
could
Token could
Feature activation+0.000
hardly
Token hardly
Feature activation+0.000
plead
Token plead
Feature activation+0.000

INTERVAL 1.342 - 1.534
CONTAINS 0.001%

18
Token 18
Feature activation+0.000
September
Token September
Feature activation+0.000
[
Token [
Feature activation+0.000
O
TokenO
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.396
.
Token.
Feature activation+0.000
6
Token 6
Feature activation+0.000
September
Token September
Feature activation+0.000
]
Token]
Feature activation+0.000
18
Token 18
Feature activation+0.000
-
Token-
Feature activation+0.000
7
Token7
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.507
ifted
Tokenifted
Feature activation+0.000
through
Token through
Feature activation+0.000
and
Token and
Feature activation+0.000
explained
Token explained
Feature activation+0.000
every
Token every
Feature activation+0.000
AG
Token AG
Feature activation+0.000
and
Token and
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
S
TokenS
Feature activation+1.465
ci
Tokenci
Feature activation+0.000
ences
Tokenences
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
responding
Token responding
Feature activation+0.000
K
TokenK
Feature activation+0.000
Din
Token Din
Feature activation+0.000
amo
Tokenamo
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.389
ev
Tokenev
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
dominated
Token dominated
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
cut
Token cut
Feature activation+0.000
his
Token his
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.422
ell
Tokenell
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.151 - 1.342
CONTAINS 0.001%

Cody
Token Cody
Feature activation+0.000
R
Token R
Feature activation+0.000
iggs
Tokeniggs
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.258
:
Token:
Feature activation+0.000
14
Token 14
Feature activation+0.000
Jay
Token Jay
Feature activation+0.000
len
Tokenlen
Feature activation+0.000
Watkins
Token Watkins
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.193
DF
TokenDF
Feature activation+0.000
sources
Token sources
Feature activation+0.000
explain
Token explain
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
Agency
Token Agency
Feature activation+0.000
,
Token,
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Lisa
Token Lisa
Feature activation+0.000
Di
Token Di
Feature activation+0.000
S
TokenS
Feature activation+1.253
ante
Tokenante
Feature activation+0.000
-
Token-
Feature activation+0.000
Frank
TokenFrank
Feature activation+0.000
,
Token,
Feature activation+0.000
Sab
Token Sab
Feature activation+0.000
starts
Token starts
Feature activation+0.000
and
Token and
Feature activation+0.000
caused
Token caused
Feature activation+0.000
then
Token then
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+1.211
eah
Tokeneah
Feature activation+0.000
awks
Tokenawks
Feature activation+0.000
coach
Token coach
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Hol
Token Hol
Feature activation+0.000
football
Token football
Feature activation+0.000
team
Token team
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+1.177
oph
Tokenoph
Feature activation+0.000
omore
Tokenomore
Feature activation+0.000
slump
Token slump
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 0.959 - 1.151
CONTAINS 0.001%

6
Token 6
Feature activation+0.000
G
Token G
Feature activation+0.000
bps
Tokenbps
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.985
ATA
TokenATA
Feature activation+0.000
3
Token 3
Feature activation+0.000
G
Token G
Feature activation+0.000
bps
Tokenbps
Feature activation+0.000
4
Token 4
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
"
Token "
Feature activation+0.000
S
TokenS
Feature activation+1.074
ki
Tokenki
Feature activation+0.000
mount
Token mount
Feature activation+0.000
aine
Tokenaine
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
and
Token and
Feature activation+0.000
ately
Tokenately
Feature activation+0.000
collapsed
Token collapsed
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.077
.
Token.
Feature activation+0.000
Y
Token Y
Feature activation+0.000
eddy
Tokeneddy
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
appa
Tokenappa
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
N
TokenN
Feature activation+0.000
UR
TokenUR
Feature activation+0.000
S
TokenS
Feature activation+1.075
ES
TokenES
Feature activation+0.000
GA
Token GA
Feature activation+0.000
VE
TokenVE
Feature activation+0.000
PAR
Token PAR
Feature activation+0.000
ENTS
TokenENTS
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
started
Token started
Feature activation+0.000
using
Token using
Feature activation+0.000
open
Token open
Feature activation+0.000
S
TokenS
Feature activation+0.965
USE
TokenUSE
Feature activation+0.000
,
Token,
Feature activation+0.000
open
Token open
Feature activation+0.000
S
TokenS
Feature activation+0.794
USE
TokenUSE
Feature activation+0.000

INTERVAL 0.767 - 0.959
CONTAINS 0.001%

.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.855
ixty
Tokenixty
Feature activation+0.000
-
Token-
Feature activation+0.000
two
Tokentwo
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
who
Token who
Feature activation+0.000
worked
Token worked
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
CPR
Token CPR
Feature activation+0.000
S
TokenS
Feature activation+0.835
paper
Token paper
Feature activation+0.000
was
Token was
Feature activation+0.000
David
Token David
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
's
Token's
Feature activation+0.000
I
Token I
Feature activation+0.000
owe
Token owe
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.910
inn
Tokeninn
Feature activation+0.000
F
Token F
Feature activation+0.000
é
Tokené
Feature activation+0.000
in
Tokenin
Feature activation+0.000
said
Token said
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RED
TokenRED
Feature activation+0.000
ST
TokenST
Feature activation+0.000
ONE
TokenONE
Feature activation+0.000
AR
Token AR
Feature activation+0.000
S
TokenS
Feature activation+0.770
EN
TokenEN
Feature activation+0.000
AL
TokenAL
Feature activation+0.000
,
Token,
Feature activation+0.000
Ala
Token Ala
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token"
Feature activation+0.000
was
Token was
Feature activation+0.000
featured
Token featured
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token "
Feature activation+0.000
S
TokenS
Feature activation+0.808
ongs
Tokenongs
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Key
Token Key
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.575 - 0.767
CONTAINS 0.001%

oding
Tokenoding
Feature activation+0.000
Palm
Token Palm
Feature activation+0.000
and
Token and
Feature activation+0.000
Seven
Token Seven
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.663
ided
Tokenided
Feature activation+0.000
Strike
Token Strike
Feature activation+0.000
;
Token;
Feature activation+0.000
Witch
Token Witch
Feature activation+0.000
Doctor
Token Doctor
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
S
TokenS
Feature activation+0.667
ev
Tokenev
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
FC
Token FC
Feature activation+0.000
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+0.000
Old
Token Old
Feature activation+0.000
Or
Token Or
Feature activation+0.000
chard
Tokenchard
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.758
aco
Tokenaco
Feature activation+0.000
alternative
Token alternative
Feature activation+0.000
education
Token education
Feature activation+0.000
program
Token program
Feature activation+0.000
.
Token.
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Crescent
Token Crescent
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+0.658
ARC
TokenARC
Feature activation+0.000
)
Token)
Feature activation+0.000
util
Token util
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
ride
Token ride
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.592
aying
Tokenaying
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000

INTERVAL 0.384 - 0.575
CONTAINS 0.001%

pressure
Token pressure
Feature activation+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
with
Token with
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.556
2
Token 2
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
.
Token.
Feature activation+0.000
Later
Token Later
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.542
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
Fury
Token Fury
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Xer
Token Xer
Feature activation+0.000
'
Token'
Feature activation+0.000
S
TokenS
Feature activation+0.566
ai
Tokenai
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
ury
Tokenury
Feature activation+0.000
's
Token's
Feature activation+0.000
syndrome
Token syndrome
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.484
j
Tokenj
Feature activation+0.000
ö
Tokenö
Feature activation+0.000
gren
Tokengren
Feature activation+0.000
's
Token's
Feature activation+0.000
(
Token (
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.538
wan
Tokenwan
Feature activation+0.000
sea
Tokensea
Feature activation+0.000
remain
Token remain
Feature activation+0.000
in
Token in
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000

INTERVAL 0.192 - 0.384
CONTAINS 0.001%

in
Token in
Feature activation+0.000
Halifax
Token Halifax
Feature activation+0.000
,
Token,
Feature activation+0.000
N
Token N
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.291
.
Token.
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
against
Token against
Feature activation+0.000
a
Token a
Feature activation+0.000
backdrop
Token backdrop
Feature activation+0.000
arisen
Token arisen
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
#
Token#
Feature activation+0.000
S
TokenS
Feature activation+0.301
od
Tokenod
Feature activation+0.000
Update
TokenUpdate
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
pitch
Token pitch
Feature activation+0.000
Stra
Token Stra
Feature activation+0.000
fe
Tokenfe
Feature activation+0.000
,
Token,
Feature activation+0.000
Seven
Token Seven
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.252
ided
Tokenided
Feature activation+0.000
Strike
Token Strike
Feature activation+0.000
,
Token,
Feature activation+0.000
Se
Token Se
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
Salem
Token Salem
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.207
ami
Tokenami
Feature activation+0.000
Ibrahim
Token Ibrahim
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
activist
Token activist
Feature activation+0.000
Your
Token Your
Feature activation+0.000
email
Token email
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.227
ev
Tokenev
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
chasing
Token chasing
Feature activation+0.000

INTERVAL 0.000 - 0.192
CONTAINS 99.990%

cell
Token cell
Feature activation+0.000
values
Token values
Feature activation+0.000
from
Token from
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
work
Token work
Feature activation+0.000
books
Tokenbooks
Feature activation+0.000
,
Token,
Feature activation+0.000
useful
Token useful
Feature activation+0.000
for
Token for
Feature activation+0.000
aud
Token aud
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
protecting
Token protecting
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
J
Token J
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
yll
Tokenyll
Feature activation+0.000
and
Token and
Feature activation+0.000
Hyde
Token Hyde
Feature activation+0.000
racing
Token racing
Feature activation+0.000
personality
Token personality
Feature activation+0.000
:
Token:
Feature activation+0.000
about
Token about
Feature activation+0.000
our
Token our
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
listen
Token listen
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
On
TokenOn
Feature activation+0.000
pe
Token pe
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
al
Token al
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
s
Token s
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
ger
Tokenger
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 H0.3: (feature 15977)

TOP ACTIVATIONS
MAX = 1.779

balanced
Token balanced
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+1.779
thing
Token thing
Feature activation+0.000
as
Token as
Feature activation+0.000
outside
Token outside
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
every
Token every
Feature activation+0.000
USB
Token USB
Feature activation+0.000
stick
Token stick
Feature activation+0.000
transform
Token transform
Feature activation+0.000
into
Token into
Feature activation+0.000
such
Token such
Feature activation+1.770
a
Token a
Feature activation+0.000
dual
Token dual
Feature activation+0.000
-
Token-
Feature activation+0.000
plug
Tokenplug
Feature activation+0.000
peripheral
Token peripheral
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
English
Token English
Feature activation+0.000
clothing
Token clothing
Feature activation+0.000
guides
Token guides
Feature activation+0.000
such
Token such
Feature activation+1.708
as
Token as
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
othes
Tokenothes
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
voters
Token voters
Feature activation+0.000
in
Token in
Feature activation+0.000
provinces
Token provinces
Feature activation+0.000
such
Token such
Feature activation+1.704
as
Token as
Feature activation+0.000
Ward
Token Ward
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
refusing
Token refusing
Feature activation+0.000
to
Token to
Feature activation+0.000
about
Token about
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
inquiries
Token inquiries
Feature activation+0.000
such
Token such
Feature activation+1.678
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
Do
TokenDo
Feature activation+0.000
you
Token you
Feature activation+0.000
beat
Token beat
Feature activation+0.000
steep
Token steep
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
in
Token in
Feature activation+0.000
social
Token social
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+1.657
as
Token as
Feature activation+0.000
housing
Token housing
Feature activation+0.000
,
Token,
Feature activation+0.000
job
Token job
Feature activation+0.000
training
Token training
Feature activation+0.000
135
Token 135
Feature activation+0.000
days
Token days
Feature activation+0.000
free
Token free
Feature activation+0.000
from
Token from
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
such
Token such
Feature activation+1.648
as
Token as
Feature activation+0.000
snatch
Token snatch
Feature activation+0.000
theft
Token theft
Feature activation+0.000
,
Token,
Feature activation+0.000
house
Token house
Feature activation+0.000
any
Token any
Feature activation+0.000
dist
Token dist
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
eful
Tokeneful
Feature activation+0.000
term
Token term
Feature activation+0.000
such
Token such
Feature activation+1.645
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
back
Tokenback
Feature activation+0.000
door
Tokendoor
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
mornings
Token mornings
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+1.636
famous
Token famous
Feature activation+0.000
races
Token races
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Windsor
Token Windsor
Feature activation+0.000
her
Token her
Feature activation+0.000
other
Token other
Feature activation+0.000
body
Token body
Feature activation+0.000
language
Token language
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.608
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
position
Token position
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
world
Token world
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
in
Token in
Feature activation+0.000
VR
Token VR
Feature activation+0.000
such
Token such
Feature activation+1.603
as
Token as
Feature activation+0.000
AMD
Token AMD
Feature activation+0.000
,
Token,
Feature activation+0.000
HTC
Token HTC
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
centrally
Token centrally
Feature activation+0.000
-
Token-
Feature activation+0.000
provided
Tokenprovided
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+1.600
as
Token as
Feature activation+0.000
accounting
Token accounting
Feature activation+0.000
and
Token and
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
.
Token.
Feature activation+0.000
without
Token without
Feature activation+0.000
the
Token the
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
oversee
Token oversee
Feature activation+0.000
such
Token such
Feature activation+1.578
complex
Token complex
Feature activation+0.000
programs
Token programs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Foot
Token Foot
Feature activation+0.000
.
Token.
Feature activation+0.000
Various
Token Various
Feature activation+0.000
cast
Token cast
Feature activation+0.000
members
Token members
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.561
as
Token as
Feature activation+0.000
Bob
Token Bob
Feature activation+0.000
O
Token O
Feature activation+0.000
den
Tokenden
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
Asked
TokenAsked
Feature activation+0.000
whether
Token whether
Feature activation+0.000
such
Token such
Feature activation+1.552
deliberate
Token deliberate
Feature activation+0.000
misinformation
Token misinformation
Feature activation+0.000
would
Token would
Feature activation+0.000
undermine
Token undermine
Feature activation+0.000
the
Token the
Feature activation+0.000
works
Token works
Feature activation+0.000
around
Token around
Feature activation+0.000
different
Token different
Feature activation+0.000
themes
Token themes
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.537
as
Token as
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Education
Token Education
Feature activation+0.000
,
Token,
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
newest
Token newest
Feature activation+0.000
teammates
Token teammates
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.527
as
Token as
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Jennings
Token Jennings
Feature activation+0.000
,
Token,
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
caught
Token caught
Feature activation+0.000
possessing
Token possessing
Feature activation+0.000
such
Token such
Feature activation+1.521
drug
Token drug
Feature activation+0.000
,
Token,
Feature activation+0.000
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
register
Token register
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+0.000
,
Token,
Feature activation+0.000
whenever
Token whenever
Feature activation+0.000
such
Token such
Feature activation+1.513
instruction
Token instruction
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
we
Token we
Feature activation+0.000
log
Token log
Feature activation+0.000
and
Token and
Feature activation+0.000
never
Token never
Feature activation+0.000
retain
Token retain
Feature activation+0.000
identifiable
Token identifiable
Feature activation+0.000
information
Token information
Feature activation+0.000
such
Token such
Feature activation+1.509
as
Token as
Feature activation+0.000
your
Token your
Feature activation+0.000
IP
Token IP
Feature activation+0.000
address
Token address
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 9.197

balanced
Token balanced
Feature activation+0.036
Top resid features:
and
Token and
Feature activation-0.055
Top resid features:
there
Token there
Feature activation+0.052
Top resid features:
is
Token is
Feature activation-0.073
Top resid features:
no
Token no
Feature activation+0.070
Top resid features:
such
Token such
Feature activation+8.958
Top resid features:
thing
Token thing
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
outside
Token outside
Feature activation+0.000
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.006
Top resid features:
USB
Token USB
Feature activation-0.009
Top resid features:
stick
Token stick
Feature activation+0.029
Top resid features:
transform
Token transform
Feature activation+0.189
Top resid features:
into
Token into
Feature activation+0.064
Top resid features:
such
Token such
Feature activation+9.140
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
dual
Token dual
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
plug
Tokenplug
Feature activation+0.000
Top resid features:
peripheral
Token peripheral
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
even
Token even
Feature activation+0.057
Top resid features:
English
Token English
Feature activation-0.001
Top resid features:
clothing
Token clothing
Feature activation-0.002
Top resid features:
guides
Token guides
Feature activation+0.065
Top resid features:
such
Token such
Feature activation+9.175
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Cl
Token Cl
Feature activation+0.000
Top resid features:
othes
Tokenothes
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
voters
Token voters
Feature activation-0.055
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
provinces
Token provinces
Feature activation-0.006
Top resid features:
such
Token such
Feature activation+8.999
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Ward
Token Ward
Feature activation+0.000
Top resid features:
ak
Tokenak
Feature activation+0.000
Top resid features:
refusing
Token refusing
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.047
Top resid features:
Islam
Token Islam
Feature activation-0.049
Top resid features:
that
Token that
Feature activation+0.052
Top resid features:
included
Token included
Feature activation+0.084
Top resid features:
inquiries
Token inquiries
Feature activation-0.006
Top resid features:
such
Token such
Feature activation+8.944
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Do
TokenDo
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
beat
Token beat
Feature activation+0.000
Top resid features:
steep
Token steep
Feature activation+0.092
Top resid features:
cuts
Token cuts
Feature activation+0.071
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
social
Token social
Feature activation+0.027
Top resid features:
services
Token services
Feature activation+0.125
Top resid features:
such
Token such
Feature activation+9.046
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
housing
Token housing
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
training
Token training
Feature activation+0.000
Top resid features:
135
Token 135
Feature activation+0.086
Top resid features:
days
Token days
Feature activation+0.053
Top resid features:
free
Token free
Feature activation-0.013
Top resid features:
from
Token from
Feature activation+0.110
Top resid features:
crimes
Token crimes
Feature activation+0.124
Top resid features:
such
Token such
Feature activation+9.128
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
snatch
Token snatch
Feature activation+0.000
Top resid features:
theft
Token theft
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.070
Top resid features:
dist
Token dist
Feature activation+0.020
Top resid features:
ast
Tokenast
Feature activation+0.028
Top resid features:
eful
Tokeneful
Feature activation+0.052
Top resid features:
term
Token term
Feature activation+0.059
Top resid features:
such
Token such
Feature activation+9.016
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ĺ
Tokenĺ
Feature activation+0.000
Top resid features:
back
Tokenback
Feature activation+0.000
Top resid features:
door
Tokendoor
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation+0.028
Top resid features:
mornings
Token mornings
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
get
Token get
Feature activation+0.069
Top resid features:
to
Token to
Feature activation-0.027
Top resid features:
such
Token such
Feature activation+9.104
Top resid features:
famous
Token famous
Feature activation+0.000
Top resid features:
races
Token races
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Windsor
Token Windsor
Feature activation+0.000
Top resid features:
her
Token her
Feature activation-0.012
Top resid features:
other
Token other
Feature activation-0.025
Top resid features:
body
Token body
Feature activation+0.019
Top resid features:
language
Token language
Feature activation-0.024
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
such
Token such
Feature activation+9.172
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
position
Token position
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
world
Token world
Feature activation-0.014
Top resid features:
leaders
Token leaders
Feature activation-0.015
Top resid features:
in
Token in
Feature activation+0.068
Top resid features:
VR
Token VR
Feature activation-0.065
Top resid features:
such
Token such
Feature activation+9.197
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
AMD
Token AMD
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
HTC
Token HTC
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.006
Top resid features:
centrally
Token centrally
Feature activation+0.064
Top resid features:
-
Token-
Feature activation-0.047
Top resid features:
provided
Tokenprovided
Feature activation+0.054
Top resid features:
services
Token services
Feature activation+0.110
Top resid features:
such
Token such
Feature activation+8.968
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
accounting
Token accounting
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
marketing
Token marketing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
without
Token without
Feature activation+0.086
Top resid features:
the
Token the
Feature activation-0.026
Top resid features:
staff
Token staff
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
oversee
Token oversee
Feature activation+0.009
Top resid features:
such
Token such
Feature activation+9.088
Top resid features:
complex
Token complex
Feature activation+0.000
Top resid features:
programs
Token programs
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Foot
Token Foot
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Various
Token Various
Feature activation-0.028
Top resid features:
cast
Token cast
Feature activation-0.011
Top resid features:
members
Token members
Feature activation-0.050
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
such
Token such
Feature activation+9.014
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Bob
Token Bob
Feature activation+0.000
Top resid features:
O
Token O
Feature activation+0.000
Top resid features:
den
Tokenden
Feature activation+0.000
Top resid features:
k
Tokenk
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Asked
TokenAsked
Feature activation-0.004
Top resid features:
whether
Token whether
Feature activation+0.349
Top resid features:
such
Token such
Feature activation+8.697
Top resid features:
deliberate
Token deliberate
Feature activation+0.000
Top resid features:
misinformation
Token misinformation
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
undermine
Token undermine
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
works
Token works
Feature activation+0.033
Top resid features:
around
Token around
Feature activation+0.101
Top resid features:
different
Token different
Feature activation+0.053
Top resid features:
themes
Token themes
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.084
Top resid features:
such
Token such
Feature activation+9.118
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Open
Token Open
Feature activation+0.000
Top resid features:
Education
Token Education
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Open
Token Open
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.011
Top resid features:
s
Tokens
Feature activation-0.035
Top resid features:
newest
Token newest
Feature activation+0.055
Top resid features:
teammates
Token teammates
Feature activation-0.132
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
such
Token such
Feature activation+8.838
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
receiver
Token receiver
Feature activation+0.000
Top resid features:
Greg
Token Greg
Feature activation+0.000
Top resid features:
Jennings
Token Jennings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
If
Token If
Feature activation+0.027
Top resid features:
you
Token you
Feature activation-0.024
Top resid features:
are
Token are
Feature activation-0.021
Top resid features:
caught
Token caught
Feature activation+0.085
Top resid features:
possessing
Token possessing
Feature activation+0.098
Top resid features:
such
Token such
Feature activation+8.935
Top resid features:
drug
Token drug
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
depending
Token depending
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
register
Token register
Feature activation+0.051
Top resid features:
is
Token is
Feature activation-0.081
Top resid features:
used
Token used
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
whenever
Token whenever
Feature activation+0.160
Top resid features:
such
Token such
Feature activation+8.937
Top resid features:
instruction
Token instruction
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
log
Token log
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.092
Top resid features:
never
Token never
Feature activation-0.015
Top resid features:
retain
Token retain
Feature activation+0.041
Top resid features:
identifiable
Token identifiable
Feature activation+0.041
Top resid features:
information
Token information
Feature activation+0.125
Top resid features:
such
Token such
Feature activation+8.905
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
IP
Token IP
Feature activation+0.000
Top resid features:
address
Token address
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.22

Head 2: 0.02

Head 3: 0.24

Head 4: 0.06

Head 5: 0.11

Head 6: 0.03

Head 7: 0.05

Head 8: 0.03

Head 9: 0.10

Head 10: 0.06

Head 11: 0.06

Positive logits

etheless4.09

NetMessage3.70

merce3.53

��3.37

unnecess3.31

raviolet3.25

worldly2.95

nces2.93

gobl2.92

azeera2.89

localized2.87

reconc2.82

quartered2.81

severe2.76

arrang2.75

showc2.65

odic2.65

profits2.64

misunder2.62

zbollah2.61

Negative logits

Ridge-2.81

Champ-2.77

Pier-2.70

Harbor-2.65

Rou-2.59

Bohem-2.55

Daytona-2.51

Ship-2.46

halla-2.44

Sicily-2.40

Cambodia-2.39

Bung-2.38

Drum-2.38

Lake-2.34

Beach-2.34

Bend-2.31

River-2.30

Que-2.28

Lago-2.28

Bunny-2.28

INTERVAL 1.601 - 1.779
CONTAINS 0.001%

135
Token 135
Feature activation+0.000
days
Token days
Feature activation+0.000
free
Token free
Feature activation+0.000
from
Token from
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
such
Token such
Feature activation+1.648
as
Token as
Feature activation+0.000
snatch
Token snatch
Feature activation+0.000
theft
Token theft
Feature activation+0.000
,
Token,
Feature activation+0.000
house
Token house
Feature activation+0.000
about
Token about
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
inquiries
Token inquiries
Feature activation+0.000
such
Token such
Feature activation+1.678
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
Do
TokenDo
Feature activation+0.000
you
Token you
Feature activation+0.000
beat
Token beat
Feature activation+0.000
any
Token any
Feature activation+0.000
dist
Token dist
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
eful
Tokeneful
Feature activation+0.000
term
Token term
Feature activation+0.000
such
Token such
Feature activation+1.645
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
back
Tokenback
Feature activation+0.000
door
Tokendoor
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
English
Token English
Feature activation+0.000
clothing
Token clothing
Feature activation+0.000
guides
Token guides
Feature activation+0.000
such
Token such
Feature activation+1.708
as
Token as
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
othes
Tokenothes
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
steep
Token steep
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
in
Token in
Feature activation+0.000
social
Token social
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+1.657
as
Token as
Feature activation+0.000
housing
Token housing
Feature activation+0.000
,
Token,
Feature activation+0.000
job
Token job
Feature activation+0.000
training
Token training
Feature activation+0.000

INTERVAL 1.423 - 1.601
CONTAINS 0.001%

rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+0.000
EU
Token EU
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
as
Token as
Feature activation+0.000
such
Token such
Feature activation+1.471
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
there
Tokenthere
Feature activation+0.000
are
Token are
Feature activation+0.000
to
Token to
Feature activation+0.000
story
Token story
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
bolster
Token bolster
Feature activation+0.000
such
Token such
Feature activation+1.467
content
Token content
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
,
Token,
Feature activation+0.000
Farmer
Token Farmer
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
caught
Token caught
Feature activation+0.000
possessing
Token possessing
Feature activation+0.000
such
Token such
Feature activation+1.521
drug
Token drug
Feature activation+0.000
,
Token,
Feature activation+0.000
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Asked
TokenAsked
Feature activation+0.000
whether
Token whether
Feature activation+0.000
such
Token such
Feature activation+1.552
deliberate
Token deliberate
Feature activation+0.000
misinformation
Token misinformation
Feature activation+0.000
would
Token would
Feature activation+0.000
undermine
Token undermine
Feature activation+0.000
the
Token the
Feature activation+0.000
works
Token works
Feature activation+0.000
around
Token around
Feature activation+0.000
different
Token different
Feature activation+0.000
themes
Token themes
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.537
as
Token as
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Education
Token Education
Feature activation+0.000
,
Token,
Feature activation+0.000
Open
Token Open
Feature activation+0.000

INTERVAL 1.246 - 1.423
CONTAINS 0.001%

is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
capable
Token capable
Feature activation+0.000
of
Token of
Feature activation+0.000
producing
Token producing
Feature activation+0.000
such
Token such
Feature activation+1.407
frequencies
Token frequencies
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
firms
Token firms
Feature activation+0.000
to
Token to
Feature activation+0.000
retain
Token retain
Feature activation+0.000
such
Token such
Feature activation+1.301
privileges
Token privileges
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
pass
Tokenpass
Feature activation+0.000
silently
Token silently
Feature activation+0.000
perform
Token perform
Feature activation+0.000
unnecessary
Token unnecessary
Feature activation+0.000
actions
Token actions
Feature activation+0.000
(
Token (
Feature activation+0.000
such
Tokensuch
Feature activation+1.291
as
Token as
Feature activation+0.000
connections
Token connections
Feature activation+0.000
to
Token to
Feature activation+0.000
unknown
Token unknown
Feature activation+0.000
servers
Token servers
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
small
Token small
Feature activation+0.000
disturbances
Token disturbances
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.310
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
painting
Token painting
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
concentrated
Token concentrated
Feature activation+0.000
in
Token in
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
areas
Token areas
Feature activation+0.000
(
Token (
Feature activation+0.000
such
Tokensuch
Feature activation+1.350
as
Token as
Feature activation+0.000
Burke
Token Burke
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000

INTERVAL 1.068 - 1.246
CONTAINS 0.001%

in
Token in
Feature activation+0.000
Far
Token Far
Feature activation+0.000
-
Token-
Feature activation+0.000
Eastern
TokenEastern
Feature activation+0.000
markets
Token markets
Feature activation+0.000
such
Token such
Feature activation+1.218
as
Token as
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
.[
Token.[
Feature activation+0.000
2
Token2
Feature activation+0.000
]
Token]
Feature activation+0.000
berries
Token berries
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
recalled
Token recalled
Feature activation+0.000
until
Token until
Feature activation+0.000
such
Token such
Feature activation+1.175
time
Token time
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
receive
Token receive
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
energy
Token energy
Feature activation+0.000
that
Token that
Feature activation+0.000
such
Token such
Feature activation+1.165
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
could
Token could
Feature activation+0.000
imb
Token imb
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000
that
Token that
Feature activation+0.000
such
Token such
Feature activation+1.149
an
Token an
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
would
Token would
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
during
Token during
Feature activation+0.000
rec
Token rec
Feature activation+0.000
essions
Tokenessions
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
things
Token things
Feature activation+0.000
such
Token such
Feature activation+1.104
as
Token as
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000

INTERVAL 0.890 - 1.068
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
such
Token such
Feature activation+0.961
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
this
Token this
Feature activation+0.000
letter
Token letter
Feature activation+0.000
,
Token,
Feature activation+0.000
include
Token include
Feature activation+0.000
government
Token government
Feature activation+0.000
offices
Token offices
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
such
Token such
Feature activation+1.027
as
Token as
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.000
DC
Token DC
Feature activation+0.000
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
software
Token software
Feature activation+0.000
licenses
Token licenses
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
such
Token such
Feature activation+1.049
example
Token example
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
Open
Token Open
Feature activation+0.000
am
Token am
Feature activation+0.000
now
Token now
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
70
Token 70
Feature activation+0.000
such
Token such
Feature activation+0.927
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
listed
Token listed
Feature activation+0.000
free
Token free
Feature activation+0.000
sale
Token sale
Feature activation+0.000
of
Token of
Feature activation+0.000
acid
Token acid
Feature activation+0.000
but
Token but
Feature activation+0.000
such
Token such
Feature activation+0.961
attacks
Token attacks
Feature activation+0.000
continue
Token continue
Feature activation+0.000
unab
Token unab
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.712 - 0.890
CONTAINS 0.001%

me
Token me
Feature activation+0.000
very
Token very
Feature activation+0.000
happy
Token happy
Feature activation+0.000
:
Token :
Feature activation+0.000
D
TokenD
Feature activation+0.000
Such
Token Such
Feature activation+0.749
small
Token small
Feature activation+0.000
bird
Token bird
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
such
Token such
Feature activation+0.759
a
Token a
Feature activation+0.000
program
Token program
Feature activation+0.000
,
Token,
Feature activation+0.000
any
Token any
Feature activation+0.000
materials
Token materials
Feature activation+0.000
basis
Token basis
Feature activation+0.000
of
Token of
Feature activation+0.000
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
such
Token such
Feature activation+0.728
facilities
Token facilities
Feature activation+0.000
provided
Token provided
Feature activation+0.000
for
Token for
Feature activation+0.000
students
Token students
Feature activation+0.000
of
Token of
Feature activation+0.000
(
Token (
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
covers
Token covers
Feature activation+0.000
testing
Token testing
Feature activation+0.000
sites
Token sites
Feature activation+0.000
such
Token such
Feature activation+0.834
as
Token as
Feature activation+0.000
Fort
Token Fort
Feature activation+0.000
Det
Token Det
Feature activation+0.000
rick
Tokenrick
Feature activation+0.000
,
Token,
Feature activation+0.000
report
Token report
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Such
TokenSuch
Feature activation+0.866
wide
Token wide
Feature activation+0.000
variations
Token variations
Feature activation+0.000
in
Token in
Feature activation+0.000
prescriptions
Token prescriptions
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.534 - 0.712
CONTAINS 0.001%

ism
Tokenism
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
could
Token could
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
such
Token such
Feature activation+0.547
a
Token a
Feature activation+0.000
debate
Token debate
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
at
Token at
Feature activation+0.000
medication
Token medication
Feature activation+0.000
or
Token or
Feature activation+0.000
lifestyle
Token lifestyle
Feature activation+0.000
changes
Token changes
Feature activation+0.000
such
Token such
Feature activation+0.550
as
Token as
Feature activation+0.000
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
physical
Token physical
Feature activation+0.000
activity
Token activity
Feature activation+0.000
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000
elector
Token elector
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.576
as
Token as
Feature activation+0.000
W
Token W
Feature activation+0.000
ills
Tokenills
Feature activation+0.000
in
Token in
Feature activation+0.000
Victoria
Token Victoria
Feature activation+0.000
8
Token8
Feature activation+0.000
76
Token76
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.646
as
Token as
Feature activation+0.000
theatre
Token theatre
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
7
Token 7
Feature activation+0.000
£
Token £
Feature activation+0.000
higher
Token higher
Feature activation+0.000
staff
Token staff
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
following
Token following
Feature activation+0.000
scandals
Token scandals
Feature activation+0.000
such
Token such
Feature activation+0.663
as
Token as
Feature activation+0.000
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.356 - 0.534
CONTAINS 0.001%

to
Token to
Feature activation+0.000
offic
Token offic
Feature activation+0.000
iate
Tokeniate
Feature activation+0.000
marriages
Token marriages
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.424
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
minister
Token minister
Feature activation+0.000
,
Token,
Feature activation+0.000
priest
Token priest
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
W
Token W
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
More
Token More
Feature activation+0.000
Such
Token Such
Feature activation+0.425
Movies
Token Movies
Feature activation+0.000
in
Token in
Feature activation+0.000
China
Token China
Feature activation+0.000
By
Token By
Feature activation+0.000
F
Token F
Feature activation+0.000
di
Token di
Feature activation+0.000
as
Tokenas
Feature activation+0.000
pora
Tokenpora
Feature activation+0.000
in
Token in
Feature activation+0.000
countries
Token countries
Feature activation+0.000
such
Token such
Feature activation+0.452
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
Kingdom
Token Kingdom
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
band
Tokenband
Feature activation+0.000
.
Token.
Feature activation+0.000
Details
Token Details
Feature activation+0.000
such
Token such
Feature activation+0.497
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
trim
Token trim
Feature activation+0.000
ring
Token ring
Feature activation+0.000
around
Token around
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
such
Token such
Feature activation+0.415
a
Token a
Feature activation+0.000
devastating
Token devastating
Feature activation+0.000
unit
Token unit
Feature activation+0.000
it
Token it
Feature activation+0.000
feels
Token feels
Feature activation+0.000

INTERVAL 0.178 - 0.356
CONTAINS 0.002%

that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
such
Token such
Feature activation+0.239
as
Token as
Feature activation+0.000
ME
Token ME
Feature activation+0.000
,
Token,
Feature activation+0.000
fib
Token fib
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
assign
Token assign
Feature activation+0.000
ee
Tokenee
Feature activation+0.000
and
Token and
Feature activation+0.000
take
Token take
Feature activation+0.000
actions
Token actions
Feature activation+0.000
such
Token such
Feature activation+0.311
as
Token as
Feature activation+0.000
restart
Token restart
Feature activation+0.000
ing
Tokening
Feature activation+0.000
a
Token a
Feature activation+0.000
match
Token match
Feature activation+0.000
stable
Token stable
Feature activation+0.000
and
Token and
Feature activation+0.000
readily
Token readily
Feature activation+0.000
preserved
Token preserved
Feature activation+0.000
proteins
Token proteins
Feature activation+0.000
such
Token such
Feature activation+0.242
as
Token as
Feature activation+0.000
act
Token act
Feature activation+0.000
in
Tokenin
Feature activation+0.000
and
Token and
Feature activation+0.000
tub
Token tub
Feature activation+0.000
includes
Token includes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
such
Token such
Feature activation+0.438
colleges
Token colleges
Feature activation+0.000
such
Token such
Feature activation+0.309
as
Token as
Feature activation+0.000
U
Token U
Feature activation+0.000
H
TokenH
Feature activation+0.000
West
Token West
Feature activation+0.000
O
Token O
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
such
Token such
Feature activation+0.248
lawmakers
Token lawmakers
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
they
Token they
Feature activation+0.000
see
Token see
Feature activation+0.000

INTERVAL 0.000 - 0.178
CONTAINS 99.991%

coll
Token coll
Feature activation+0.000
oqu
Tokenoqu
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
academy
Token academy
Feature activation+0.000
's
Token's
Feature activation+0.000
Mad
Token Mad
Feature activation+0.000
k
Tokenk
Feature activation+0.000
our
Tokenour
Feature activation+0.000
of
Token of
Feature activation+0.000
bre
Token bre
Feature activation+0.000
vity
Tokenvity
Feature activation+0.000
and
Token and
Feature activation+0.000
clarity
Token clarity
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
my
Token my
Feature activation+0.000
intent
Token intent
Feature activation+0.000
waterproof
Token waterproof
Feature activation+0.000
u
Token u
Feature activation+0.000
reth
Tokenreth
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
coating
Token coating
Feature activation+0.000
helping
Token helping
Feature activation+0.000
keep
Token keep
Feature activation+0.000
moisture
Token moisture
Feature activation+0.000
away
Token away
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
/
Token/
Feature activation+0.000
authors
Tokenauthors
Feature activation+0.000
/
Token/
Feature activation+0.000
tone
Tokentone
Feature activation+0.000
-
Token-
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ays
Tokenays
Feature activation+0.000
/)
Token/)
Feature activation+0.000
after
Token after
Feature activation+0.000
previously
Token previously
Feature activation+0.000
writing
Token writing
Feature activation+0.000
marry
Token marry
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
V
TokenV
Feature activation+0.000
ars
Tokenars
Feature activation+0.000
ha
Tokenha
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
lives
Token lives
Feature activation+0.000
with
Token with
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 H0.3: (feature 15805)

TOP ACTIVATIONS
MAX = 2.169

legal
Token legal
Feature activation+0.000
gag
Token gag
Feature activation+0.000
order
Token order
Feature activation+0.000
he
Token he
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
imag
Token imag
Feature activation+2.169
ines
Tokenines
Feature activation+1.362
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
de
Token de
Feature activation+0.000
promo
Token promo
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ão
Tokenão
Feature activation+0.000
da
Token da
Feature activation+0.000
imag
Token imag
Feature activation+1.812
em
Tokenem
Feature activation+0.000
de
Token de
Feature activation+0.000
in
Token in
Feature activation+0.000
ova
Tokenova
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
officially
Token officially
Feature activation+0.000
released
Token released
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
Cer
Token Cer
Feature activation+0.000
imag
Tokenimag
Feature activation+1.709
ics
Tokenics
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
the
Token the
Feature activation+0.000
6
Token 6
Feature activation+0.000
200
Token200
Feature activation+0.000
mont
Tokenmont
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
earth
Token earth
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.642
ery
Tokenery
Feature activation+0.022
company
Token company
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
its
Token its
Feature activation+0.000
First
Token First
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
context
Token context
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.567
ining
Tokenining
Feature activation+0.818
Vice
Token Vice
Feature activation+0.000
City
Token City
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
gag
Token gag
Feature activation+0.000
order
Token order
Feature activation+0.000
he
Token he
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
imag
Token imag
Feature activation+2.169
ines
Tokenines
Feature activation+1.362
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
that
Token that
Feature activation+0.000
context
Token context
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.567
ining
Tokenining
Feature activation+0.818
Vice
Token Vice
Feature activation+0.000
City
Token City
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
very
Token very
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
of
Token of
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
imaginary
Token imaginary
Feature activation+0.395
kissing
Token kissing
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
kissing
Token kissing
Feature activation+0.000
-
Token-
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
earth
Token earth
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.642
ery
Tokenery
Feature activation+0.022
company
Token company
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
its
Token its
Feature activation+0.000
First
Token First
Feature activation+0.000
Look
TokenLook
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
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
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
<|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
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

Top DFA by src position
MAX = 4.714

legal
Token legal
Feature activation-0.005
Top resid features:
gag
Token gag
Feature activation-0.011
Top resid features:
order
Token order
Feature activation+0.027
Top resid features:
he
Token he
Feature activation-0.040
Top resid features:
apparently
Token apparently
Feature activation-0.022
Top resid features:
imag
Token imag
Feature activation+4.714
Top resid features:
ines
Tokenines
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
de
Token de
Feature activation-0.004
Top resid features:
promo
Token promo
Feature activation+0.046
Top resid features:
ç
Tokenç
Feature activation-0.016
Top resid features:
ão
Tokenão
Feature activation-0.011
Top resid features:
da
Token da
Feature activation-0.013
Top resid features:
imag
Token imag
Feature activation+4.349
Top resid features:
em
Tokenem
Feature activation+0.000
Top resid features:
de
Token de
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
ova
Tokenova
Feature activation+0.000
Top resid features:
ç
Tokenç
Feature activation+0.000
Top resid features:
officially
Token officially
Feature activation-0.025
Top resid features:
released
Token released
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
both
Token both
Feature activation-0.012
Top resid features:
Cer
Token Cer
Feature activation+0.027
Top resid features:
imag
Tokenimag
Feature activation+4.228
Top resid features:
ics
Tokenics
Feature activation+0.000
Top resid features:
claimed
Token claimed
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
6
Token 6
Feature activation+0.000
Top resid features:
200
Token200
Feature activation+0.000
Top resid features:
mont
Tokenmont
Feature activation+0.011
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
based
Tokenbased
Feature activation+0.000
Top resid features:
earth
Token earth
Feature activation-0.034
Top resid features:
-
Token-
Feature activation+0.015
Top resid features:
imag
Tokenimag
Feature activation+4.239
Top resid features:
ery
Tokenery
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
deployed
Token deployed
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
First
Token First
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.028
Top resid features:
that
Token that
Feature activation-0.022
Top resid features:
context
Token context
Feature activation+0.011
Top resid features:
re
Token re
Feature activation+0.075
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
imag
Tokenimag
Feature activation+4.044
Top resid features:
ining
Tokenining
Feature activation+0.000
Top resid features:
Vice
Token Vice
Feature activation+0.000
Top resid features:
City
Token City
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
legal
Token legal
Feature activation-0.016
Top resid features:
gag
Token gag
Feature activation+0.014
Top resid features:
order
Token order
Feature activation+0.009
Top resid features:
he
Token he
Feature activation-0.029
Top resid features:
apparently
Token apparently
Feature activation-0.007
Top resid features:
imag
Token imag
Feature activation+3.593
Top resid features:
ines
Tokenines
Feature activation+0.398
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.032
Top resid features:
that
Token that
Feature activation-0.026
Top resid features:
context
Token context
Feature activation-0.010
Top resid features:
re
Token re
Feature activation+0.017
Top resid features:
-
Token-
Feature activation+0.012
Top resid features:
imag
Tokenimag
Feature activation+3.039
Top resid features:
ining
Tokenining
Feature activation+0.401
Top resid features:
Vice
Token Vice
Feature activation+0.000
Top resid features:
City
Token City
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
pictures
Token pictures
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
each
Token each
Feature activation-0.006
Top resid features:
other
Token other
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
imaginary
Token imaginary
Feature activation+2.908
Top resid features:
kissing
Token kissing
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
kissing
Token kissing
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
mont
Tokenmont
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
based
Tokenbased
Feature activation-0.003
Top resid features:
earth
Token earth
Feature activation-0.018
Top resid features:
-
Token-
Feature activation+0.021
Top resid features:
imag
Tokenimag
Feature activation+2.021
Top resid features:
ery
Tokenery
Feature activation+0.528
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
deployed
Token deployed
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
First
Token First
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation-0.109
Top resid features:
committee
Token committee
Feature activation-0.066
Top resid features:
headed
Token headed
Feature activation-0.077
Top resid features:
by
Token by
Feature activation+0.059
Top resid features:
V
Token V
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.647
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.137
Top resid features:
rik
Tokenrik
Feature activation+0.012
Top resid features:
ar
Tokenar
Feature activation-0.005
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
Saturday
Token Saturday
Feature activation-0.078
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
defence
Token defence
Feature activation-0.070
Top resid features:
ministry
Token ministry
Feature activation-0.174
Top resid features:
committee
Token committee
Feature activation-0.044
Top resid features:
headed
Token headed
Feature activation+0.004
Top resid features:
by
Token by
Feature activation+0.027
Top resid features:
V
Token V
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.003
Top resid features:
Saturday
Token Saturday
Feature activation-0.065
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
defence
Token defence
Feature activation-0.023
Top resid features:
ministry
Token ministry
Feature activation-0.271
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.014
Top resid features:
Saturday
Token Saturday
Feature activation-0.077
Top resid features:
.
Token.
Feature activation+0.129
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
Ċ
TokenĊ
Feature activation+0.152
Top resid features:
The
TokenThe
Feature activation+0.901
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation-0.008
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
Saturday
Token Saturday
Feature activation-0.043
Top resid features:
.
Token.
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
defence
Token defence
Feature activation-0.040
Top resid features:
ministry
Token ministry
Feature activation-0.060
Top resid features:
committee
Token committee
Feature activation-0.411
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.021
Top resid features:
defence
Token defence
Feature activation-0.064
Top resid features:
ministry
Token ministry
Feature activation-0.118
Top resid features:
committee
Token committee
Feature activation-0.084
Top resid features:
headed
Token headed
Feature activation+0.075
Top resid features:
by
Token by
Feature activation+0.550
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation-0.039
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.048
Top resid features:
The
TokenThe
Feature activation-0.008
Top resid features:
defence
Token defence
Feature activation+0.513
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation-0.012
Top resid features:
said
Token said
Feature activation+0.066
Top resid features:
Saturday
Token Saturday
Feature activation-0.068
Top resid features:
.
Token.
Feature activation+0.121
Top resid features:
Ċ
TokenĊ
Feature activation+0.504
Top resid features:
Ċ
TokenĊ
Feature activation+0.637
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.251
Top resid features:
rik
Tokenrik
Feature activation+0.036
Top resid features:
ar
Tokenar
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.249
Top resid features:
Saturday
Token Saturday
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.754
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation+0.039
Top resid features:
ar
Tokenar
Feature activation-0.009
Top resid features:
said
Token said
Feature activation+0.088
Top resid features:
Saturday
Token Saturday
Feature activation-0.054
Top resid features:
.
Token.
Feature activation+0.220
Top resid features:
Ċ
TokenĊ
Feature activation+0.812
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.13

Head 2: 0.03

Head 3: 0.23

Head 4: 0.21

Head 5: 0.11

Head 6: 0.04

Head 7: 0.06

Head 8: 0.04

Head 9: 0.05

Head 10: 0.06

Head 11: 0.02

Positive logits

"$:/4.83

エル4.69

ゼウス4.38

intrins4.01

-+-+4.00

ーテ3.95

TextColor3.89

imag3.82

~~~~3.77

////////3.71

jah3.71

3.68

////3.56

RON3.56

aroo3.55

ウス3.55

WithNo3.53

IELD3.50

裏�3.49

Interpret3.47

Negative logits

Downloadha-4.38

uberty-4.37

vous-4.07

xual-3.68

paying-3.65

iferation-3.58

driving-3.58

avis-3.46

uters-3.43

graduate-3.40

feeding-3.38

ateral-3.34

surgical-3.29

driver-3.24

hormonal-3.24

chemotherapy-3.22

pediatric-3.21

king-3.20

pleting-3.20

physicians-3.19

INTERVAL 1.952 - 2.169
CONTAINS 0.000%

legal
Token legal
Feature activation+0.000
gag
Token gag
Feature activation+0.000
order
Token order
Feature activation+0.000
he
Token he
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
imag
Token imag
Feature activation+2.169
ines
Tokenines
Feature activation+1.362
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.735 - 1.952
CONTAINS 0.000%

de
Token de
Feature activation+0.000
promo
Token promo
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ão
Tokenão
Feature activation+0.000
da
Token da
Feature activation+0.000
imag
Token imag
Feature activation+1.812
em
Tokenem
Feature activation+0.000
de
Token de
Feature activation+0.000
in
Token in
Feature activation+0.000
ova
Tokenova
Feature activation+0.000
ç
Tokenç
Feature activation+0.000

INTERVAL 1.518 - 1.735
CONTAINS 0.000%

in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
context
Token context
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.567
ining
Tokenining
Feature activation+0.818
Vice
Token Vice
Feature activation+0.000
City
Token City
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
mont
Tokenmont
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
earth
Token earth
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.642
ery
Tokenery
Feature activation+0.022
company
Token company
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
its
Token its
Feature activation+0.000
First
Token First
Feature activation+0.000
officially
Token officially
Feature activation+0.000
released
Token released
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
Cer
Token Cer
Feature activation+0.000
imag
Tokenimag
Feature activation+1.709
ics
Tokenics
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
the
Token the
Feature activation+0.000
6
Token 6
Feature activation+0.000
200
Token200
Feature activation+0.000

INTERVAL 1.301 - 1.518
CONTAINS 0.000%

gag
Token gag
Feature activation+0.000
order
Token order
Feature activation+0.000
he
Token he
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
imag
Token imag
Feature activation+2.169
ines
Tokenines
Feature activation+1.362
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.084 - 1.301
CONTAINS 0.000%

INTERVAL 0.867 - 1.084
CONTAINS 0.000%

INTERVAL 0.651 - 0.867
CONTAINS 0.000%

that
Token that
Feature activation+0.000
context
Token context
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
imag
Tokenimag
Feature activation+1.567
ining
Tokenining
Feature activation+0.818
Vice
Token Vice
Feature activation+0.000
City
Token City
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
very
Token very
Feature activation+0.000

INTERVAL 0.434 - 0.651
CONTAINS 0.000%

INTERVAL 0.217 - 0.434
CONTAINS 0.000%

pictures
Token pictures
Feature activation+0.000
of
Token of
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
imaginary
Token imaginary
Feature activation+0.395
kissing
Token kissing
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
kissing
Token kissing
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.000 - 0.217
CONTAINS 99.999%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
excited
Token excited
Feature activation+0.000
The
Token The
Feature activation+0.000
Late
Token Late
Feature activation+0.000
Show
Token Show
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
Colbert
Token Colbert
Feature activation+0.000
.
Token.
Feature activation+0.000
also
Token also
Feature activation+0.000
scored
Token scored
Feature activation+0.000
in
Token in
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Panthers
Token Panthers
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
kitchen
Token kitchen
Feature activation+0.000
sink
Token sink
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
ATA
TokenATA
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
Autom
Token Autom
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
Public
Token Public
Feature activation+0.000
Turing
Token Turing
Feature activation+0.000
test
Token test
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
Comput
Token Comput
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
and
Token and
Feature activation+0.000
pumping
Token pumping
Feature activation+0.000
up
Token up
Feature activation+0.000
our
Token our
Feature activation+0.000
guys
Token guys
Feature activation+0.000
or
Token or
Feature activation+0.000
ch
Token ch
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
ping
Tokenping
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
team
Token team
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