H6.3 top features

Top feature 0 in H6.3: (feature 22083)

TOP ACTIVATIONS
MAX = 4.807

to
Token to
Feature activation+0.000
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+4.807
will
Token will
Feature activation+3.436
have
Token have
Feature activation+3.042
to
Token to
Feature activation+2.298
give
Token give
Feature activation+0.924
up
Token up
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
corporate
Token corporate
Feature activation+0.000
taxes
Token taxes
Feature activation+0.542
,
Token,
Feature activation+4.416
that
Token that
Feature activation+3.028
's
Token's
Feature activation+3.826
fine
Token fine
Feature activation+2.449
,
Token,
Feature activation+0.033
reduce
Token reduce
Feature activation+0.178
to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+2.357
they
Token they
Feature activation+3.906
'd
Token'd
Feature activation+3.962
settle
Token settle
Feature activation+0.897
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.636
married
Token married
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+2.357
they
Token they
Feature activation+3.906
'd
Token'd
Feature activation+3.962
settle
Token settle
Feature activation+0.897
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.636
this
Token this
Feature activation+0.060
kind
Token kind
Feature activation+0.262
of
Token of
Feature activation+0.060
inequality
Token inequality
Feature activation+0.315
off
Token off
Feature activation+0.008
,
Token,
Feature activation+3.879
you
Token you
Feature activation+2.538
would
Token would
Feature activation+2.705
also
Token also
Feature activation+0.835
have
Token have
Feature activation+1.401
to
Token to
Feature activation+0.589
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
information
Token information
Feature activation+0.000
you
Token you
Feature activation+3.829
always
Token always
Feature activation+3.470
had
Token had
Feature activation+2.110
to
Token to
Feature activation+1.541
go
Token go
Feature activation+0.759
through
Token through
Feature activation+0.804
reduce
Token reduce
Feature activation+0.000
corporate
Token corporate
Feature activation+0.000
taxes
Token taxes
Feature activation+0.542
,
Token,
Feature activation+4.416
that
Token that
Feature activation+3.028
's
Token's
Feature activation+3.826
fine
Token fine
Feature activation+2.449
,
Token,
Feature activation+0.033
reduce
Token reduce
Feature activation+0.178
them
Token them
Feature activation+0.790
,"
Token,"
Feature activation+0.000
learn
Token learn
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.559
,
Token,
Feature activation+3.121
this
Token this
Feature activation+2.905
is
Token is
Feature activation+3.713
the
Token the
Feature activation+3.820
place
Token place
Feature activation+1.538
to
Token to
Feature activation+1.506
do
Token do
Feature activation+1.086
it
Token it
Feature activation+1.052
.
Token.
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
environment
Token environment
Feature activation+0.101
,
Token,
Feature activation+3.771
you
Token you
Feature activation+2.914
have
Token have
Feature activation+2.307
to
Token to
Feature activation+0.888
play
Token play
Feature activation+0.370
by
Token by
Feature activation+0.000
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.559
,
Token,
Feature activation+3.121
this
Token this
Feature activation+2.905
is
Token is
Feature activation+3.713
the
Token the
Feature activation+3.820
place
Token place
Feature activation+1.538
to
Token to
Feature activation+1.506
do
Token do
Feature activation+1.086
it
Token it
Feature activation+1.052
cards
Token cards
Feature activation+0.006
detailing
Token detailing
Feature activation+0.000
the
Token the
Feature activation+0.000
hide
Token hide
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+3.649
head
Token head
Feature activation+1.344
over
Token over
Feature activation+0.467
to
Token to
Feature activation+1.390
Mov
Token Mov
Feature activation+0.000
oto
Tokenoto
Feature activation+0.000
take
Token take
Feature activation+0.000
some
Token some
Feature activation+0.032
action
Token action
Feature activation+0.517
on
Token on
Feature activation+0.166
healthcare
Token healthcare
Feature activation+0.000
,
Token,
Feature activation+3.614
call
Token call
Feature activation+0.426
your
Token your
Feature activation+0.000
congress
Token congress
Feature activation+0.000
person
Tokenperson
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
movements
Token movements
Feature activation+0.000
of
Token of
Feature activation+0.000
ether
Token ether
Feature activation+0.000
,
Token,
Feature activation+3.590
they
Token they
Feature activation+2.223
simply
Token simply
Feature activation+1.567
call
Token call
Feature activation+0.695
their
Token their
Feature activation+0.000
broker
Token broker
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+3.474
we
Token we
Feature activation+2.405
'll
Token'll
Feature activation+2.216
have
Token have
Feature activation+1.636
to
Token to
Feature activation+0.814
come
Token come
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
information
Token information
Feature activation+0.000
you
Token you
Feature activation+3.829
always
Token always
Feature activation+3.470
had
Token had
Feature activation+2.110
to
Token to
Feature activation+1.541
go
Token go
Feature activation+0.759
through
Token through
Feature activation+0.804
corporate
Token corporate
Feature activation+0.000
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+4.807
will
Token will
Feature activation+3.436
have
Token have
Feature activation+3.042
to
Token to
Feature activation+2.298
give
Token give
Feature activation+0.924
up
Token up
Feature activation+0.000
some
Token some
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
something
Token something
Feature activation+0.000
,
Token,
Feature activation+0.949
pay
Token pay
Feature activation+3.379
for
Token for
Feature activation+0.553
it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
poverty
Token poverty
Feature activation+0.000
further
Token further
Feature activation+0.000
,
Token,
Feature activation+3.304
it
Token it
Feature activation+3.027
can
Token can
Feature activation+2.103
be
Token be
Feature activation+2.969
done
Token done
Feature activation+0.838
very
Token very
Feature activation+0.251
married
Token married
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+3.253
you
Token you
Feature activation+2.486
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+1.341
go
Token go
Feature activation+1.392
%
Token%
Feature activation+0.000
to
Token to
Feature activation+0.000
4
Token 4
Feature activation+0.000
%
Token%
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+3.188
the
Token the
Feature activation+2.168
plan
Token plan
Feature activation+1.350
may
Token may
Feature activation+2.636
pay
Token pay
Feature activation+0.889
for
Token for
Feature activation+0.000

Top DFA by src position
MAX = 3.953

,
Token,
Feature activation+0.025
Top resid features:
âĢ
Token âĢ
Feature activation-0.037
Top resid features:
ľ
Tokenľ
Feature activation-0.000
Top resid features:
if
Tokenif
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.059
Top resid features:
want
Token want
Feature activation+3.953
Top resid features:
to
Token to
Feature activation+1.537
Top resid features:
care
Token care
Feature activation+0.111
Top resid features:
for
Token for
Feature activation-0.002
Top resid features:
your
Token your
Feature activation-0.002
Top resid features:
grandson
Token grandson
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.019
Top resid features:
"
Token"
Feature activation+0.025
Top resid features:
So
TokenSo
Feature activation-0.037
Top resid features:
if
Token if
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+0.199
Top resid features:
want
Token want
Feature activation+3.378
Top resid features:
to
Token to
Feature activation+1.319
Top resid features:
reduce
Token reduce
Feature activation+0.292
Top resid features:
corporate
Token corporate
Feature activation+0.052
Top resid features:
taxes
Token taxes
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.081
Top resid features:
explain
Token explain
Feature activation+0.023
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
if
Token if
Feature activation-0.001
Top resid features:
women
Token women
Feature activation-0.015
Top resid features:
really
Token really
Feature activation+0.109
Top resid features:
wanted
Token wanted
Feature activation+3.347
Top resid features:
to
Token to
Feature activation+1.321
Top resid features:
end
Token end
Feature activation+0.140
Top resid features:
rape
Token rape
Feature activation-0.207
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
they
Token they
Feature activation+0.057
Top resid features:
explain
Token explain
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
if
Token if
Feature activation-0.081
Top resid features:
women
Token women
Feature activation-0.005
Top resid features:
really
Token really
Feature activation+0.095
Top resid features:
wanted
Token wanted
Feature activation+3.197
Top resid features:
to
Token to
Feature activation+1.554
Top resid features:
end
Token end
Feature activation+0.152
Top resid features:
rape
Token rape
Feature activation-0.149
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
they
Token they
Feature activation+0.017
Top resid features:
market
Token market
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
If
Token If
Feature activation+0.029
Top resid features:
you
Token you
Feature activation+0.070
Top resid features:
would
Token would
Feature activation+0.249
Top resid features:
want
Token want
Feature activation+3.060
Top resid features:
to
Token to
Feature activation+0.803
Top resid features:
cut
Token cut
Feature activation+0.090
Top resid features:
this
Token this
Feature activation+0.095
Top resid features:
kind
Token kind
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.063
Top resid features:
old
Token old
Feature activation+0.001
Top resid features:
days
Token days
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
if
Token if
Feature activation-0.038
Top resid features:
you
Token you
Feature activation+0.056
Top resid features:
wanted
Token wanted
Feature activation+2.729
Top resid features:
to
Token to
Feature activation+1.133
Top resid features:
reach
Token reach
Feature activation+0.272
Top resid features:
large
Token large
Feature activation+0.019
Top resid features:
audiences
Token audiences
Feature activation+0.182
Top resid features:
of
Token of
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
So
TokenSo
Feature activation-0.026
Top resid features:
if
Token if
Feature activation+0.107
Top resid features:
you
Token you
Feature activation+0.146
Top resid features:
want
Token want
Feature activation+2.607
Top resid features:
to
Token to
Feature activation+1.323
Top resid features:
reduce
Token reduce
Feature activation+0.244
Top resid features:
corporate
Token corporate
Feature activation+0.041
Top resid features:
taxes
Token taxes
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.133
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
If
TokenIf
Feature activation+0.020
Top resid features:
you
Token you
Feature activation+0.127
Top resid features:
want
Token want
Feature activation+2.944
Top resid features:
to
Token to
Feature activation+1.105
Top resid features:
learn
Token learn
Feature activation+0.078
Top resid features:
Arabic
Token Arabic
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.178
Top resid features:
this
Token this
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
ľ
Tokenľ
Feature activation-0.004
Top resid features:
If
TokenIf
Feature activation+0.045
Top resid features:
you
Token you
Feature activation+0.069
Top resid features:
want
Token want
Feature activation+2.421
Top resid features:
to
Token to
Feature activation+1.193
Top resid features:
be
Token be
Feature activation+0.873
Top resid features:
in
Token in
Feature activation+0.063
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
global
Token global
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
If
TokenIf
Feature activation+0.022
Top resid features:
you
Token you
Feature activation+0.150
Top resid features:
want
Token want
Feature activation+3.216
Top resid features:
to
Token to
Feature activation+0.821
Top resid features:
learn
Token learn
Feature activation+0.067
Top resid features:
Arabic
Token Arabic
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.155
Top resid features:
this
Token this
Feature activation+0.021
Top resid features:
full
Token full
Feature activation-0.006
Top resid features:
40
Token 40
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
If
Token If
Feature activation+0.077
Top resid features:
you
Token you
Feature activation+0.075
Top resid features:
want
Token want
Feature activation+1.926
Top resid features:
to
Token to
Feature activation+1.495
Top resid features:
see
Token see
Feature activation+0.700
Top resid features:
the
Token the
Feature activation+0.097
Top resid features:
individual
Token individual
Feature activation-0.002
Top resid features:
cards
Token cards
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
If
TokenIf
Feature activation+0.052
Top resid features:
you
Token you
Feature activation+0.094
Top resid features:
want
Token want
Feature activation+2.527
Top resid features:
to
Token to
Feature activation+1.351
Top resid features:
take
Token take
Feature activation+0.200
Top resid features:
some
Token some
Feature activation+0.123
Top resid features:
action
Token action
Feature activation+0.130
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
of
Token of
Feature activation-0.043
Top resid features:
today
Token today
Feature activation-0.039
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
if
Token if
Feature activation+0.043
Top resid features:
investors
Token investors
Feature activation+0.101
Top resid features:
want
Token want
Feature activation+3.851
Top resid features:
hassle
Token hassle
Feature activation+0.121
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
free
Tokenfree
Feature activation-0.117
Top resid features:
exposure
Token exposure
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
"
Token"
Feature activation+0.030
Top resid features:
If
TokenIf
Feature activation+0.021
Top resid features:
Barcelona
Token Barcelona
Feature activation-0.017
Top resid features:
want
Token want
Feature activation+2.704
Top resid features:
to
Token to
Feature activation+1.134
Top resid features:
make
Token make
Feature activation+0.167
Top resid features:
history
Token history
Feature activation+0.226
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
old
Token old
Feature activation+0.002
Top resid features:
days
Token days
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
if
Token if
Feature activation+0.034
Top resid features:
you
Token you
Feature activation+0.057
Top resid features:
wanted
Token wanted
Feature activation+2.525
Top resid features:
to
Token to
Feature activation+0.950
Top resid features:
reach
Token reach
Feature activation+0.182
Top resid features:
large
Token large
Feature activation+0.043
Top resid features:
audiences
Token audiences
Feature activation+0.107
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
âĢ
Token âĢ
Feature activation-0.010
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
if
Tokenif
Feature activation+0.037
Top resid features:
you
Token you
Feature activation+0.053
Top resid features:
want
Token want
Feature activation+2.573
Top resid features:
to
Token to
Feature activation+1.136
Top resid features:
care
Token care
Feature activation+0.249
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
your
Token your
Feature activation+0.030
Top resid features:
grandson
Token grandson
Feature activation+0.045
Top resid features:
here
Token here
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
is
Token is
Feature activation-0.071
Top resid features:
if
Token if
Feature activation+0.020
Top resid features:
you
Token you
Feature activation+0.080
Top resid features:
want
Token want
Feature activation+3.409
Top resid features:
something
Token something
Feature activation+0.592
Top resid features:
,
Token,
Feature activation+0.108
Top resid features:
pay
Token pay
Feature activation+0.066
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Social
Token Social
Feature activation-0.009
Top resid features:
Security
Token Security
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
If
Token If
Feature activation+0.115
Top resid features:
you
Token you
Feature activation+0.181
Top resid features:
want
Token want
Feature activation+2.792
Top resid features:
to
Token to
Feature activation+0.938
Top resid features:
reduce
Token reduce
Feature activation+0.359
Top resid features:
poverty
Token poverty
Feature activation-0.166
Top resid features:
further
Token further
Feature activation-0.100
Top resid features:
,
Token,
Feature activation+0.071
Top resid features:
domestic
Token domestic
Feature activation-0.007
Top resid features:
partnerships
Token partnerships
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
If
Token If
Feature activation+0.030
Top resid features:
you
Token you
Feature activation+0.104
Top resid features:
wanted
Token wanted
Feature activation+2.830
Top resid features:
to
Token to
Feature activation+0.801
Top resid features:
get
Token get
Feature activation+0.268
Top resid features:
married
Token married
Feature activation+0.104
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
"
Token "
Feature activation+0.027
Top resid features:
if
Tokenif
Feature activation+0.071
Top resid features:
they
Token they
Feature activation+0.101
Top resid features:
want
Token want
Feature activation+2.751
Top resid features:
to
Token to
Feature activation+1.113
Top resid features:
assume
Token assume
Feature activation-0.033
Top resid features:
3
Token 3
Feature activation+0.012
Top resid features:
%
Token%
Feature activation-0.053
Top resid features:
to
Token to
Feature activation-0.025
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.02

Head 3: 0.51

Head 4: 0.03

Head 5: 0.08

Head 6: 0.06

Head 7: 0.09

Head 8: 0.04

Head 9: 0.02

Head 10: 0.02

Head 11: 0.06

Positive logits

ibrary2.43

must2.19

hemat2.16

hematic2.15

Fusion2.13

illac2.09

RAFT2.07

Amar2.07

feasibility2.06

hoops2.06

iP2.05

cheapest2.01

pony2.00

handcuffs1.97

reservations1.96

ought1.96

Fitzpatrick1.92

cartridges1.92

fusion1.91

zip1.91

Negative logits

sidx-3.09

-2.20

-2.16

Survivors-2.15

Sense-2.12

ptoms-2.11

ヘラ-2.09

Conf-2.08

-2.06

Happiness-2.02

ffic-2.01

龍喚士-1.99

atter-1.97

-1.96

deepening-1.96

-1.95

reflect-1.94

guiActiveUn-1.93

coli-1.93

shed-1.92

INTERVAL 4.326 - 4.807
CONTAINS 0.000%

want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
corporate
Token corporate
Feature activation+0.000
taxes
Token taxes
Feature activation+0.542
,
Token,
Feature activation+4.416
that
Token that
Feature activation+3.028
's
Token's
Feature activation+3.826
fine
Token fine
Feature activation+2.449
,
Token,
Feature activation+0.033
reduce
Token reduce
Feature activation+0.178
to
Token to
Feature activation+0.000
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+4.807
will
Token will
Feature activation+3.436
have
Token have
Feature activation+3.042
to
Token to
Feature activation+2.298
give
Token give
Feature activation+0.924
up
Token up
Feature activation+0.000

INTERVAL 3.845 - 4.326
CONTAINS 0.000%

wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+2.357
they
Token they
Feature activation+3.906
'd
Token'd
Feature activation+3.962
settle
Token settle
Feature activation+0.897
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.636
to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+2.357
they
Token they
Feature activation+3.906
'd
Token'd
Feature activation+3.962
settle
Token settle
Feature activation+0.897
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.636
married
Token married
Feature activation+0.000
this
Token this
Feature activation+0.060
kind
Token kind
Feature activation+0.262
of
Token of
Feature activation+0.060
inequality
Token inequality
Feature activation+0.315
off
Token off
Feature activation+0.008
,
Token,
Feature activation+3.879
you
Token you
Feature activation+2.538
would
Token would
Feature activation+2.705
also
Token also
Feature activation+0.835
have
Token have
Feature activation+1.401
to
Token to
Feature activation+0.589

INTERVAL 3.365 - 3.845
CONTAINS 0.001%

learn
Token learn
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.559
,
Token,
Feature activation+3.121
this
Token this
Feature activation+2.905
is
Token is
Feature activation+3.713
the
Token the
Feature activation+3.820
place
Token place
Feature activation+1.538
to
Token to
Feature activation+1.506
do
Token do
Feature activation+1.086
it
Token it
Feature activation+1.052
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
information
Token information
Feature activation+0.000
you
Token you
Feature activation+3.829
always
Token always
Feature activation+3.470
had
Token had
Feature activation+2.110
to
Token to
Feature activation+1.541
go
Token go
Feature activation+0.759
through
Token through
Feature activation+0.804
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
something
Token something
Feature activation+0.000
,
Token,
Feature activation+0.949
pay
Token pay
Feature activation+3.379
for
Token for
Feature activation+0.553
it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+4.807
will
Token will
Feature activation+3.436
have
Token have
Feature activation+3.042
to
Token to
Feature activation+2.298
give
Token give
Feature activation+0.924
up
Token up
Feature activation+0.000
some
Token some
Feature activation+0.000
cards
Token cards
Feature activation+0.006
detailing
Token detailing
Feature activation+0.000
the
Token the
Feature activation+0.000
hide
Token hide
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+3.649
head
Token head
Feature activation+1.344
over
Token over
Feature activation+0.467
to
Token to
Feature activation+1.390
Mov
Token Mov
Feature activation+0.000
oto
Tokenoto
Feature activation+0.000

INTERVAL 2.884 - 3.365
CONTAINS 0.002%

or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.000
circus
Token circus
Feature activation+0.000
clown
Token clown
Feature activation+0.000
the
Token the
Feature activation+2.443
only
Token only
Feature activation+2.980
thing
Token thing
Feature activation+2.654
standing
Token standing
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
way
Token way
Feature activation+0.447
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+2.513
he
Token he
Feature activation+3.016
couldn
Token couldn
Feature activation+2.987
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.144
be
Token be
Feature activation+1.773
%
Token%
Feature activation+0.000
to
Token to
Feature activation+0.000
4
Token 4
Feature activation+0.000
%
Token%
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+3.188
the
Token the
Feature activation+2.168
plan
Token plan
Feature activation+1.350
may
Token may
Feature activation+2.636
pay
Token pay
Feature activation+0.889
for
Token for
Feature activation+0.000
married
Token married
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+3.253
you
Token you
Feature activation+2.486
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+1.341
go
Token go
Feature activation+1.392
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.046
repeal
Token repeal
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
,
Token,
Feature activation+3.046
we
Token we
Feature activation+2.906
better
Token better
Feature activation+0.890
hold
Token hold
Feature activation+0.345
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.403 - 2.884
CONTAINS 0.003%

a
Token a
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+2.702
this
Token this
Feature activation+2.679
kid
Token kid
Feature activation+0.000
can
Token can
Feature activation+1.494
be
Token be
Feature activation+1.053
it
Token it
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
,
Token,
Feature activation+1.073
you
Token you
Feature activation+2.754
could
Token could
Feature activation+2.533
just
Token just
Feature activation+1.034
enter
Token enter
Feature activation+0.000
270
Token 270
Feature activation+0.000
//
Token //
Feature activation+0.014
but
Token but
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+2.702
this
Token this
Feature activation+2.679
kid
Token kid
Feature activation+0.000
can
Token can
Feature activation+1.494
be
Token be
Feature activation+1.053
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+2.513
he
Token he
Feature activation+3.016
couldn
Token couldn
Feature activation+2.987
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.144
of
Token of
Feature activation+0.060
inequality
Token inequality
Feature activation+0.315
off
Token off
Feature activation+0.008
,
Token,
Feature activation+3.879
you
Token you
Feature activation+2.538
would
Token would
Feature activation+2.705
also
Token also
Feature activation+0.835
have
Token have
Feature activation+1.401
to
Token to
Feature activation+0.589
cut
Token cut
Feature activation+0.166
startups
Token startups
Feature activation+0.000

INTERVAL 1.923 - 2.403
CONTAINS 0.005%

with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
information
Token information
Feature activation+0.000
you
Token you
Feature activation+3.829
always
Token always
Feature activation+3.470
had
Token had
Feature activation+2.110
to
Token to
Feature activation+1.541
go
Token go
Feature activation+0.759
through
Token through
Feature activation+0.804
corporate
Token corporate
Feature activation+0.000
gate
Token gate
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+4.807
will
Token will
Feature activation+3.436
have
Token have
Feature activation+3.042
to
Token to
Feature activation+2.298
give
Token give
Feature activation+0.924
up
Token up
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.030
(
Token (
Feature activation+0.000
can
Tokencan
Feature activation+0.000
't
Token't
Feature activation+0.000
blame
Token blame
Feature activation+0.000
you
Token you
Feature activation+0.000
),
Token),
Feature activation+2.360
the
Token the
Feature activation+0.305
short
Token short
Feature activation+0.000
version
Token version
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
If
Token If
Feature activation+0.000
they
Token they
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
,
Token,
Feature activation+2.157
we
Token we
Feature activation+1.950
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.664
here
Token here
Feature activation+1.088
B
Token B
Feature activation+0.000
augh
Tokenaugh
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
bench
Token bench
Feature activation+0.000
,
Token,
Feature activation+2.385
there
Token there
Feature activation+1.873
is
Token is
Feature activation+1.116
a
Token a
Feature activation+0.766
petition
Token petition
Feature activation+0.524
you
Token you
Feature activation+0.563

INTERVAL 1.442 - 1.923
CONTAINS 0.005%

competition
Token competition
Feature activation+0.000
,
Token,
Feature activation+1.719
then
Token then
Feature activation+2.683
we
Token we
Feature activation+1.927
do
Token do
Feature activation+1.249
not
Token not
Feature activation+1.717
have
Token have
Feature activation+0.961
the
Token the
Feature activation+0.149
luxury
Token luxury
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
offer
Token offer
Feature activation+0.000
toys
Token toys
Feature activation+0.000
as
Token as
Feature activation+0.000
incentives
Token incentives
Feature activation+0.000
,
Token,
Feature activation+2.549
the
Token the
Feature activation+1.739
meals
Token meals
Feature activation+0.411
must
Token must
Feature activation+1.031
meet
Token meet
Feature activation+0.000
new
Token new
Feature activation+0.000
nutrition
Token nutrition
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
topic
Token topic
Feature activation+0.000
,
Token,
Feature activation+0.530
then
Token then
Feature activation+1.457
I
Token I
Feature activation+0.160
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
point
Token point
Feature activation+0.000
fashion
Token fashion
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+2.169
they
Token they
Feature activation+1.855
could
Token could
Feature activation+1.937
have
Token have
Feature activation+1.728
approached
Token approached
Feature activation+0.409
models
Token models
Feature activation+0.000
like
Token like
Feature activation+0.000
Andre
Token Andre
Feature activation+0.000
ja
Tokenja
Feature activation+0.000
text
Token text
Feature activation+0.000
in
Token in
Feature activation+0.000
In
Token In
Feature activation+0.000
Design
TokenDesign
Feature activation+0.000
,
Token,
Feature activation+2.084
then
Token then
Feature activation+1.796
bounce
Token bounce
Feature activation+0.148
the
Token the
Feature activation+0.000
file
Token file
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.961 - 1.442
CONTAINS 0.009%

or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000
appointments
Token appointments
Feature activation+0.000
,
Token,
Feature activation+0.553
they
Token they
Feature activation+1.432
get
Token get
Feature activation+1.297
them
Token them
Feature activation+0.640
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
spot
Token spot
Feature activation+0.000
,
Token,
Feature activation+2.157
we
Token we
Feature activation+1.950
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.664
here
Token here
Feature activation+1.088
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
ready
Token ready
Feature activation+0.000
."
Token."
Feature activation+0.000
a
Token a
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000
appointments
Token appointments
Feature activation+0.000
,
Token,
Feature activation+0.553
they
Token they
Feature activation+1.432
get
Token get
Feature activation+1.297
them
Token them
Feature activation+0.640
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
spot
Token spot
Feature activation+0.000
.
Token.
Feature activation+0.000
then
Token then
Feature activation+0.417
do
Token do
Feature activation+0.008
something
Token something
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+1.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.102
Ret
TokenRet
Feature activation+0.000
weet
Tokenweet
Feature activation+0.000
:
Token:
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
G
Token G
Feature activation+0.000
ives
Tokenives
Feature activation+0.000
a
Token a
Feature activation+0.000
Shit
Token Shit
Feature activation+0.000
?,
Token?,
Feature activation+1.081
stop
Token stop
Feature activation+1.484
being
Token being
Feature activation+0.735
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.481 - 0.961
CONTAINS 0.016%

a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
cause
Token cause
Feature activation+0.000
,
Token,
Feature activation+1.441
perhaps
Token perhaps
Feature activation+0.562
try
Token try
Feature activation+0.740
Open
Token Open
Feature activation+0.000
SC
TokenSC
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
you
Token you
Feature activation+0.106
collect
Token collect
Feature activation+0.000
something
Token something
Feature activation+0.000
and
Token and
Feature activation+0.562
then
Token then
Feature activation+0.241
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
DIY
Token DIY
Feature activation+0.000
approach
Token approach
Feature activation+0.000
you
Token you
Feature activation+1.507
may
Token may
Feature activation+1.053
be
Token be
Feature activation+0.706
interested
Token interested
Feature activation+0.485
in
Token in
Feature activation+0.194
our
Token our
Feature activation+0.000
brother
Token brother
Feature activation+0.000
company
Token company
Feature activation+0.000
wed
Token wed
Feature activation+0.567
"
Token "
Feature activation+0.379
would
Tokenwould
Feature activation+2.276
suffer
Token suffer
Feature activation+2.148
many
Token many
Feature activation+0.125
hardships
Token hardships
Feature activation+0.552
of
Token of
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
magnitude
Token magnitude
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
conversion
Token conversion
Feature activation+0.000
,
Token,
Feature activation+1.048
you
Token you
Feature activation+0.915
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.672
need
Token need
Feature activation+0.267
to
Token to
Feature activation+0.258
talk
Token talk
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000

INTERVAL 0.000 - 0.481
CONTAINS 99.958%

parties
Token parties
Feature activation+0.000
at
Token at
Feature activation+0.000
both
Token both
Feature activation+0.000
ends
Token ends
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
transaction
Token transaction
Feature activation+0.000
are
Token are
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
Ma
Token Ma
Feature activation+0.000
eda
Tokeneda
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
design
Token design
Feature activation+0.000
played
Token played
Feature activation+0.000
a
Token a
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Tokenit
Feature activation+0.000
city
Token city
Feature activation+0.000
dwell
Token dwell
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
funded
Token funded
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
of
Token of
Feature activation+0.000
Yelp
Token Yelp
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
"
Token "
Feature activation+0.000
Ryan
TokenRyan
Feature activation+0.000
Budget
Token Budget
Feature activation+0.000
,"
Token,"
Feature activation+0.000
also
Token also
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
mass
Token mass
Feature activation+0.000
shootings
Token shootings
Feature activation+0.000
who
Token who
Feature activation+0.000
watched
Token watched
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

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 H6.3: (feature 24144)

TOP ACTIVATIONS
MAX = 4.972

then
Token then
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
and
Token and
Feature activation+0.015
then
Token then
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
blue
Token blue
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
economists
Token economists
Feature activation+0.000
at
Token at
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
economists
Token economists
Feature activation+0.000
on
Token on
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+1.851
you
Token you
Feature activation+1.669
might
Token might
Feature activation+1.701
want
Token want
Feature activation+1.136
to
Token to
Feature activation+0.721
consider
Token consider
Feature activation+0.683
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
an
Token an
Feature activation+0.000
addition
Token addition
Feature activation+0.000
chain
Token chain
Feature activation+0.000
,
Token,
Feature activation+1.736
the
Token the
Feature activation+1.453
next
Token next
Feature activation+0.545
form
Token form
Feature activation+0.189
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
k
Token k
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
el
Tokenel
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
,
Token,
Feature activation+1.444
it
Token it
Feature activation+1.720
can
Token can
Feature activation+1.512
spread
Token spread
Feature activation+0.000
very
Token very
Feature activation+0.000
rapidly
Token rapidly
Feature activation+0.000
."
Token."
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+1.851
you
Token you
Feature activation+1.669
might
Token might
Feature activation+1.701
want
Token want
Feature activation+1.136
to
Token to
Feature activation+0.721
consider
Token consider
Feature activation+0.683
packing
Token packing
Feature activation+0.000
a
Token a
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201
that
Token that
Feature activation+0.278
visiting
Token visiting
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+1.851
you
Token you
Feature activation+1.669
might
Token might
Feature activation+1.701
want
Token want
Feature activation+1.136
to
Token to
Feature activation+0.721
consider
Token consider
Feature activation+0.683
packing
Token packing
Feature activation+0.000
the
Token the
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201
enn
Tokenenn
Feature activation+0.000
el
Tokenel
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
,
Token,
Feature activation+1.444
it
Token it
Feature activation+1.720
can
Token can
Feature activation+1.512
spread
Token spread
Feature activation+0.000
very
Token very
Feature activation+0.000
rapidly
Token rapidly
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
do
Token do
Feature activation+0.000
an
Token an
Feature activation+0.000
addition
Token addition
Feature activation+0.000
chain
Token chain
Feature activation+0.000
,
Token,
Feature activation+1.736
the
Token the
Feature activation+1.453
next
Token next
Feature activation+0.545
form
Token form
Feature activation+0.189
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
in
Token in
Feature activation+0.000
k
Token k
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
el
Tokenel
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
,
Token,
Feature activation+1.444
it
Token it
Feature activation+1.720
can
Token can
Feature activation+1.512
spread
Token spread
Feature activation+0.000
very
Token very
Feature activation+0.000
rapidly
Token rapidly
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201
that
Token that
Feature activation+0.278
business
Token business
Feature activation+0.073

Top DFA by src position
MAX = 4.139

But
TokenBut
Feature activation-0.008
Top resid features:
if
Token if
Feature activation-0.034
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+0.050
Top resid features:
going
Token going
Feature activation+1.580
Top resid features:
to
Token to
Feature activation+4.139
Top resid features:
insist
Token insist
Feature activation+0.180
Top resid features:
on
Token on
Feature activation+0.068
Top resid features:
modeling
Token modeling
Feature activation-0.052
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
future
Token future
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
If
Token If
Feature activation-0.060
Top resid features:
it
Token it
Feature activation+0.037
Top resid features:
was
Token was
Feature activation+0.140
Top resid features:
going
Token going
Feature activation+1.850
Top resid features:
to
Token to
Feature activation+3.799
Top resid features:
rely
Token rely
Feature activation+0.316
Top resid features:
on
Token on
Feature activation+0.033
Top resid features:
them
Token them
Feature activation+0.052
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
it
Token it
Feature activation-0.068
Top resid features:
But
TokenBut
Feature activation-0.017
Top resid features:
if
Token if
Feature activation-0.055
Top resid features:
you
Token you
Feature activation-0.058
Top resid features:
are
Token are
Feature activation+0.045
Top resid features:
going
Token going
Feature activation+1.670
Top resid features:
to
Token to
Feature activation+3.416
Top resid features:
insist
Token insist
Feature activation+0.181
Top resid features:
on
Token on
Feature activation+0.105
Top resid features:
modeling
Token modeling
Feature activation-0.090
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
future
Token future
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
If
Token If
Feature activation-0.030
Top resid features:
it
Token it
Feature activation+0.063
Top resid features:
was
Token was
Feature activation+0.107
Top resid features:
going
Token going
Feature activation+1.515
Top resid features:
to
Token to
Feature activation+2.786
Top resid features:
rely
Token rely
Feature activation+0.730
Top resid features:
on
Token on
Feature activation+0.052
Top resid features:
them
Token them
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
If
Token If
Feature activation-0.053
Top resid features:
it
Token it
Feature activation+0.118
Top resid features:
was
Token was
Feature activation+0.227
Top resid features:
going
Token going
Feature activation+1.580
Top resid features:
to
Token to
Feature activation+2.597
Top resid features:
rely
Token rely
Feature activation+0.514
Top resid features:
on
Token on
Feature activation+0.050
Top resid features:
them
Token them
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation-0.004
Top resid features:
if
Token if
Feature activation-0.002
Top resid features:
you
Token you
Feature activation-0.048
Top resid features:
are
Token are
Feature activation+0.059
Top resid features:
going
Token going
Feature activation+1.254
Top resid features:
to
Token to
Feature activation+3.323
Top resid features:
insist
Token insist
Feature activation+0.155
Top resid features:
on
Token on
Feature activation+0.089
Top resid features:
modeling
Token modeling
Feature activation-0.037
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
future
Token future
Feature activation+0.009
Top resid features:
But
TokenBut
Feature activation+0.002
Top resid features:
if
Token if
Feature activation-0.019
Top resid features:
you
Token you
Feature activation-0.023
Top resid features:
are
Token are
Feature activation+0.036
Top resid features:
going
Token going
Feature activation+1.268
Top resid features:
to
Token to
Feature activation+2.322
Top resid features:
insist
Token insist
Feature activation+0.150
Top resid features:
on
Token on
Feature activation+0.080
Top resid features:
modeling
Token modeling
Feature activation-0.030
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
future
Token future
Feature activation+0.001
Top resid features:
But
TokenBut
Feature activation+0.009
Top resid features:
if
Token if
Feature activation-0.000
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+0.025
Top resid features:
going
Token going
Feature activation+0.727
Top resid features:
to
Token to
Feature activation+2.351
Top resid features:
insist
Token insist
Feature activation+0.066
Top resid features:
on
Token on
Feature activation+0.055
Top resid features:
modeling
Token modeling
Feature activation-0.039
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
future
Token future
Feature activation-0.004
Top resid features:
But
TokenBut
Feature activation+0.005
Top resid features:
if
Token if
Feature activation-0.002
Top resid features:
you
Token you
Feature activation-0.014
Top resid features:
are
Token are
Feature activation+0.028
Top resid features:
going
Token going
Feature activation+0.697
Top resid features:
to
Token to
Feature activation+2.264
Top resid features:
insist
Token insist
Feature activation+0.116
Top resid features:
on
Token on
Feature activation+0.073
Top resid features:
modeling
Token modeling
Feature activation-0.037
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
future
Token future
Feature activation+0.007
Top resid features:
if
Token if
Feature activation-0.038
Top resid features:
you
Token you
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation+0.046
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
re
Tokenre
Feature activation+0.074
Top resid features:
planning
Token planning
Feature activation+1.576
Top resid features:
on
Token on
Feature activation+0.735
Top resid features:
visiting
Token visiting
Feature activation+0.153
Top resid features:
either
Token either
Feature activation+0.117
Top resid features:
amusement
Token amusement
Feature activation+0.027
Top resid features:
park
Token park
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
Since
TokenSince
Feature activation-0.086
Top resid features:
we
Token we
Feature activation-0.010
Top resid features:
are
Token are
Feature activation+0.221
Top resid features:
going
Token going
Feature activation+1.286
Top resid features:
to
Token to
Feature activation+1.621
Top resid features:
do
Token do
Feature activation+0.184
Top resid features:
an
Token an
Feature activation-0.013
Top resid features:
addition
Token addition
Feature activation-0.057
Top resid features:
chain
Token chain
Feature activation-0.245
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
"
Token "
Feature activation-0.020
Top resid features:
When
TokenWhen
Feature activation-0.117
Top resid features:
dogs
Token dogs
Feature activation+0.031
Top resid features:
are
Token are
Feature activation+0.021
Top resid features:
going
Token going
Feature activation+1.012
Top resid features:
to
Token to
Feature activation+1.846
Top resid features:
day
Token day
Feature activation-0.001
Top resid features:
care
Token care
Feature activation+0.020
Top resid features:
or
Token or
Feature activation-0.035
Top resid features:
dog
Token dog
Feature activation-0.011
Top resid features:
parks
Token parks
Feature activation-0.002
Top resid features:
if
Token if
Feature activation-0.018
Top resid features:
you
Token you
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.022
Top resid features:
re
Tokenre
Feature activation+0.030
Top resid features:
planning
Token planning
Feature activation+1.276
Top resid features:
on
Token on
Feature activation+0.910
Top resid features:
visiting
Token visiting
Feature activation+0.151
Top resid features:
either
Token either
Feature activation+0.136
Top resid features:
amusement
Token amusement
Feature activation+0.009
Top resid features:
park
Token park
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
if
Token if
Feature activation+0.042
Top resid features:
we
Token we
Feature activation+0.082
Top resid features:
want
Token want
Feature activation+0.503
Top resid features:
to
Token to
Feature activation+0.820
Top resid features:
be
Token be
Feature activation+0.287
Top resid features:
in
Token in
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
cleaning
Token cleaning
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
if
Token if
Feature activation-0.015
Top resid features:
you
Token you
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation-0.015
Top resid features:
Ļ
TokenĻ
Feature activation+0.027
Top resid features:
re
Tokenre
Feature activation+0.074
Top resid features:
planning
Token planning
Feature activation+1.290
Top resid features:
on
Token on
Feature activation+0.861
Top resid features:
visiting
Token visiting
Feature activation+0.100
Top resid features:
either
Token either
Feature activation+0.164
Top resid features:
amusement
Token amusement
Feature activation+0.025
Top resid features:
park
Token park
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.107
Top resid features:
if
Token if
Feature activation+0.025
Top resid features:
we
Token we
Feature activation+0.104
Top resid features:
want
Token want
Feature activation+0.362
Top resid features:
to
Token to
Feature activation+0.638
Top resid features:
be
Token be
Feature activation+0.365
Top resid features:
in
Token in
Feature activation+0.080
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
cleaning
Token cleaning
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
"
Token "
Feature activation-0.013
Top resid features:
When
TokenWhen
Feature activation-0.086
Top resid features:
dogs
Token dogs
Feature activation+0.044
Top resid features:
are
Token are
Feature activation+0.013
Top resid features:
going
Token going
Feature activation+0.630
Top resid features:
to
Token to
Feature activation+1.882
Top resid features:
day
Token day
Feature activation+0.004
Top resid features:
care
Token care
Feature activation+0.025
Top resid features:
or
Token or
Feature activation-0.016
Top resid features:
dog
Token dog
Feature activation+0.001
Top resid features:
parks
Token parks
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
Since
TokenSince
Feature activation-0.055
Top resid features:
we
Token we
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+0.123
Top resid features:
going
Token going
Feature activation+0.818
Top resid features:
to
Token to
Feature activation+1.423
Top resid features:
do
Token do
Feature activation+0.177
Top resid features:
an
Token an
Feature activation+0.014
Top resid features:
addition
Token addition
Feature activation-0.035
Top resid features:
chain
Token chain
Feature activation-0.049
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
"
Token "
Feature activation-0.036
Top resid features:
When
TokenWhen
Feature activation-0.128
Top resid features:
dogs
Token dogs
Feature activation+0.068
Top resid features:
are
Token are
Feature activation+0.024
Top resid features:
going
Token going
Feature activation+0.855
Top resid features:
to
Token to
Feature activation+1.677
Top resid features:
day
Token day
Feature activation+0.007
Top resid features:
care
Token care
Feature activation+0.036
Top resid features:
or
Token or
Feature activation-0.032
Top resid features:
dog
Token dog
Feature activation-0.003
Top resid features:
parks
Token parks
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
if
Token if
Feature activation+0.032
Top resid features:
we
Token we
Feature activation+0.015
Top resid features:
want
Token want
Feature activation+0.325
Top resid features:
to
Token to
Feature activation+0.583
Top resid features:
be
Token be
Feature activation+0.267
Top resid features:
in
Token in
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
cleaning
Token cleaning
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.03

Head 3: 0.50

Head 4: 0.03

Head 5: 0.09

Head 6: 0.06

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.02

Head 11: 0.05

Positive logits

ought2.40

must2.32

���2.31

necess2.26

needs2.20

restraints2.19

needs2.18

shouldn2.16

Sov2.16

compromises2.11

ymm2.04

Armory2.02

Skydragon2.00

obligation1.98

must1.98

brainer1.97

need1.94

trump1.93

wcsstore1.91

inks1.90

Negative logits

resumed-2.18

inical-2.12

Earn-2.10

plunged-2.08

erk-2.03

regained-2.02

ILD-2.01

Now-1.99

orescence-1.95

etooth-1.95

srf-1.93

otle-1.92

healed-1.90

Later-1.87

Afterwards-1.87

returned-1.85

clinical-1.83

Nest-1.82

apsed-1.82

RESULTS-1.81

INTERVAL 4.475 - 4.972
CONTAINS 0.000%

to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
then
Token then
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000

INTERVAL 3.978 - 4.475
CONTAINS 0.000%

rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
blue
Token blue
Feature activation+0.000
and
Token and
Feature activation+0.015
then
Token then
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278

INTERVAL 3.481 - 3.978
CONTAINS 0.000%

going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.330
,
Token,
Feature activation+3.877
it
Token it
Feature activation+4.957
would
Token would
Feature activation+4.199
provide
Token provide
Feature activation+0.606
them
Token them
Feature activation+0.813
with
Token with
Feature activation+0.000
planning
Token planning
Feature activation+0.000
around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.983 - 3.481
CONTAINS 0.000%

INTERVAL 2.486 - 2.983
CONTAINS 0.000%

around
Token around
Feature activation+0.000
it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.989 - 2.486
CONTAINS 0.000%

it
Token it
Feature activation+0.293
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
economists
Token economists
Feature activation+0.000
,
Token,
Feature activation+4.317
you
Token you
Feature activation+4.972
have
Token have
Feature activation+3.799
to
Token to
Feature activation+2.861
do
Token do
Feature activation+2.172
it
Token it
Feature activation+2.278
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
economists
Token economists
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 1.492 - 1.989
CONTAINS 0.001%

to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
an
Token an
Feature activation+0.000
addition
Token addition
Feature activation+0.000
chain
Token chain
Feature activation+0.000
,
Token,
Feature activation+1.736
the
Token the
Feature activation+1.453
next
Token next
Feature activation+0.545
form
Token form
Feature activation+0.189
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
k
Token k
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
el
Tokenel
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
,
Token,
Feature activation+1.444
it
Token it
Feature activation+1.720
can
Token can
Feature activation+1.512
spread
Token spread
Feature activation+0.000
very
Token very
Feature activation+0.000
rapidly
Token rapidly
Feature activation+0.000
."
Token."
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+1.851
you
Token you
Feature activation+1.669
might
Token might
Feature activation+1.701
want
Token want
Feature activation+1.136
to
Token to
Feature activation+0.721
consider
Token consider
Feature activation+0.683
packing
Token packing
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201
that
Token that
Feature activation+0.278
the
Token the
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201

INTERVAL 0.994 - 1.492
CONTAINS 0.002%

to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+1.122
they
Token they
Feature activation+0.786
'd
Token'd
Feature activation+1.077
settle
Token settle
Feature activation+0.000
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
married
Token married
Feature activation+0.000
be
Token be
Feature activation+0.000
changes
Token changes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
routine
Token routine
Feature activation+0.000
,
Token,
Feature activation+1.324
let
Token let
Feature activation+1.195
the
Token the
Feature activation+0.000
child
Token child
Feature activation+0.278
know
Token know
Feature activation+0.721
in
Token in
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.010
,
Token,
Feature activation+1.162
make
Token make
Feature activation+0.576
sure
Token sure
Feature activation+0.453
you
Token you
Feature activation+0.280
do
Token do
Feature activation+0.000
everything
Token everything
Feature activation+0.000
of
Token of
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
business
Token business
Feature activation+0.590
,
Token,
Feature activation+1.569
then
Token then
Feature activation+1.699
we
Token we
Feature activation+1.399
have
Token have
Feature activation+1.134
to
Token to
Feature activation+0.493
own
Token own
Feature activation+0.201
that
Token that
Feature activation+0.278
business
Token business
Feature activation+0.073
to
Token to
Feature activation+0.000
catch
Token catch
Feature activation+0.000
the
Token the
Feature activation+0.000
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+1.091
we
Token we
Feature activation+0.331
're
Token're
Feature activation+0.060
expecting
Token expecting
Feature activation+0.000
some
Token some
Feature activation+0.000
significant
Token significant
Feature activation+0.000

INTERVAL 0.497 - 0.994
CONTAINS 0.004%

the
Token the
Feature activation+0.000
house
Token house
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.840
it
Token it
Feature activation+0.505
would
Token would
Feature activation+0.758
have
Token have
Feature activation+0.531
to
Token to
Feature activation+0.378
pay
Token pay
Feature activation+0.112
the
Token the
Feature activation+0.000
lender
Token lender
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.664
we
Token we
Feature activation+0.321
'll
Token'll
Feature activation+0.291
have
Token have
Feature activation+0.130
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
grandson
Token grandson
Feature activation+0.000
you
Token you
Feature activation+0.722
will
Token will
Feature activation+0.484
have
Token have
Feature activation+0.269
to
Token to
Feature activation+0.125
give
Token give
Feature activation+0.000
up
Token up
Feature activation+0.000
an
Token an
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
trust
Tokentrust
Feature activation+0.000
issue
Token issue
Feature activation+0.000
,
Token,
Feature activation+0.885
why
Token why
Feature activation+0.338
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
or
Token or
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
,
Token,
Feature activation+0.544
the
Token the
Feature activation+0.882
Army
Token Army
Feature activation+0.384
will
Token will
Feature activation+0.729
gain
Token gain
Feature activation+0.000
range
Token range
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
decent
Token decent
Feature activation+0.000

INTERVAL 0.000 - 0.497
CONTAINS 99.992%

rookie
Token rookie
Feature activation+0.000
V
Token V
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Bott
Token Bott
Feature activation+0.000
as
Tokenas
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
structure
Token structure
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
elected
Token elected
Feature activation+0.000
by
Token by
Feature activation+0.000
voters
Token voters
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.000
information
Token information
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Last
Token Last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
Agency
Token Agency
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
drug
Token drug
Feature activation+0.000
inter
Token inter
Feature activation+0.000
d
Tokend
Feature activation+0.000
Scientist
Token Scientist
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
Evangel
Token Evangel
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
officials
Token officials
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 H6.3: (feature 12229)

TOP ACTIVATIONS
MAX = 3.991

his
Token his
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+0.000
setting
Tokensetting
Feature activation+0.000
pace
Token pace
Feature activation+0.000
.
Token.
Feature activation+3.991
The
Token The
Feature activation+1.687
Packers
Token Packers
Feature activation+0.841
would
Token would
Feature activation+0.148
head
Token head
Feature activation+0.000
back
Token back
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.370
but
Token but
Feature activation+3.430
they
Token they
Feature activation+3.201
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fl
Token fl
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.370
but
Token but
Feature activation+3.430
they
Token they
Feature activation+3.201
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fl
Token fl
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
their
Token their
Feature activation+0.000
speech
Token speech
Feature activation+0.174
on
Token on
Feature activation+0.081
June
Token June
Feature activation+0.294
13
Token 13
Feature activation+0.749
,
Token,
Feature activation+1.166
but
Token but
Feature activation+3.178
decided
Token decided
Feature activation+3.150
to
Token to
Feature activation+1.014
postpone
Token postpone
Feature activation+0.093
it
Token it
Feature activation+0.487
after
Token after
Feature activation+0.000
on
Token on
Feature activation+0.081
June
Token June
Feature activation+0.294
13
Token 13
Feature activation+0.749
,
Token,
Feature activation+1.166
but
Token but
Feature activation+3.178
decided
Token decided
Feature activation+3.150
to
Token to
Feature activation+1.014
postpone
Token postpone
Feature activation+0.093
it
Token it
Feature activation+0.487
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.100
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.238
but
Token but
Feature activation+2.466
delivered
Token delivered
Feature activation+2.839
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.277
that
Token that
Feature activation+0.083
sex
Token sex
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.169
but
Token but
Feature activation+2.538
was
Token was
Feature activation+2.830
taken
Token taken
Feature activation+0.000
away
Token away
Feature activation+0.000
in
Token in
Feature activation+0.000
handcuffs
Token handcuffs
Feature activation+0.000
before
Token before
Feature activation+0.000
reun
Token reun
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
.
Token.
Feature activation+2.091
Ċ
TokenĊ
Feature activation+1.375
Ċ
TokenĊ
Feature activation+1.787
But
TokenBut
Feature activation+2.761
whether
Token whether
Feature activation+0.308
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.619
grants
Token grants
Feature activation+0.000
officer
Token officer
Feature activation+0.000
-
Token-
Feature activation+0.000
involved
Tokeninvolved
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
,
Token,
Feature activation+0.308
but
Token but
Feature activation+2.637
that
Token that
Feature activation+1.460
officer
Token officer
Feature activation+0.000
's
Token's
Feature activation+0.000
camera
Token camera
Feature activation+0.000
had
Token had
Feature activation+0.469
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
server
Token server
Feature activation+0.119
,
Token,
Feature activation+0.269
but
Token but
Feature activation+2.592
Imran
Token Imran
Feature activation+0.000
moved
Token moved
Feature activation+0.000
files
Token files
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
for
Token for
Feature activation+0.000
sex
Token sex
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.169
but
Token but
Feature activation+2.538
was
Token was
Feature activation+2.830
taken
Token taken
Feature activation+0.000
away
Token away
Feature activation+0.000
in
Token in
Feature activation+0.000
handcuffs
Token handcuffs
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.238
but
Token but
Feature activation+2.466
delivered
Token delivered
Feature activation+2.839
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.277
Wisconsin
Token Wisconsin
Feature activation+0.025
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.023
,
Token,
Feature activation+0.280
but
Token but
Feature activation+1.404
in
Token in
Feature activation+2.421
late
Token late
Feature activation+0.142
December
Token December
Feature activation+0.226
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
January
Token January
Feature activation+0.000
a
Token a
Feature activation+0.000
flare
Token flare
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.291
but
Token but
Feature activation+2.328
I
Token I
Feature activation+1.599
think
Token think
Feature activation+0.207
I
Token I
Feature activation+0.309
will
Token will
Feature activation+0.000
wait
Token wait
Feature activation+0.000
motion
Token motion
Feature activation+0.081
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.214
afternoon
Token afternoon
Feature activation+0.799
,
Token,
Feature activation+0.625
but
Token but
Feature activation+2.318
Hanson
Token Hanson
Feature activation+0.056
got
Token got
Feature activation+1.197
there
Token there
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
and
Token and
Feature activation+0.000
recreate
Token recreate
Feature activation+0.000
--
Token--
Feature activation+0.000
but
Tokenbut
Feature activation+2.122
finding
Token finding
Feature activation+0.517
the
Token the
Feature activation+0.000
correct
Token correct
Feature activation+0.000
lex
Token lex
Feature activation+0.000
icon
Tokenicon
Feature activation+0.000
convince
Token convince
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
.
Token.
Feature activation+2.091
Ċ
TokenĊ
Feature activation+1.375
Ċ
TokenĊ
Feature activation+1.787
But
TokenBut
Feature activation+2.761
whether
Token whether
Feature activation+0.308
or
Token or
Feature activation+0.000
common
Token common
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Netherlands
Token Netherlands
Feature activation+0.000
.
Token.
Feature activation+1.278
But
Token But
Feature activation+2.034
then
Token then
Feature activation+0.389
prices
Token prices
Feature activation+0.072
t
Token t
Feature activation+0.000
umbled
Tokenumbled
Feature activation+0.000
following
Token following
Feature activation+0.000
to
Token to
Feature activation+0.000
university
Token university
Feature activation+0.000
with
Token with
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.615
but
Token but
Feature activation+2.024
she
Token she
Feature activation+1.047
was
Token was
Feature activation+0.678
walking
Token walking
Feature activation+0.000
alone
Token alone
Feature activation+0.000
when
Token when
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
ret
Token ret
Feature activation+0.000
itled
Tokenitled
Feature activation+0.000
.
Token.
Feature activation+1.558
But
Token But
Feature activation+1.864
finding
Token finding
Feature activation+0.440
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
fit
Token fit
Feature activation+0.000

Top DFA by src position
MAX = 2.889

the
Token the
Feature activation+0.000
Top resid features:
Green
Token Green
Feature activation+0.001
Top resid features:
Bay
Token Bay
Feature activation+0.000
Top resid features:
Packers
Token Packers
Feature activation+0.006
Top resid features:
was
Token was
Feature activation+0.138
Top resid features:
supposed
Token supposed
Feature activation+2.237
Top resid features:
to
Token to
Feature activation+1.857
Top resid features:
go
Token go
Feature activation+0.152
Top resid features:
something
Token something
Feature activation-0.003
Top resid features:
like
Token like
Feature activation+0.003
Top resid features:
this
Token this
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Paper
TokenPaper
Feature activation+0.008
Top resid features:
receipts
Token receipts
Feature activation+0.021
Top resid features:
are
Token are
Feature activation-0.003
Top resid features:
supposed
Token supposed
Feature activation+1.711
Top resid features:
to
Token to
Feature activation+1.593
Top resid features:
be
Token be
Feature activation+0.771
Top resid features:
on
Token on
Feature activation-0.015
Top resid features:
their
Token their
Feature activation-0.013
Top resid features:
way
Token way
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Paper
TokenPaper
Feature activation+0.004
Top resid features:
receipts
Token receipts
Feature activation+0.030
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
supposed
Token supposed
Feature activation+1.415
Top resid features:
to
Token to
Feature activation+1.717
Top resid features:
be
Token be
Feature activation+0.642
Top resid features:
on
Token on
Feature activation-0.012
Top resid features:
their
Token their
Feature activation-0.004
Top resid features:
way
Token way
Feature activation-0.000
Top resid features:
out
Token out
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Trump
TokenTrump
Feature activation-0.013
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
originally
Token originally
Feature activation+0.195
Top resid features:
scheduled
Token scheduled
Feature activation+1.779
Top resid features:
to
Token to
Feature activation+1.583
Top resid features:
deliver
Token deliver
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
speech
Token speech
Feature activation+0.088
Top resid features:
on
Token on
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Trump
TokenTrump
Feature activation-0.026
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
originally
Token originally
Feature activation+0.192
Top resid features:
scheduled
Token scheduled
Feature activation+1.007
Top resid features:
to
Token to
Feature activation+2.390
Top resid features:
deliver
Token deliver
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
speech
Token speech
Feature activation+0.093
Top resid features:
on
Token on
Feature activation+0.032
Top resid features:
June
Token June
Feature activation+0.017
Top resid features:
failed
Token failed
Feature activation-0.033
Top resid features:
austerity
Token austerity
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
was
Token was
Feature activation-0.006
Top resid features:
supposed
Token supposed
Feature activation+1.312
Top resid features:
to
Token to
Feature activation+2.243
Top resid features:
deliver
Token deliver
Feature activation+0.042
Top resid features:
growth
Token growth
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
but
Token but
Feature activation-0.010
Top resid features:
delivered
Token delivered
Feature activation+0.026
Top resid features:
---
Token ---
Feature activation+0.023
Top resid features:
Mic
Token Mic
Feature activation-0.025
Top resid features:
ah
Tokenah
Feature activation-0.012
Top resid features:
Rhodes
Token Rhodes
Feature activation-0.011
Top resid features:
was
Token was
Feature activation-0.090
Top resid features:
scheduled
Token scheduled
Feature activation+2.000
Top resid features:
to
Token to
Feature activation+1.509
Top resid features:
be
Token be
Feature activation+0.167
Top resid features:
on
Token on
Feature activation+0.032
Top resid features:
trial
Token trial
Feature activation+0.045
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Be
TokenBe
Feature activation+0.004
Top resid features:
ijing
Tokenijing
Feature activation-0.023
Top resid features:
had
Token had
Feature activation+0.296
Top resid features:
hoped
Token hoped
Feature activation+1.752
Top resid features:
that
Token that
Feature activation+1.083
Top resid features:
allowing
Token allowing
Feature activation-0.004
Top resid features:
Hong
Token Hong
Feature activation+0.001
Top resid features:
Kong
Token Kong
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Police
TokenPolice
Feature activation+0.006
Top resid features:
were
Token were
Feature activation+0.035
Top resid features:
hoping
Token hoping
Feature activation+2.889
Top resid features:
body
Token body
Feature activation+0.006
Top resid features:
cameras
Token cameras
Feature activation+0.019
Top resid features:
would
Token would
Feature activation+0.467
Top resid features:
shed
Token shed
Feature activation-0.066
Top resid features:
light
Token light
Feature activation-0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
data
Token data
Feature activation+0.019
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
supposed
Token supposed
Feature activation+1.449
Top resid features:
to
Token to
Feature activation+1.337
Top resid features:
be
Token be
Feature activation+0.540
Top resid features:
stored
Token stored
Feature activation+0.022
Top resid features:
on
Token on
Feature activation-0.022
Top resid features:
his
Token his
Feature activation-0.015
Top resid features:
---
Token ---
Feature activation+0.016
Top resid features:
Mic
Token Mic
Feature activation-0.015
Top resid features:
ah
Tokenah
Feature activation-0.012
Top resid features:
Rhodes
Token Rhodes
Feature activation-0.007
Top resid features:
was
Token was
Feature activation-0.041
Top resid features:
scheduled
Token scheduled
Feature activation+1.757
Top resid features:
to
Token to
Feature activation+1.263
Top resid features:
be
Token be
Feature activation+0.194
Top resid features:
on
Token on
Feature activation+0.045
Top resid features:
trial
Token trial
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
failed
Token failed
Feature activation-0.047
Top resid features:
austerity
Token austerity
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
was
Token was
Feature activation+0.021
Top resid features:
supposed
Token supposed
Feature activation+1.349
Top resid features:
to
Token to
Feature activation+1.956
Top resid features:
deliver
Token deliver
Feature activation+0.035
Top resid features:
growth
Token growth
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
but
Token but
Feature activation-0.017
Top resid features:
delivered
Token delivered
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Big
TokenBig
Feature activation+0.006
Top resid features:
things
Token things
Feature activation-0.038
Top resid features:
were
Token were
Feature activation+0.087
Top resid features:
expected
Token expected
Feature activation+2.674
Top resid features:
from
Token from
Feature activation+0.122
Top resid features:
Louisville
Token Louisville
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
Wisconsin
Token Wisconsin
Feature activation+0.028
Top resid features:
this
Token this
Feature activation+0.007
Top resid features:
rounded
Token rounded
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
I
TokenI
Feature activation+0.013
Top resid features:
was
Token was
Feature activation+0.023
Top resid features:
planning
Token planning
Feature activation+1.449
Top resid features:
on
Token on
Feature activation+1.565
Top resid features:
cutting
Token cutting
Feature activation-0.061
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
flare
Token flare
Feature activation-0.020
Top resid features:
first
Token first
Feature activation+0.007
Top resid features:
thing
Token thing
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Di
TokenDi
Feature activation+0.009
Top resid features:
Nat
Token Nat
Feature activation+0.005
Top resid features:
ale
Tokenale
Feature activation+0.015
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
planning
Token planning
Feature activation+1.471
Top resid features:
to
Token to
Feature activation+1.263
Top resid features:
move
Token move
Feature activation+0.056
Top resid features:
the
Token the
Feature activation-0.021
Top resid features:
Greens
Token Greens
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Its
Token Its
Feature activation+0.021
Top resid features:
actual
Token actual
Feature activation-0.029
Top resid features:
meaning
Token meaning
Feature activation+0.022
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
supposed
Token supposed
Feature activation+1.329
Top resid features:
to
Token to
Feature activation+1.414
Top resid features:
invoke
Token invoke
Feature activation-0.049
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
idea
Token idea
Feature activation-0.011
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
'
Token '
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Be
TokenBe
Feature activation+0.011
Top resid features:
ijing
Tokenijing
Feature activation+0.015
Top resid features:
had
Token had
Feature activation+0.265
Top resid features:
hoped
Token hoped
Feature activation+1.357
Top resid features:
that
Token that
Feature activation+0.794
Top resid features:
allowing
Token allowing
Feature activation-0.008
Top resid features:
Hong
Token Hong
Feature activation+0.004
Top resid features:
Kong
Token Kong
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
Sche
Token Sche
Feature activation+0.009
Top resid features:
ep
Tokenep
Feature activation+0.003
Top resid features:
ens
Tokenens
Feature activation-0.000
Top resid features:
had
Token had
Feature activation+0.032
Top resid features:
intended
Token intended
Feature activation+1.063
Top resid features:
to
Token to
Feature activation+1.396
Top resid features:
rese
Token rese
Feature activation-0.033
Top resid features:
ll
Tokenll
Feature activation-0.027
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
house
Token house
Feature activation+0.006
Top resid features:
after
Token after
Feature activation+0.050
Top resid features:
with
Token with
Feature activation-0.008
Top resid features:
her
Token her
Feature activation-0.001
Top resid features:
brother
Token brother
Feature activation-0.007
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
would
Token would
Feature activation+0.068
Top resid features:
normally
Token normally
Feature activation+2.697
Top resid features:
walk
Token walk
Feature activation-0.019
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
university
Token university
Feature activation+0.040
Top resid features:
with
Token with
Feature activation+0.008
Top resid features:
him
Token him
Feature activation+0.016
Top resid features:
York
Token York
Feature activation-0.002
Top resid features:
City
Token City
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
hoped
Token hoped
Feature activation+1.265
Top resid features:
that
Token that
Feature activation+0.878
Top resid features:
such
Token such
Feature activation+0.003
Top resid features:
an
Token an
Feature activation+0.003
Top resid features:
expansion
Token expansion
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.079
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.03

Head 3: 0.50

Head 4: 0.05

Head 5: 0.07

Head 6: 0.05

Head 7: 0.09

Head 8: 0.03

Head 9: 0.02

Head 10: 0.03

Head 11: 0.04

Positive logits

failed3.17

Instead3.11

alas3.06

Instead3.03

instead2.90

failed2.87

Nope2.82

fails2.69

opted2.46

iP2.44

disappoint2.41

balk2.40

nonexistent2.28

RAFT2.26

chose2.26

fal2.26

failing2.25

chers2.24

instead2.24

refused2.18

Negative logits

Cause-2.59

chy-2.42

Cortex-2.30

Attributes-2.20

Enhance-2.20

Related-2.19

Corridor-2.17

Causes-2.16

Unle-2.14

Decay-2.14

Cause-2.14

Clicker-2.11

Discuss-2.09

Amen-2.09

Lift-2.09

Finger-2.07

xx-2.04

Areas-2.03

Ü-2.02

Remy-2.01

INTERVAL 3.592 - 3.991
CONTAINS 0.000%

his
Token his
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+0.000
setting
Tokensetting
Feature activation+0.000
pace
Token pace
Feature activation+0.000
.
Token.
Feature activation+3.991
The
Token The
Feature activation+1.687
Packers
Token Packers
Feature activation+0.841
would
Token would
Feature activation+0.148
head
Token head
Feature activation+0.000
back
Token back
Feature activation+0.000

INTERVAL 3.193 - 3.592
CONTAINS 0.000%

on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.370
but
Token but
Feature activation+3.430
they
Token they
Feature activation+3.201
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fl
Token fl
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.370
but
Token but
Feature activation+3.430
they
Token they
Feature activation+3.201
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fl
Token fl
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 2.794 - 3.193
CONTAINS 0.001%

to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.238
but
Token but
Feature activation+2.466
delivered
Token delivered
Feature activation+2.839
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.277
that
Token that
Feature activation+0.083
sex
Token sex
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.169
but
Token but
Feature activation+2.538
was
Token was
Feature activation+2.830
taken
Token taken
Feature activation+0.000
away
Token away
Feature activation+0.000
in
Token in
Feature activation+0.000
handcuffs
Token handcuffs
Feature activation+0.000
before
Token before
Feature activation+0.000
speech
Token speech
Feature activation+0.174
on
Token on
Feature activation+0.081
June
Token June
Feature activation+0.294
13
Token 13
Feature activation+0.749
,
Token,
Feature activation+1.166
but
Token but
Feature activation+3.178
decided
Token decided
Feature activation+3.150
to
Token to
Feature activation+1.014
postpone
Token postpone
Feature activation+0.093
it
Token it
Feature activation+0.487
after
Token after
Feature activation+0.000
on
Token on
Feature activation+0.081
June
Token June
Feature activation+0.294
13
Token 13
Feature activation+0.749
,
Token,
Feature activation+1.166
but
Token but
Feature activation+3.178
decided
Token decided
Feature activation+3.150
to
Token to
Feature activation+1.014
postpone
Token postpone
Feature activation+0.093
it
Token it
Feature activation+0.487
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.100

INTERVAL 2.395 - 2.794
CONTAINS 0.001%

reun
Token reun
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
.
Token.
Feature activation+2.091
Ċ
TokenĊ
Feature activation+1.375
Ċ
TokenĊ
Feature activation+1.787
But
TokenBut
Feature activation+2.761
whether
Token whether
Feature activation+0.308
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.619
grants
Token grants
Feature activation+0.000
for
Token for
Feature activation+0.000
sex
Token sex
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.169
but
Token but
Feature activation+2.538
was
Token was
Feature activation+2.830
taken
Token taken
Feature activation+0.000
away
Token away
Feature activation+0.000
in
Token in
Feature activation+0.000
handcuffs
Token handcuffs
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.238
but
Token but
Feature activation+2.466
delivered
Token delivered
Feature activation+2.839
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.277
Wisconsin
Token Wisconsin
Feature activation+0.025
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.023
,
Token,
Feature activation+0.280
but
Token but
Feature activation+1.404
in
Token in
Feature activation+2.421
late
Token late
Feature activation+0.142
December
Token December
Feature activation+0.226
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
January
Token January
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
server
Token server
Feature activation+0.119
,
Token,
Feature activation+0.269
but
Token but
Feature activation+2.592
Imran
Token Imran
Feature activation+0.000
moved
Token moved
Feature activation+0.000
files
Token files
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.996 - 2.395
CONTAINS 0.001%

common
Token common
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Netherlands
Token Netherlands
Feature activation+0.000
.
Token.
Feature activation+1.278
But
Token But
Feature activation+2.034
then
Token then
Feature activation+0.389
prices
Token prices
Feature activation+0.072
t
Token t
Feature activation+0.000
umbled
Tokenumbled
Feature activation+0.000
following
Token following
Feature activation+0.000
motion
Token motion
Feature activation+0.081
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.214
afternoon
Token afternoon
Feature activation+0.799
,
Token,
Feature activation+0.625
but
Token but
Feature activation+2.318
Hanson
Token Hanson
Feature activation+0.056
got
Token got
Feature activation+1.197
there
Token there
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.000
convince
Token convince
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
.
Token.
Feature activation+2.091
Ċ
TokenĊ
Feature activation+1.375
Ċ
TokenĊ
Feature activation+1.787
But
TokenBut
Feature activation+2.761
whether
Token whether
Feature activation+0.308
or
Token or
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
and
Token and
Feature activation+0.000
recreate
Token recreate
Feature activation+0.000
--
Token--
Feature activation+0.000
but
Tokenbut
Feature activation+2.122
finding
Token finding
Feature activation+0.517
the
Token the
Feature activation+0.000
correct
Token correct
Feature activation+0.000
lex
Token lex
Feature activation+0.000
icon
Tokenicon
Feature activation+0.000
a
Token a
Feature activation+0.000
flare
Token flare
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.291
but
Token but
Feature activation+2.328
I
Token I
Feature activation+1.599
think
Token think
Feature activation+0.207
I
Token I
Feature activation+0.309
will
Token will
Feature activation+0.000
wait
Token wait
Feature activation+0.000

INTERVAL 1.596 - 1.996
CONTAINS 0.002%

flare
Token flare
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.291
but
Token but
Feature activation+2.328
I
Token I
Feature activation+1.599
think
Token think
Feature activation+0.207
I
Token I
Feature activation+0.309
will
Token will
Feature activation+0.000
wait
Token wait
Feature activation+0.000
and
Token and
Feature activation+0.000
meant
Token meant
Feature activation+0.000
to
Token to
Feature activation+0.000
silence
Token silence
Feature activation+0.000
her
Token her
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.743
she
Token she
Feature activation+0.317
vowed
Token vowed
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
campaigning
Token campaigning
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
.
Token.
Feature activation+2.091
Ċ
TokenĊ
Feature activation+1.375
Ċ
TokenĊ
Feature activation+1.787
But
TokenBut
Feature activation+2.761
whether
Token whether
Feature activation+0.308
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.619
built
Token built
Feature activation+0.000
by
Token by
Feature activation+0.000
Guardiola
Token Guardiola
Feature activation+0.218
and
Token and
Feature activation+0.281
overall
Token overall
Feature activation+0.000
it
Token it
Feature activation+1.682
appears
Token appears
Feature activation+0.555
as
Token as
Feature activation+0.000
though
Token though
Feature activation+0.000
he
Token he
Feature activation+0.822
was
Token was
Feature activation+0.250
team
Token team
Feature activation+0.000
down
Token down
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
storm
Token storm
Feature activation+0.000
.
Token.
Feature activation+1.745
They
Token They
Feature activation+1.198
were
Token were
Feature activation+1.058
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
phase
Token phase
Feature activation+0.000

INTERVAL 1.197 - 1.596
CONTAINS 0.003%

joining
Token joining
Feature activation+0.000
the
Token the
Feature activation+0.000
Special
Token Special
Feature activation+0.000
Forces
Token Forces
Feature activation+0.000
,
Token,
Feature activation+0.180
but
Token but
Feature activation+1.447
broke
Token broke
Feature activation+0.102
both
Token both
Feature activation+0.000
legs
Token legs
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
designed
Token designed
Feature activation+0.139
to
Token to
Feature activation+0.000
hit
Token hit
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.095
but
Token but
Feature activation+1.493
about
Token about
Feature activation+0.368
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.065
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.205
Wisconsin
Token Wisconsin
Feature activation+0.025
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.023
,
Token,
Feature activation+0.280
but
Token but
Feature activation+1.404
in
Token in
Feature activation+2.421
late
Token late
Feature activation+0.142
December
Token December
Feature activation+0.226
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
security
Token security
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
tr
Token tr
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
.
Token.
Feature activation+1.279
Ċ
TokenĊ
Feature activation+0.337
Ċ
TokenĊ
Feature activation+0.753
I
TokenI
Feature activation+0.530
worried
Token worried
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+0.000
's
Token's
Feature activation+0.000
editorial
Token editorial
Feature activation+0.000
independence
Token independence
Feature activation+0.000
but
Token but
Feature activation+1.298
,
Token,
Feature activation+0.772
nonetheless
Token nonetheless
Feature activation+0.498
,
Token,
Feature activation+0.077
did
Token did
Feature activation+0.400
think
Token think
Feature activation+0.050

INTERVAL 0.798 - 1.197
CONTAINS 0.011%

the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.749
in
Token in
Feature activation+1.030
fact
Token fact
Feature activation+0.823
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
er
Tokener
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
two
Token two
Feature activation+0.000
jails
Token jails
Feature activation+0.000
.
Token.
Feature activation+0.808
Ċ
TokenĊ
Feature activation+0.462
Ċ
TokenĊ
Feature activation+0.374
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.909
was
Token was
Feature activation+0.817
considered
Token considered
Feature activation+0.000
a
Token a
Feature activation+0.000
possible
Token possible
Feature activation+0.000
trade
Token trade
Feature activation+0.000
people
Token people
Feature activation+0.000
escape
Token escape
Feature activation+0.000
from
Token from
Feature activation+0.000
oppression
Token oppression
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.949
was
Token was
Feature activation+0.747
jar
Token jar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
African
Token African
Feature activation+0.000
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+0.000
community
Token community
Feature activation+0.248
,
Token,
Feature activation+0.970
she
Token she
Feature activation+1.006
could
Token could
Feature activation+0.640
not
Token not
Feature activation+0.746
have
Token have
Feature activation+0.461
done
Token done
Feature activation+0.205
a
Token a
Feature activation+0.000

INTERVAL 0.399 - 0.798
CONTAINS 0.033%

by
Token by
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
Rick
Token Rick
Feature activation+0.000
Snyder
Token Snyder
Feature activation+0.000
,
Token,
Feature activation+0.599
never
Token never
Feature activation+0.000
added
Token added
Feature activation+0.000
corrosion
Token corrosion
Feature activation+0.000
controls
Token controls
Feature activation+0.000
to
Token to
Feature activation+0.000
than
Token than
Feature activation+0.000
facts
Token facts
Feature activation+0.000
,
Token,
Feature activation+0.171
the
Token the
Feature activation+0.151
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.519
constituted
Token constituted
Feature activation+0.000
a
Token a
Feature activation+0.000
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
member
Tokenmember
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
grocery
Token grocery
Feature activation+0.000
chain
Token chain
Feature activation+0.000
was
Token was
Feature activation+0.135
really
Token really
Feature activation+0.509
about
Token about
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Wow
TokenWow
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
gamma
Token gamma
Feature activation+0.000
bomb
Token bomb
Feature activation+0.000
and
Token and
Feature activation+0.475
hold
Token hold
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
ransom
Token ransom
Feature activation+0.000
for
Token for
Feature activation+0.000
selected
Token selected
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
G
Token G
Feature activation+0.000
iro
Tokeniro
Feature activation+0.000
.
Token.
Feature activation+0.545
Most
Token Most
Feature activation+0.096
of
Token of
Feature activation+0.137
the
Token the
Feature activation+0.036
riders
Token riders
Feature activation+0.000
did
Token did
Feature activation+0.005

INTERVAL 0.000 - 0.399
CONTAINS 99.949%

a
Token a
Feature activation+0.000
virgin
Token virgin
Feature activation+0.000
birth
Token birth
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Messiah
Token Messiah
Feature activation+0.000
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
k
Tokenk
Feature activation+0.000
1
Token 1
Feature activation+0.000
:
Token:
Feature activation+0.000
sympathetic
Token sympathetic
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
.
Token.
Feature activation+0.000
Ultimately
Token Ultimately
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
enrich
Token enrich
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
rep
Token rep
Feature activation+0.000
rogram
Tokenrogram
Feature activation+0.000
med
Tokenmed
Feature activation+0.000
to
Token to
Feature activation+0.000
target
Token target
Feature activation+0.000
different
Token different
Feature activation+0.000
sites
Token sites
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+0.000
set
Token set
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
charge
Token charge
Feature activation+0.000
their
Token their
Feature activation+0.000
local
Token local
Feature activation+0.000
subsidiaries
Token subsidiaries
Feature activation+0.000
for
Token for
Feature activation+0.000
centrally
Token centrally
Feature activation+0.000
-
Token-
Feature activation+0.000
late
Token late
Feature activation+0.000
-
Token-
Feature activation+0.000
night
Tokennight
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
with
Token with
Feature activation+0.000
both
Token both
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
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 H6.3: (feature 10930)

TOP ACTIVATIONS
MAX = 6.144

of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
out
Token out
Feature activation+0.000
years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.223
some
Token some
Feature activation+0.385
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
and
Token and
Feature activation+4.724
now
Token now
Feature activation+3.487
all
Token all
Feature activation+2.584
three
Token three
Feature activation+1.858
of
Token of
Feature activation+1.537
them
Token them
Feature activation+1.895
clearing
Token clearing
Feature activation+0.000
or
Token or
Feature activation+0.000
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242
becomes
Token becomes
Feature activation+2.930
evident
Token evident
Feature activation+4.071
.
Token.
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.130
The
TokenThe
Feature activation+0.017
all
Token all
Feature activation+0.000
or
Token or
Feature activation+0.000
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
essential
Tokenessential
Feature activation+0.000
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
and
Token and
Feature activation+4.724
now
Token now
Feature activation+3.487
all
Token all
Feature activation+2.584
three
Token three
Feature activation+1.858
of
Token of
Feature activation+1.537
them
Token them
Feature activation+1.895
were
Token were
Feature activation+1.828
,
Token,
Feature activation+0.557
alcohol
Token alcohol
Feature activation+0.000
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
well
Token well
Feature activation+0.092
over
Token over
Feature activation+0.000
50
Token 50
Feature activation+0.000
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
essential
Tokenessential
Feature activation+0.000
of
Token of
Feature activation+0.000
st
Tokenst
Feature activation+0.116
birthday
Token birthday
Feature activation+0.047
(
Token (
Feature activation+0.000
November
TokenNovember
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+3.165
three
Token three
Feature activation+1.672
more
Token more
Feature activation+0.757
years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
50
Token 50
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242
becomes
Token becomes
Feature activation+2.930
evident
Token evident
Feature activation+4.071
.
Token.
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.130
The
TokenThe
Feature activation+0.017
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
well
Token well
Feature activation+0.092
over
Token over
Feature activation+0.000
add
Token add
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
and
Token and
Feature activation+2.818
I
Token I
Feature activation+2.312
think
Token think
Feature activation+1.201
you
Token you
Feature activation+1.988
have
Token have
Feature activation+0.717
got
Token got
Feature activation+0.129
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
of
Token of
Feature activation+0.000
wine
Token wine
Feature activation+0.000
and
Token and
Feature activation+2.337
some
Token some
Feature activation+0.385
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
and
Token and
Feature activation+2.818
I
Token I
Feature activation+2.312
think
Token think
Feature activation+1.201
you
Token you
Feature activation+1.988
have
Token have
Feature activation+0.717
got
Token got
Feature activation+0.129
a
Token a
Feature activation+0.000
and
Token and
Feature activation+2.337
some
Token some
Feature activation+0.385
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
and
Token and
Feature activation+4.724
now
Token now
Feature activation+3.487
all
Token all
Feature activation+2.584
three
Token three
Feature activation+1.858
of
Token of
Feature activation+1.537

Top DFA by src position
MAX = 5.663

area
Token area
Feature activation-0.005
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
default
Token default
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Mix
Token Mix
Feature activation+0.845
Top resid features:
in
Token in
Feature activation+5.554
Top resid features:
injuries
Token injuries
Feature activation+0.069
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
an
Token an
Feature activation+0.049
Top resid features:
imminent
Token imminent
Feature activation+0.008
Top resid features:
31
Token 31
Feature activation+0.033
Top resid features:
area
Token area
Feature activation-0.005
Top resid features:
by
Token by
Feature activation-0.003
Top resid features:
default
Token default
Feature activation-0.033
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Mix
Token Mix
Feature activation+0.716
Top resid features:
in
Token in
Feature activation+5.663
Top resid features:
injuries
Token injuries
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.190
Top resid features:
an
Token an
Feature activation+0.078
Top resid features:
imminent
Token imminent
Feature activation+0.023
Top resid features:
31
Token 31
Feature activation+0.039
Top resid features:
area
Token area
Feature activation-0.018
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
default
Token default
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Mix
Token Mix
Feature activation+0.274
Top resid features:
in
Token in
Feature activation+5.484
Top resid features:
injuries
Token injuries
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.140
Top resid features:
an
Token an
Feature activation+0.032
Top resid features:
imminent
Token imminent
Feature activation+0.007
Top resid features:
31
Token 31
Feature activation+0.019
Top resid features:
finish
Token finish
Feature activation-0.008
Top resid features:
off
Token off
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
day
Token day
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Add
Token Add
Feature activation+1.834
Top resid features:
a
Token a
Feature activation+0.578
Top resid features:
few
Token few
Feature activation+0.471
Top resid features:
glasses
Token glasses
Feature activation+0.053
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
wine
Token wine
Feature activation+0.052
Top resid features:
activities
Token activities
Feature activation-0.015
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
choice
Token choice
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Throw
Token Throw
Feature activation+0.094
Top resid features:
in
Token in
Feature activation+4.359
Top resid features:
an
Token an
Feature activation+0.511
Top resid features:
ancient
Token ancient
Feature activation+0.062
Top resid features:
woodland
Token woodland
Feature activation+0.001
Top resid features:
clearing
Token clearing
Feature activation-0.017
Top resid features:
or
Token or
Feature activation-0.004
Top resid features:
rapid
Token rapid
Feature activation-0.014
Top resid features:
change
Token change
Feature activation-0.038
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Combine
Token Combine
Feature activation+1.282
Top resid features:
this
Token this
Feature activation+1.165
Top resid features:
with
Token with
Feature activation+1.327
Top resid features:
an
Token an
Feature activation+0.295
Top resid features:
understanding
Token understanding
Feature activation+0.206
Top resid features:
that
Token that
Feature activation+0.131
Top resid features:
just
Token just
Feature activation+0.022
Top resid features:
10
Token 10
Feature activation+0.005
Top resid features:
activities
Token activities
Feature activation-0.013
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
choice
Token choice
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
Throw
Token Throw
Feature activation+0.328
Top resid features:
in
Token in
Feature activation+3.804
Top resid features:
an
Token an
Feature activation+0.351
Top resid features:
ancient
Token ancient
Feature activation+0.056
Top resid features:
woodland
Token woodland
Feature activation+0.033
Top resid features:
clearing
Token clearing
Feature activation-0.028
Top resid features:
or
Token or
Feature activation-0.041
Top resid features:
finish
Token finish
Feature activation-0.024
Top resid features:
off
Token off
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
day
Token day
Feature activation-0.032
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Add
Token Add
Feature activation+1.591
Top resid features:
a
Token a
Feature activation+1.025
Top resid features:
few
Token few
Feature activation+0.489
Top resid features:
glasses
Token glasses
Feature activation+0.042
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
wine
Token wine
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
5
Token5
Feature activation-0.001
Top resid features:
per
Token per
Feature activation-0.003
Top resid features:
cent
Token cent
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Add
Token Add
Feature activation+2.909
Top resid features:
H
Token H
Feature activation+0.091
Top resid features:
ST
TokenST
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.580
Top resid features:
real
Token real
Feature activation+0.083
Top resid features:
estate
Token estate
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
per
Token per
Feature activation-0.002
Top resid features:
cent
Token cent
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Add
Token Add
Feature activation+2.385
Top resid features:
H
Token H
Feature activation+0.051
Top resid features:
ST
TokenST
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.311
Top resid features:
real
Token real
Feature activation+0.030
Top resid features:
estate
Token estate
Feature activation+0.021
Top resid features:
activities
Token activities
Feature activation-0.014
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
choice
Token choice
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Throw
Token Throw
Feature activation+0.237
Top resid features:
in
Token in
Feature activation+3.384
Top resid features:
an
Token an
Feature activation+0.289
Top resid features:
ancient
Token ancient
Feature activation+0.061
Top resid features:
woodland
Token woodland
Feature activation+0.014
Top resid features:
clearing
Token clearing
Feature activation-0.035
Top resid features:
or
Token or
Feature activation-0.084
Top resid features:
area
Token area
Feature activation-0.008
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
default
Token default
Feature activation-0.035
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Mix
Token Mix
Feature activation+0.356
Top resid features:
in
Token in
Feature activation+2.860
Top resid features:
injuries
Token injuries
Feature activation+0.133
Top resid features:
,
Token,
Feature activation+0.249
Top resid features:
an
Token an
Feature activation+0.300
Top resid features:
imminent
Token imminent
Feature activation+0.071
Top resid features:
31
Token 31
Feature activation+0.143
Top resid features:
rapid
Token rapid
Feature activation-0.024
Top resid features:
change
Token change
Feature activation-0.034
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Combine
Token Combine
Feature activation+0.574
Top resid features:
this
Token this
Feature activation+1.178
Top resid features:
with
Token with
Feature activation+1.894
Top resid features:
an
Token an
Feature activation+0.225
Top resid features:
understanding
Token understanding
Feature activation+0.098
Top resid features:
that
Token that
Feature activation+0.172
Top resid features:
just
Token just
Feature activation+0.026
Top resid features:
10
Token 10
Feature activation-0.017
Top resid features:
rapid
Token rapid
Feature activation-0.008
Top resid features:
change
Token change
Feature activation-0.018
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Combine
Token Combine
Feature activation+0.853
Top resid features:
this
Token this
Feature activation+1.135
Top resid features:
with
Token with
Feature activation+1.472
Top resid features:
an
Token an
Feature activation+0.239
Top resid features:
understanding
Token understanding
Feature activation+0.113
Top resid features:
that
Token that
Feature activation+0.069
Top resid features:
just
Token just
Feature activation+0.030
Top resid features:
10
Token 10
Feature activation-0.005
Top resid features:
rapid
Token rapid
Feature activation-0.014
Top resid features:
change
Token change
Feature activation-0.041
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Combine
Token Combine
Feature activation+0.689
Top resid features:
this
Token this
Feature activation+0.849
Top resid features:
with
Token with
Feature activation+1.173
Top resid features:
an
Token an
Feature activation+0.371
Top resid features:
understanding
Token understanding
Feature activation+0.350
Top resid features:
that
Token that
Feature activation+0.091
Top resid features:
just
Token just
Feature activation+0.021
Top resid features:
10
Token 10
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
5
Token5
Feature activation-0.000
Top resid features:
per
Token per
Feature activation-0.004
Top resid features:
cent
Token cent
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Add
Token Add
Feature activation+2.224
Top resid features:
H
Token H
Feature activation+0.063
Top resid features:
ST
TokenST
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.294
Top resid features:
real
Token real
Feature activation+0.043
Top resid features:
estate
Token estate
Feature activation+0.028
Top resid features:
So
TokenSo
Feature activation-0.042
Top resid features:
OK
Token OK
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
add
Token add
Feature activation+0.289
Top resid features:
that
Token that
Feature activation+0.871
Top resid features:
to
Token to
Feature activation+1.617
Top resid features:
the
Token the
Feature activation+0.650
Top resid features:
list
Token list
Feature activation+0.529
Top resid features:
and
Token and
Feature activation+0.140
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
finish
Token finish
Feature activation-0.012
Top resid features:
off
Token off
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
day
Token day
Feature activation-0.046
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Add
Token Add
Feature activation+1.310
Top resid features:
a
Token a
Feature activation+0.801
Top resid features:
few
Token few
Feature activation+0.626
Top resid features:
glasses
Token glasses
Feature activation+0.201
Top resid features:
of
Token of
Feature activation+0.143
Top resid features:
wine
Token wine
Feature activation+0.241
Top resid features:
So
TokenSo
Feature activation-0.049
Top resid features:
OK
Token OK
Feature activation-0.029
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
add
Token add
Feature activation+0.516
Top resid features:
that
Token that
Feature activation+0.986
Top resid features:
to
Token to
Feature activation+1.070
Top resid features:
the
Token the
Feature activation+0.487
Top resid features:
list
Token list
Feature activation+0.184
Top resid features:
and
Token and
Feature activation+0.262
Top resid features:
I
Token I
Feature activation+0.023
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
finish
Token finish
Feature activation-0.012
Top resid features:
off
Token off
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
day
Token day
Feature activation-0.029
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Add
Token Add
Feature activation+0.684
Top resid features:
a
Token a
Feature activation+0.482
Top resid features:
few
Token few
Feature activation+0.494
Top resid features:
glasses
Token glasses
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+0.061
Top resid features:
wine
Token wine
Feature activation+0.020
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.03

Head 3: 0.49

Head 4: 0.03

Head 5: 0.09

Head 6: 0.05

Head 7: 0.06

Head 8: 0.04

Head 9: 0.02

Head 10: 0.03

Head 11: 0.08

Positive logits

unbeat2.34

exponentially2.16

explodes2.10

unsur2.08

astounding2.04

goose2.04

skyrocket2.03

becomes2.02

unbelievable2.00

surely1.97

whirlwind1.92

zsche1.92

incredible1.90

staggering1.90

spir1.89

mare1.89

boils1.86

vib1.85

unbelievably1.84

gulf1.84

Negative logits

Copyright-2.56

iquette-2.55

stice-2.48

osponsors-2.27

ipeg-2.18

msec-2.16

wcsstore-2.11

-2.11

autions-2.08

StreamerBot-2.07

pione-2.03

アル-2.03

DeliveryDate-2.03

-2.02

龍�-2.01

escription-2.01

-2.00

-1.99

-1.99

-1.99

INTERVAL 5.530 - 6.144
CONTAINS 0.000%

years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
out
Token out
Feature activation+0.000

INTERVAL 4.915 - 5.530
CONTAINS 0.000%

guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.179
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.223

INTERVAL 4.301 - 4.915
CONTAINS 0.000%

some
Token some
Feature activation+0.385
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
and
Token and
Feature activation+4.724
now
Token now
Feature activation+3.487
all
Token all
Feature activation+2.584
three
Token three
Feature activation+1.858
of
Token of
Feature activation+1.537
them
Token them
Feature activation+1.895

INTERVAL 3.686 - 4.301
CONTAINS 0.000%

clearing
Token clearing
Feature activation+0.000
or
Token or
Feature activation+0.000
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
or
Token or
Feature activation+0.000
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
essential
Tokenessential
Feature activation+0.000
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242
becomes
Token becomes
Feature activation+2.930
evident
Token evident
Feature activation+4.071
.
Token.
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.130
The
TokenThe
Feature activation+0.017
all
Token all
Feature activation+0.000

INTERVAL 3.072 - 3.686
CONTAINS 0.001%

,
Token,
Feature activation+0.557
alcohol
Token alcohol
Feature activation+0.000
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
well
Token well
Feature activation+0.092
over
Token over
Feature activation+0.000
50
Token 50
Feature activation+0.000
beers
Token beers
Feature activation+1.042
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+2.244
and
Token and
Feature activation+4.724
now
Token now
Feature activation+3.487
all
Token all
Feature activation+2.584
three
Token three
Feature activation+1.858
of
Token of
Feature activation+1.537
them
Token them
Feature activation+1.895
were
Token were
Feature activation+1.828
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+4.146
you
Token you
Feature activation+3.732
have
Token have
Feature activation+3.221
that
Token that
Feature activation+0.534
most
Token most
Feature activation+0.000
quint
Token quint
Feature activation+0.000
essential
Tokenessential
Feature activation+0.000
of
Token of
Feature activation+0.000
st
Tokenst
Feature activation+0.116
birthday
Token birthday
Feature activation+0.047
(
Token (
Feature activation+0.000
November
TokenNovember
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+3.165
three
Token three
Feature activation+1.672
more
Token more
Feature activation+0.757
years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000

INTERVAL 2.458 - 3.072
CONTAINS 0.001%

add
Token add
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
and
Token and
Feature activation+2.818
I
Token I
Feature activation+2.312
think
Token think
Feature activation+1.201
you
Token you
Feature activation+1.988
have
Token have
Feature activation+0.717
got
Token got
Feature activation+0.129
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.290
and
Token and
Feature activation+3.344
some
Token some
Feature activation+0.688
people
Token people
Feature activation+2.907
are
Token are
Feature activation+3.294
now
Token now
Feature activation+1.903
paying
Token paying
Feature activation+0.164
well
Token well
Feature activation+0.092
over
Token over
Feature activation+0.000
50
Token 50
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242
becomes
Token becomes
Feature activation+2.930
evident
Token evident
Feature activation+4.071
.
Token.
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.130
The
TokenThe
Feature activation+0.017

INTERVAL 1.843 - 2.458
CONTAINS 0.001%

to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
groove
Token groove
Feature activation+0.000
,
Token,
Feature activation+1.571
you
Token you
Feature activation+2.125
start
Token start
Feature activation+1.792
to
Token to
Feature activation+1.401
understand
Token understand
Feature activation+0.750
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
more
Token more
Feature activation+0.757
years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+2.181
and
Token and
Feature activation+6.008
the
Token the
Feature activation+6.144
chances
Token chances
Feature activation+5.528
of
Token of
Feature activation+1.221
hammer
Token hammer
Feature activation+0.000
of
Token of
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
on
Token on
Feature activation+0.000
transfers
Token transfers
Feature activation+0.000
and
Token and
Feature activation+1.883
wages
Token wages
Feature activation+0.113
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
decade
Token decade
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
and
Token and
Feature activation+2.818
I
Token I
Feature activation+2.312
think
Token think
Feature activation+1.201
you
Token you
Feature activation+1.988
have
Token have
Feature activation+0.717
got
Token got
Feature activation+0.129
a
Token a
Feature activation+0.000

INTERVAL 1.229 - 1.843
CONTAINS 0.002%

the
Token the
Feature activation+0.000
growth
Token growth
Feature activation+0.000
of
Token of
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.145
lead
Token lead
Feature activation+1.785
to
Token to
Feature activation+0.924
one
Token one
Feature activation+0.241
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
worlds
Token worlds
Feature activation+0.000
birthday
Token birthday
Feature activation+0.047
(
Token (
Feature activation+0.000
November
TokenNovember
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+3.165
three
Token three
Feature activation+1.672
more
Token more
Feature activation+0.757
years
Token years
Feature activation+0.120
of
Token of
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
exercise
Token exercise
Feature activation+0.000
people
Token people
Feature activation+0.041
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+1.377
he
Token he
Feature activation+1.524
found
Token found
Feature activation+1.176
that
Token that
Feature activation+0.474
only
Token only
Feature activation+0.072
those
Token those
Feature activation+0.000
world
Token world
Feature activation+0.000
building
Token building
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+1.599
the
Token the
Feature activation+0.671
most
Token most
Feature activation+0.260
annoying
Token annoying
Feature activation+0.000
part
Token part
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
continued
Token continued
Feature activation+0.000
fossil
Token fossil
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
burning
Token burning
Feature activation+0.000
,
Token,
Feature activation+1.341
both
Token both
Feature activation+1.678
the
Token the
Feature activation+0.157
present
Token present
Feature activation+0.000
level
Token level
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.614 - 1.229
CONTAINS 0.007%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242
becomes
Token becomes
Feature activation+2.930
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Carn
Token Carn
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
an
Tokenan
Feature activation+0.000
,
Token,
Feature activation+1.133
Th
Token Th
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
sh
Tokensh
Feature activation+0.475
has
Token has
Feature activation+0.726
and
Token and
Feature activation+0.358
you
Token you
Feature activation+0.596
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
get
Token get
Feature activation+0.616
a
Token a
Feature activation+0.168
third
Token third
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
growth
Token growth
Feature activation+0.000
of
Token of
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.145
lead
Token lead
Feature activation+1.785
to
Token to
Feature activation+0.924
one
Token one
Feature activation+0.241
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
worlds
Token worlds
Feature activation+0.000
largest
Token largest
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.071
the
Token the
Feature activation+3.026
rate
Token rate
Feature activation+2.089
and
Token and
Feature activation+0.654
scope
Token scope
Feature activation+1.159
of
Token of
Feature activation+0.621
what
Token what
Feature activation+0.532
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.242

INTERVAL 0.000 - 0.614
CONTAINS 99.988%

sal
Tokensal
Feature activation+0.000
vation
Tokenvation
Feature activation+0.000
Account
Token Account
Feature activation+0.000
:
Token:
Feature activation+0.000
St
Token St
Feature activation+0.000
air
Tokenair
Feature activation+0.000
c
Tokenc
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
reversed
Token reversed
Feature activation+0.000
course
Token course
Feature activation+0.000
on
Token on
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
investments
Token investments
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
near
Token near
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
fold
Tokenfold
Feature activation+0.000
increase
Token increase
Feature activation+0.000
cruel
Token cruel
Feature activation+0.000
and
Token and
Feature activation+0.000
greedy
Token greedy
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
,
Token,
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
particip
Token particip
Feature activation+0.000
atory
Tokenatory
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
civic
Token civic
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
drafting
Token drafting
Feature activation+0.000
language
Token language
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
recess
Token recess
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
drive
Token drive
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 H6.3: (feature 10922)

TOP ACTIVATIONS
MAX = 6.044

have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.356
when
Token when
Feature activation+4.746
really
Token really
Feature activation+6.044
we
Token we
Feature activation+1.263
have
Token have
Feature activation+1.156
not
Token not
Feature activation+1.467
.
Token.
Feature activation+0.563
Ċ
TokenĊ
Feature activation+0.000
it
Token it
Feature activation+0.001
hits
Token hits
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+1.926
In
Token In
Feature activation+3.147
reality
Token reality
Feature activation+4.844
,
Token,
Feature activation+1.032
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.356
when
Token when
Feature activation+4.746
really
Token really
Feature activation+6.044
we
Token we
Feature activation+1.263
have
Token have
Feature activation+1.156
not
Token not
Feature activation+1.467
.
Token.
Feature activation+0.563
serving
Token serving
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
handled
Token handled
Feature activation+0.000
divorce
Token divorce
Feature activation+0.000
.
Token.
Feature activation+1.995
Ċ
TokenĊ
Feature activation+0.967
Ċ
TokenĊ
Feature activation+1.336
In
TokenIn
Feature activation+2.676
fact
Token fact
Feature activation+4.301
,
Token,
Feature activation+1.645
the
Token the
Feature activation+0.327
figures
Token figures
Feature activation+0.345
are
Token are
Feature activation+0.361
significantly
Token significantly
Feature activation+0.000
its
Token its
Feature activation+0.000
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
handled
Token handled
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
er
Tokener
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.400
this
Token this
Feature activation+0.006
,
Token,
Feature activation+0.959
but
Token but
Feature activation+3.917
are
Token are
Feature activation+3.135
you
Token you
Feature activation+0.808
sure
Token sure
Feature activation+0.072
?
Token?
Feature activation+0.115
You
Token You
Feature activation+0.000
're
Token're
Feature activation+0.000
just
Token just
Feature activation+0.318
playing
Token playing
Feature activation+0.000
around
Token around
Feature activation+0.000
,
Token,
Feature activation+1.512
but
Token but
Feature activation+3.776
then
Token then
Feature activation+3.281
you
Token you
Feature activation+1.689
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.607
are
Token are
Feature activation+0.047
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
masterpiece
Token masterpiece
Feature activation+0.000
,
Token,
Feature activation+0.963
but
Token but
Feature activation+3.756
when
Token when
Feature activation+3.166
you
Token you
Feature activation+1.677
get
Token get
Feature activation+1.051
sober
Token sober
Feature activation+0.101
you
Token you
Feature activation+0.000
had
Token had
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
color
Token color
Feature activation+0.000
change
Token change
Feature activation+0.150
when
Token when
Feature activation+2.554
,
Token,
Feature activation+1.769
in
Token in
Feature activation+1.783
fact
Token fact
Feature activation+3.432
,
Token,
Feature activation+1.937
it
Token it
Feature activation+0.937
was
Token was
Feature activation+0.282
biased
Token biased
Feature activation+0.057
by
Token by
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
re
Token re
Feature activation+0.000
forestation
Tokenforestation
Feature activation+0.000
programs
Token programs
Feature activation+0.000
.
Token.
Feature activation+1.677
But
Token But
Feature activation+3.420
these
Token these
Feature activation+2.020
programs
Token programs
Feature activation+0.508
are
Token are
Feature activation+1.612
problematic
Token problematic
Feature activation+0.083
in
Token in
Feature activation+0.018
just
Token just
Feature activation+0.318
playing
Token playing
Feature activation+0.000
around
Token around
Feature activation+0.000
,
Token,
Feature activation+1.512
but
Token but
Feature activation+3.776
then
Token then
Feature activation+3.281
you
Token you
Feature activation+1.689
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.607
involved
Token involved
Feature activation+0.073
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
masterpiece
Token masterpiece
Feature activation+0.000
,
Token,
Feature activation+0.963
but
Token but
Feature activation+3.756
when
Token when
Feature activation+3.166
you
Token you
Feature activation+1.677
get
Token get
Feature activation+1.051
sober
Token sober
Feature activation+0.101
you
Token you
Feature activation+0.000
realize
Token realize
Feature activation+0.239
when
Token when
Feature activation+0.004
it
Token it
Feature activation+0.001
hits
Token hits
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+1.926
In
Token In
Feature activation+3.147
reality
Token reality
Feature activation+4.844
,
Token,
Feature activation+1.032
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.400
this
Token this
Feature activation+0.006
,
Token,
Feature activation+0.959
but
Token but
Feature activation+3.917
are
Token are
Feature activation+3.135
you
Token you
Feature activation+0.808
sure
Token sure
Feature activation+0.072
?
Token?
Feature activation+0.115
You
Token You
Feature activation+0.000
may
Token may
Feature activation+0.188
new
Token new
Feature activation+0.000
gold
Token gold
Feature activation+0.000
standard
Token standard
Feature activation+0.000
.
Token.
Feature activation+0.116
In
Token In
Feature activation+1.038
truth
Token truth
Feature activation+3.077
,
Token,
Feature activation+0.224
it
Token it
Feature activation+0.228
was
Token was
Feature activation+0.384
a
Token a
Feature activation+0.148
dollar
Token dollar
Feature activation+0.000

Top DFA by src position
MAX = 5.940

easy
Token easy
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
del
Token del
Feature activation+0.004
Top resid features:
ude
Tokenude
Feature activation+0.042
Top resid features:
ourselves
Token ourselves
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+5.940
Top resid features:
we
Token we
Feature activation+0.431
Top resid features:
have
Token have
Feature activation+0.018
Top resid features:
found
Token found
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
truth
Token truth
Feature activation-0.004
Top resid features:
robot
Token robot
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
Most
Token Most
Feature activation+0.016
Top resid features:
people
Token people
Feature activation+0.023
Top resid features:
think
Token think
Feature activation+4.636
Top resid features:
a
Token a
Feature activation+0.032
Top resid features:
collaborative
Token collaborative
Feature activation-0.005
Top resid features:
robot
Token robot
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.061
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
easy
Token easy
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
del
Token del
Feature activation+0.005
Top resid features:
ude
Tokenude
Feature activation+0.050
Top resid features:
ourselves
Token ourselves
Feature activation+0.079
Top resid features:
that
Token that
Feature activation+4.326
Top resid features:
we
Token we
Feature activation+0.622
Top resid features:
have
Token have
Feature activation+0.035
Top resid features:
found
Token found
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
truth
Token truth
Feature activation-0.011
Top resid features:
led
Token led
Feature activation-0.003
Top resid features:
many
Token many
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.019
Top resid features:
falsely
Token falsely
Feature activation+0.219
Top resid features:
believe
Token believe
Feature activation+1.986
Top resid features:
that
Token that
Feature activation+2.885
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
company
Token company
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.056
Top resid features:
serving
Token serving
Feature activation+0.015
Top resid features:
as
Token as
Feature activation-0.007
Top resid features:
Sky
Token Sky
Feature activation+0.002
Top resid features:
led
Token led
Feature activation+0.001
Top resid features:
many
Token many
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
falsely
Token falsely
Feature activation+0.274
Top resid features:
believe
Token believe
Feature activation+2.502
Top resid features:
that
Token that
Feature activation+2.339
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
company
Token company
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.027
Top resid features:
serving
Token serving
Feature activation+0.009
Top resid features:
this
Token this
Feature activation-0.003
Top resid features:
persistent
Token persistent
Feature activation-0.008
Top resid features:
myth
Token myth
Feature activation+0.315
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
America
Token America
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+4.216
Top resid features:
about
Token about
Feature activation+0.035
Top resid features:
half
Token half
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
all
Token all
Feature activation+0.007
Top resid features:
marriages
Token marriages
Feature activation+0.009
Top resid features:
Sky
Token Sky
Feature activation+0.001
Top resid features:
led
Token led
Feature activation-0.000
Top resid features:
many
Token many
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
falsely
Token falsely
Feature activation+0.180
Top resid features:
believe
Token believe
Feature activation+2.556
Top resid features:
that
Token that
Feature activation+1.546
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
company
Token company
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.056
Top resid features:
serving
Token serving
Feature activation+0.008
Top resid features:
ammed
Tokenammed
Feature activation-0.007
Top resid features:
up
Token up
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
I
Token I
Feature activation-0.007
Top resid features:
falsely
Token falsely
Feature activation+0.050
Top resid features:
believed
Token believed
Feature activation+2.297
Top resid features:
I
Token I
Feature activation+1.605
Top resid features:
had
Token had
Feature activation+0.227
Top resid features:
won
Token won
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
battle
Token battle
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
You
TokenYou
Feature activation+0.012
Top resid features:
may
Token may
Feature activation-0.009
Top resid features:
think
Token think
Feature activation+1.348
Top resid features:
you
Token you
Feature activation+2.805
Top resid features:
have
Token have
Feature activation+0.236
Top resid features:
never
Token never
Feature activation-0.040
Top resid features:
experienced
Token experienced
Feature activation+0.028
Top resid features:
this
Token this
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
do
Token do
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
You
Token You
Feature activation+0.011
Top resid features:
may
Token may
Feature activation+0.005
Top resid features:
think
Token think
Feature activation+1.840
Top resid features:
you
Token you
Feature activation+1.800
Top resid features:
're
Token're
Feature activation+0.485
Top resid features:
just
Token just
Feature activation+0.061
Top resid features:
playing
Token playing
Feature activation+0.022
Top resid features:
around
Token around
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
criticism
Token criticism
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
You
Token You
Feature activation+0.023
Top resid features:
think
Token think
Feature activation+1.511
Top resid features:
you
Token you
Feature activation+2.304
Top resid features:
are
Token are
Feature activation+0.266
Top resid features:
creating
Token creating
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
masterpiece
Token masterpiece
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
falsely
Token falsely
Feature activation+0.149
Top resid features:
believed
Token believed
Feature activation+1.446
Top resid features:
I
Token I
Feature activation+2.154
Top resid features:
had
Token had
Feature activation+0.150
Top resid features:
won
Token won
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
battle
Token battle
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
ammed
Tokenammed
Feature activation-0.003
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
I
Token I
Feature activation-0.007
Top resid features:
falsely
Token falsely
Feature activation+0.111
Top resid features:
believed
Token believed
Feature activation+1.975
Top resid features:
I
Token I
Feature activation+1.602
Top resid features:
had
Token had
Feature activation+0.150
Top resid features:
won
Token won
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
battle
Token battle
Feature activation+0.037
Top resid features:
awareness
Token awareness
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
creating
Token creating
Feature activation-0.013
Top resid features:
an
Token an
Feature activation+0.004
Top resid features:
illusion
Token illusion
Feature activation+0.754
Top resid features:
that
Token that
Feature activation+2.966
Top resid features:
a
Token a
Feature activation+0.085
Top resid features:
choice
Token choice
Feature activation-0.003
Top resid features:
had
Token had
Feature activation+0.014
Top resid features:
preceded
Token preceded
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
industry
Token industry
Feature activation-0.008
Top resid features:
claims
Token claims
Feature activation+2.066
Top resid features:
to
Token to
Feature activation+1.665
Top resid features:
encourage
Token encourage
Feature activation+0.051
Top resid features:
re
Token re
Feature activation+0.002
Top resid features:
forestation
Tokenforestation
Feature activation+0.041
Top resid features:
programs
Token programs
Feature activation+0.043
Top resid features:
do
Token do
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
You
Token You
Feature activation+0.007
Top resid features:
may
Token may
Feature activation-0.020
Top resid features:
think
Token think
Feature activation+1.517
Top resid features:
you
Token you
Feature activation+1.741
Top resid features:
're
Token're
Feature activation+0.370
Top resid features:
just
Token just
Feature activation+0.038
Top resid features:
playing
Token playing
Feature activation+0.007
Top resid features:
around
Token around
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
criticism
Token criticism
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
You
Token You
Feature activation+0.016
Top resid features:
think
Token think
Feature activation+1.456
Top resid features:
you
Token you
Feature activation+1.839
Top resid features:
are
Token are
Feature activation+0.161
Top resid features:
creating
Token creating
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
masterpiece
Token masterpiece
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
robot
Token robot
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Most
Token Most
Feature activation+0.043
Top resid features:
people
Token people
Feature activation+0.078
Top resid features:
think
Token think
Feature activation+2.846
Top resid features:
a
Token a
Feature activation+0.057
Top resid features:
collaborative
Token collaborative
Feature activation-0.005
Top resid features:
robot
Token robot
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.086
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
You
TokenYou
Feature activation+0.007
Top resid features:
may
Token may
Feature activation-0.003
Top resid features:
think
Token think
Feature activation+0.370
Top resid features:
you
Token you
Feature activation+2.976
Top resid features:
have
Token have
Feature activation+0.270
Top resid features:
never
Token never
Feature activation-0.028
Top resid features:
experienced
Token experienced
Feature activation+0.001
Top resid features:
this
Token this
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
drafted
Token drafted
Feature activation-0.021
Top resid features:
what
Token what
Feature activation-0.062
Top resid features:
many
Token many
Feature activation+0.005
Top resid features:
mistakenly
Token mistakenly
Feature activation+0.194
Top resid features:
believe
Token believe
Feature activation+2.686
Top resid features:
was
Token was
Feature activation+0.585
Top resid features:
a
Token a
Feature activation+0.090
Top resid features:
new
Token new
Feature activation-0.008
Top resid features:
gold
Token gold
Feature activation-0.005
Top resid features:
standard
Token standard
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.04

Head 3: 0.47

Head 4: 0.05

Head 5: 0.08

Head 6: 0.05

Head 7: 0.10

Head 8: 0.03

Head 9: 0.01

Head 10: 0.02

Head 11: 0.05

Positive logits

reality3.32

Nope2.91

ignores2.91

reality2.88

Fraud2.78

truth2.71

fails2.63

actually2.61

Reality2.59

Wr2.55

wrongly2.55

onsense2.52

actually2.52

Wrong2.45

false2.45

mistakenly2.43

misleading2.40

Turns2.39

ALSE2.39

claim2.37

Negative logits

Likes-2.54

Torrent-2.46

Banner-2.31

Archdemon-2.30

Eyes-2.20

iaries-2.12

entin-2.09

cellaneous-2.09

Decay-2.08

warr-2.07

-2.06

Clash-2.05

chy-2.04

Ports-2.01

reusable-2.01

orough-1.99

Interested-1.98

ngth-1.97

Gentle-1.97

ipation-1.96

INTERVAL 5.440 - 6.044
CONTAINS 0.000%

have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.356
when
Token when
Feature activation+4.746
really
Token really
Feature activation+6.044
we
Token we
Feature activation+1.263
have
Token have
Feature activation+1.156
not
Token not
Feature activation+1.467
.
Token.
Feature activation+0.563
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 4.835 - 5.440
CONTAINS 0.000%

it
Token it
Feature activation+0.001
hits
Token hits
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+1.926
In
Token In
Feature activation+3.147
reality
Token reality
Feature activation+4.844
,
Token,
Feature activation+1.032
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 4.231 - 4.835
CONTAINS 0.000%

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.356
when
Token when
Feature activation+4.746
really
Token really
Feature activation+6.044
we
Token we
Feature activation+1.263
have
Token have
Feature activation+1.156
not
Token not
Feature activation+1.467
.
Token.
Feature activation+0.563
serving
Token serving
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
handled
Token handled
Feature activation+0.000
divorce
Token divorce
Feature activation+0.000
.
Token.
Feature activation+1.995
Ċ
TokenĊ
Feature activation+0.967
Ċ
TokenĊ
Feature activation+1.336
In
TokenIn
Feature activation+2.676
fact
Token fact
Feature activation+4.301
,
Token,
Feature activation+1.645
the
Token the
Feature activation+0.327
figures
Token figures
Feature activation+0.345
are
Token are
Feature activation+0.361
significantly
Token significantly
Feature activation+0.000

INTERVAL 3.626 - 4.231
CONTAINS 0.001%

are
Token are
Feature activation+0.047
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
masterpiece
Token masterpiece
Feature activation+0.000
,
Token,
Feature activation+0.963
but
Token but
Feature activation+3.756
when
Token when
Feature activation+3.166
you
Token you
Feature activation+1.677
get
Token get
Feature activation+1.051
sober
Token sober
Feature activation+0.101
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
just
Token just
Feature activation+0.318
playing
Token playing
Feature activation+0.000
around
Token around
Feature activation+0.000
,
Token,
Feature activation+1.512
but
Token but
Feature activation+3.776
then
Token then
Feature activation+3.281
you
Token you
Feature activation+1.689
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.607
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
er
Tokener
Feature activation+0.000
had
Token had
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.400
this
Token this
Feature activation+0.006
,
Token,
Feature activation+0.959
but
Token but
Feature activation+3.917
are
Token are
Feature activation+3.135
you
Token you
Feature activation+0.808
sure
Token sure
Feature activation+0.072
?
Token?
Feature activation+0.115
You
Token You
Feature activation+0.000

INTERVAL 3.022 - 3.626
CONTAINS 0.001%

won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
,
Token,
Feature activation+1.091
when
Token when
Feature activation+3.684
in
Token in
Feature activation+3.461
fact
Token fact
Feature activation+3.971
she
Token she
Feature activation+0.166
had
Token had
Feature activation+0.622
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
when
Token when
Feature activation+0.004
it
Token it
Feature activation+0.001
hits
Token hits
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+1.926
In
Token In
Feature activation+3.147
reality
Token reality
Feature activation+4.844
,
Token,
Feature activation+1.032
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.400
this
Token this
Feature activation+0.006
,
Token,
Feature activation+0.959
but
Token but
Feature activation+3.917
are
Token are
Feature activation+3.135
you
Token you
Feature activation+0.808
sure
Token sure
Feature activation+0.072
?
Token?
Feature activation+0.115
You
Token You
Feature activation+0.000
may
Token may
Feature activation+0.188
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
masterpiece
Token masterpiece
Feature activation+0.000
,
Token,
Feature activation+0.963
but
Token but
Feature activation+3.756
when
Token when
Feature activation+3.166
you
Token you
Feature activation+1.677
get
Token get
Feature activation+1.051
sober
Token sober
Feature activation+0.101
you
Token you
Feature activation+0.000
realize
Token realize
Feature activation+0.239
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+1.753
when
Token when
Feature activation+4.726
in
Token in
Feature activation+4.725
actual
Token actual
Feature activation+4.021
ity
Tokenity
Feature activation+3.062
Hello
Token Hello
Feature activation+0.000
Games
Token Games
Feature activation+0.000
handled
Token handled
Feature activation+0.000
the
Token the
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.000

INTERVAL 2.418 - 3.022
CONTAINS 0.002%

class
Token class
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
.
Token.
Feature activation+1.621
âĢ
TokenâĢ
Feature activation+0.218
Ŀ
TokenĿ
Feature activation+0.203
In
Token In
Feature activation+3.008
a
Token a
Feature activation+1.064
speech
Token speech
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
actual
Token actual
Feature activation+0.846
biological
Token biological
Feature activation+0.000
sex
Token sex
Feature activation+0.005
,
Token,
Feature activation+0.184
even
Token even
Feature activation+0.770
when
Token when
Feature activation+2.431
people
Token people
Feature activation+1.171
can
Token can
Feature activation+0.519
see
Token see
Feature activation+0.242
they
Token they
Feature activation+0.188
are
Token are
Feature activation+0.224
will
Token will
Feature activation+0.000
investigate
Token investigate
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.348
but
Token but
Feature activation+2.977
that
Token that
Feature activation+1.418
is
Token is
Feature activation+2.205
not
Token not
Feature activation+1.803
good
Token good
Feature activation+0.261
enough
Token enough
Feature activation+0.168
had
Token had
Feature activation+0.000
preceded
Token preceded
Feature activation+0.000
the
Token the
Feature activation+0.093
color
Token color
Feature activation+0.000
change
Token change
Feature activation+0.150
when
Token when
Feature activation+2.554
,
Token,
Feature activation+1.769
in
Token in
Feature activation+1.783
fact
Token fact
Feature activation+3.432
,
Token,
Feature activation+1.937
it
Token it
Feature activation+0.937
mathematics
Token mathematics
Feature activation+0.000
(
Token (
Feature activation+0.000
STEM
TokenSTEM
Feature activation+0.000
)
Token)
Feature activation+0.000
fields
Token fields
Feature activation+0.000
.
Token.
Feature activation+2.841
The
Token The
Feature activation+2.060
false
Token false
Feature activation+1.301
claims
Token claims
Feature activation+0.766
are
Token are
Feature activation+1.732
examples
Token examples
Feature activation+0.604

INTERVAL 1.813 - 2.418
CONTAINS 0.005%

BBC
Token BBC
Feature activation+0.000
's
Token's
Feature activation+0.000
editorial
Token editorial
Feature activation+0.000
independence
Token independence
Feature activation+0.000
but
Token but
Feature activation+2.847
,
Token,
Feature activation+1.883
nonetheless
Token nonetheless
Feature activation+1.380
,
Token,
Feature activation+0.948
did
Token did
Feature activation+1.355
think
Token think
Feature activation+0.504
it
Token it
Feature activation+0.386
Hunts
Token Hunts
Feature activation+0.000
man
Tokenman
Feature activation+0.000
said
Token said
Feature activation+0.135
.
Token.
Feature activation+0.482
"
Token "
Feature activation+1.398
But
TokenBut
Feature activation+1.954
these
Token these
Feature activation+0.410
people
Token people
Feature activation+0.220
aren
Token aren
Feature activation+1.011
't
Token't
Feature activation+0.359
seeing
Token seeing
Feature activation+0.104
stop
Token stop
Feature activation+0.000
when
Token when
Feature activation+0.004
it
Token it
Feature activation+0.001
hits
Token hits
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+1.926
In
Token In
Feature activation+3.147
reality
Token reality
Feature activation+4.844
,
Token,
Feature activation+1.032
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
billion
Token billion
Feature activation+0.087
in
Token in
Feature activation+0.307
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
decade
Token decade
Feature activation+0.000
.
Token.
Feature activation+2.154
A
Token A
Feature activation+0.772
iding
Tokeniding
Feature activation+0.000
and
Token and
Feature activation+0.000
ab
Token ab
Feature activation+0.000
etting
Tokenetting
Feature activation+0.000
change
Token change
Feature activation+0.150
when
Token when
Feature activation+2.554
,
Token,
Feature activation+1.769
in
Token in
Feature activation+1.783
fact
Token fact
Feature activation+3.432
,
Token,
Feature activation+1.937
it
Token it
Feature activation+0.937
was
Token was
Feature activation+0.282
biased
Token biased
Feature activation+0.057
by
Token by
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.209 - 1.813
CONTAINS 0.017%

may
Token may
Feature activation+0.000
seem
Token seem
Feature activation+0.000
overwhelming
Token overwhelming
Feature activation+0.000
to
Token to
Feature activation+0.000
beginners
Token beginners
Feature activation+0.000
but
Token but
Feature activation+1.348
it
Token it
Feature activation+0.949
's
Token's
Feature activation+1.067
really
Token really
Feature activation+1.190
not
Token not
Feature activation+0.493
that
Token that
Feature activation+0.000
in
Token in
Feature activation+0.000
malware
Token malware
Feature activation+0.000
may
Token may
Feature activation+0.000
sound
Token sound
Feature activation+0.000
frightening
Token frightening
Feature activation+0.000
,
Token,
Feature activation+1.210
it
Token it
Feature activation+1.784
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
noted
Token noted
Feature activation+0.050
that
Token that
Feature activation+0.231
a
Token a
Feature activation+0.000
shutdown
Token shutdown
Feature activation+0.000
option
Token option
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.623
,
Token,
Feature activation+1.610
there
Token there
Feature activation+0.490
are
Token are
Feature activation+0.006
some
Token some
Feature activation+0.000
troubling
Token troubling
Feature activation+0.000
signs
Token signs
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
as
Token as
Feature activation+0.000
described
Token described
Feature activation+0.000
but
Token but
Feature activation+1.520
when
Token when
Feature activation+1.630
Mike
Token Mike
Feature activation+0.291
tried
Token tried
Feature activation+0.269
to
Token to
Feature activation+0.025
fire
Token fire
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
identity
Token identity
Feature activation+0.000
.
Token.
Feature activation+1.015
Ċ
TokenĊ
Feature activation+0.905
Ċ
TokenĊ
Feature activation+1.655
Lisa
TokenLisa
Feature activation+0.000
Diamond
Token Diamond
Feature activation+0.000
has
Token has
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
some
Token some
Feature activation+0.000

INTERVAL 0.604 - 1.209
CONTAINS 0.061%

revolution
Token revolution
Feature activation+0.000
and
Token and
Feature activation+0.071
these
Token these
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
statements
Token statements
Feature activation+0.000
--
Token --
Feature activation+0.623
when
Token when
Feature activation+0.726
I
Token I
Feature activation+0.019
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
class
Token class
Feature activation+0.000
children
Token children
Feature activation+0.000
of
Token of
Feature activation+0.000
color
Token color
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
.
Token.
Feature activation+0.810
It
Token It
Feature activation+1.427
was
Token was
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.064
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
protective
Token protective
Feature activation+0.000
component
Token component
Feature activation+0.068
,
Token,
Feature activation+0.747
which
Token which
Feature activation+0.933
normally
Token normally
Feature activation+0.842
also
Token also
Feature activation+0.241
provides
Token provides
Feature activation+0.000
some
Token some
Feature activation+0.000
padding
Token padding
Feature activation+0.000
.
Token.
Feature activation+0.536
argument
Token argument
Feature activation+0.000
goes
Token goes
Feature activation+0.000
.
Token.
Feature activation+0.385
Ċ
TokenĊ
Feature activation+0.364
Ċ
TokenĊ
Feature activation+0.586
I
TokenI
Feature activation+1.026
agree
Token agree
Feature activation+0.305
with
Token with
Feature activation+0.000
this
Token this
Feature activation+0.000
argument
Token argument
Feature activation+0.000
in
Token in
Feature activation+0.000
in
Token in
Feature activation+0.000
September
Token September
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.722
We
TokenWe
Feature activation+0.838
didn
Token didn
Feature activation+0.691
't
Token't
Feature activation+0.747
expect
Token expect
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
escalate
Token escalate
Feature activation+0.000

INTERVAL 0.000 - 0.604
CONTAINS 99.915%

def
Token def
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
is
Token is
Feature activation+0.000
displayed
Token displayed
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
club
Token club
Feature activation+0.000
building
Token building
Feature activation+0.000
which
Token which
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
building
Token building
Feature activation+0.000
a
Token a
Feature activation+0.000
demo
Token demo
Feature activation+0.000
app
Token app
Feature activation+0.000
called
Token called
Feature activation+0.000
Attend
Token Attend
Feature activation+0.000
ance
Tokenance
Feature activation+0.000
App
Token App
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Lives
Token Lives
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
network
Token network
Feature activation+0.000
of
Token of
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Lives
Token Lives
Feature activation+0.000
Matter
Token Matter
Feature activation+0.000
organizers
Token organizers
Feature activation+0.000
,
Token,
Feature activation+0.000
missions
Tokenmissions
Feature activation+0.000
Test
Token Test
Feature activation+0.000
scores
Token scores
Feature activation+0.000
and
Token and
Feature activation+0.000
undergraduate
Token undergraduate
Feature activation+0.000
Grade
Token Grade
Feature activation+0.000
Point
Token Point
Feature activation+0.000
A
Token A
Feature activation+0.000
verages
Tokenverages
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
missionary
Token missionary
Feature activation+0.000
arm
Token arm
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Evangel
Token Evangel
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
Free
Token Free
Feature activation+0.000
Church
Token Church
Feature activation+0.000
of
Token of
Feature activation+0.000
America
Token America
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 H6.3: (feature 15225)

TOP ACTIVATIONS
MAX = 7.330

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
,
Token,
Feature activation+4.360
we
Token we
Feature activation+7.330
âĢ
TokenâĢ
Feature activation+3.108
Ļ
TokenĻ
Feature activation+0.364
ve
Tokenve
Feature activation+0.147
actually
Token actually
Feature activation+1.738
discovered
Token discovered
Feature activation+0.419
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
divorce
Token divorce
Feature activation+0.538
laws
Token laws
Feature activation+0.710
.
Token.
Feature activation+6.483
It
Token It
Feature activation+5.416
âĢ
TokenâĢ
Feature activation+2.415
Ļ
TokenĻ
Feature activation+0.273
s
Tokens
Feature activation+4.221
also
Token also
Feature activation+1.527
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
get
Token get
Feature activation+0.000
by
Token by
Feature activation+0.000
--
Token --
Feature activation+2.292
you
Token you
Feature activation+6.048
can
Token can
Feature activation+3.875
get
Token get
Feature activation+2.817
ahead
Token ahead
Feature activation+0.000
.
Token.
Feature activation+1.086
And
Token And
Feature activation+0.076
land
Token land
Feature activation+0.000
you
Token you
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+5.610
You
Token You
Feature activation+4.188
can
Token can
Feature activation+1.124
also
Token also
Feature activation+0.467
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
ics
Tokenics
Feature activation+0.000
and
Token and
Feature activation+1.120
wild
Token wild
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.340
âĢĵ
Token âĢĵ
Feature activation+5.526
it
Token it
Feature activation+5.189
aims
Token aims
Feature activation+3.304
to
Token to
Feature activation+1.369
convey
Token convey
Feature activation+0.177
a
Token a
Feature activation+0.243
just
Token just
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
divorce
Token divorce
Feature activation+0.538
laws
Token laws
Feature activation+0.710
.
Token.
Feature activation+6.483
It
Token It
Feature activation+5.416
âĢ
TokenâĢ
Feature activation+2.415
Ļ
TokenĻ
Feature activation+0.273
s
Tokens
Feature activation+4.221
also
Token also
Feature activation+1.527
the
Token the
Feature activation+0.000
intellectual
Token intellectual
Feature activation+0.000
ghetto
Token ghetto
Feature activation+0.552
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.814
âĢĶ
TokenâĢĶ
Feature activation+5.256
the
Tokenthe
Feature activation+4.727
book
Token book
Feature activation+0.413
came
Token came
Feature activation+1.076
within
Token within
Feature activation+0.000
one
Token one
Feature activation+0.000
as
Token as
Feature activation+0.224
purely
Token purely
Feature activation+0.000
transit
Token transit
Feature activation+0.000
projects
Token projects
Feature activation+0.689
,
Token,
Feature activation+2.392
you
Token you
Feature activation+5.195
've
Token've
Feature activation+4.391
got
Token got
Feature activation+3.753
to
Token to
Feature activation+3.247
look
Token look
Feature activation+0.430
at
Token at
Feature activation+0.858
and
Token and
Feature activation+1.120
wild
Token wild
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.340
âĢĵ
Token âĢĵ
Feature activation+5.526
it
Token it
Feature activation+5.189
aims
Token aims
Feature activation+3.304
to
Token to
Feature activation+1.369
convey
Token convey
Feature activation+0.177
a
Token a
Feature activation+0.243
deeper
Token deeper
Feature activation+0.000
there
Token there
Feature activation+0.000
for
Token for
Feature activation+0.000
show
Token show
Feature activation+0.000
,
Token,
Feature activation+3.586
though
Token though
Feature activation+0.319
;
Token;
Feature activation+5.054
many
Token many
Feature activation+1.009
of
Token of
Feature activation+0.139
them
Token them
Feature activation+0.677
offer
Token offer
Feature activation+0.100
you
Token you
Feature activation+0.000
chasing
Token chasing
Feature activation+0.000
an
Token an
Feature activation+0.000
advantageous
Token advantageous
Feature activation+0.000
narrative
Token narrative
Feature activation+0.000
.
Token.
Feature activation+2.740
He
Token He
Feature activation+5.024
genuinely
Token genuinely
Feature activation+1.634
believes
Token believes
Feature activation+0.887
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
is
Token is
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
client
Token client
Feature activation+0.000
and
Token and
Feature activation+1.187
attorney
Token attorney
Feature activation+0.000
.
Token.
Feature activation+4.947
The
Token The
Feature activation+1.978
two
Token two
Feature activation+0.615
were
Token were
Feature activation+1.949
joined
Token joined
Feature activation+0.000
at
Token at
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
play
Token play
Feature activation+0.000
.
Token.
Feature activation+4.904
Live
Token Live
Feature activation+0.197
the
Token the
Feature activation+0.054
game
Token game
Feature activation+0.000
-
Token -
Feature activation+1.089
From
TokenFrom
Feature activation+0.595
"
Token "
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
competitive
Token competitive
Feature activation+0.000
",
Token",
Feature activation+3.203
there
Token there
Feature activation+4.747
's
Token's
Feature activation+3.304
belief
Token belief
Feature activation+2.165
the
Token the
Feature activation+1.385
Heat
Token Heat
Feature activation+0.000
can
Token can
Feature activation+0.225
ghetto
Token ghetto
Feature activation+0.552
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.814
âĢĶ
TokenâĢĶ
Feature activation+5.256
the
Tokenthe
Feature activation+4.727
book
Token book
Feature activation+0.413
came
Token came
Feature activation+1.076
within
Token within
Feature activation+0.000
one
Token one
Feature activation+0.000
tick
Token tick
Feature activation+0.000
any
Token any
Feature activation+0.000
known
Token known
Feature activation+0.000
economic
Token economic
Feature activation+0.000
theories
Token theories
Feature activation+0.000
,
Token,
Feature activation+1.553
they
Token they
Feature activation+4.670
are
Token are
Feature activation+2.908
fantasy
Token fantasy
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.414
Ŀ
TokenĿ
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
regular
Token regular
Feature activation+0.000
media
Token media
Feature activation+0.000
player
Token player
Feature activation+0.000
.
Token.
Feature activation+4.656
iTunes
Token iTunes
Feature activation+1.143
has
Token has
Feature activation+2.756
been
Token been
Feature activation+1.901
designed
Token designed
Feature activation+0.841
to
Token to
Feature activation+0.137
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
intelligent
Token intelligent
Feature activation+0.006
.
Token.
Feature activation+4.208
He
Token He
Feature activation+4.474
âĢ
TokenâĢ
Feature activation+0.980
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.075
conscious
Token conscious
Feature activation+0.090
.
Token.
Feature activation+0.092
purely
Token purely
Feature activation+0.000
transit
Token transit
Feature activation+0.000
projects
Token projects
Feature activation+0.689
,
Token,
Feature activation+2.392
you
Token you
Feature activation+5.195
've
Token've
Feature activation+4.391
got
Token got
Feature activation+3.753
to
Token to
Feature activation+3.247
look
Token look
Feature activation+0.430
at
Token at
Feature activation+0.858
what
Token what
Feature activation+0.368
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
,
Token,
Feature activation+4.360
we
Token we
Feature activation+7.330
âĢ
TokenâĢ
Feature activation+3.108
Ļ
TokenĻ
Feature activation+0.364
ve
Tokenve
Feature activation+0.147
actually
Token actually
Feature activation+1.738

Top DFA by src position
MAX = 7.412

evolve
Token evolve
Feature activation+0.009
Top resid features:
isn
Token isn
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.044
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
t
Tokent
Feature activation+0.024
Top resid features:
just
Token just
Feature activation+7.412
Top resid features:
speculation
Token speculation
Feature activation+0.237
Top resid features:
,
Token,
Feature activation+0.137
Top resid features:
we
Token we
Feature activation+0.052
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
cause
Token cause
Feature activation+0.015
Top resid features:
isn
Token isn
Feature activation-0.035
Top resid features:
âĢ
TokenâĢ
Feature activation+0.051
Top resid features:
Ļ
TokenĻ
Feature activation+0.034
Top resid features:
t
Tokent
Feature activation+0.089
Top resid features:
just
Token just
Feature activation+6.545
Top resid features:
liberal
Token liberal
Feature activation+0.192
Top resid features:
divorce
Token divorce
Feature activation+0.051
Top resid features:
laws
Token laws
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.210
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.016
Top resid features:
can
Token can
Feature activation+0.011
Top resid features:
do
Token do
Feature activation-0.003
Top resid features:
more
Token more
Feature activation-0.036
Top resid features:
than
Token than
Feature activation+1.824
Top resid features:
just
Token just
Feature activation+4.841
Top resid features:
get
Token get
Feature activation+0.232
Top resid features:
by
Token by
Feature activation+0.058
Top resid features:
--
Token --
Feature activation+0.059
Top resid features:
you
Token you
Feature activation-0.016
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.035
Top resid features:
B
Token B
Feature activation+0.004
Top resid features:
umble
Tokenumble
Feature activation+0.003
Top resid features:
won
Token won
Feature activation-0.006
Top resid features:
't
Token't
Feature activation-0.009
Top resid features:
just
Token just
Feature activation+6.004
Top resid features:
land
Token land
Feature activation+0.126
Top resid features:
you
Token you
Feature activation+0.016
Top resid features:
with
Token with
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
date
Token date
Feature activation+0.046
Top resid features:
Black
TokenBlack
Feature activation+0.002
Top resid features:
Sands
Token Sands
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
than
Token than
Feature activation+2.515
Top resid features:
just
Token just
Feature activation+3.428
Top resid features:
comic
Token comic
Feature activation+0.055
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
book
Tokenbook
Feature activation+0.020
Top resid features:
hero
Token hero
Feature activation+0.054
Top resid features:
ics
Tokenics
Feature activation+0.039
Top resid features:
cause
Token cause
Feature activation+0.030
Top resid features:
isn
Token isn
Feature activation-0.049
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
t
Tokent
Feature activation+0.097
Top resid features:
just
Token just
Feature activation+5.712
Top resid features:
liberal
Token liberal
Feature activation+0.193
Top resid features:
divorce
Token divorce
Feature activation+0.027
Top resid features:
laws
Token laws
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.214
Top resid features:
It
Token It
Feature activation-0.150
Top resid features:
This
Token This
Feature activation-0.014
Top resid features:
isn
Token isn
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+0.023
Top resid features:
just
Token just
Feature activation+3.435
Top resid features:
some
Token some
Feature activation+2.457
Top resid features:
remote
Token remote
Feature activation+0.051
Top resid features:
corner
Token corner
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
an
Token an
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
saying
Token saying
Feature activation+0.032
Top resid features:
you
Token you
Feature activation-0.012
Top resid features:
can
Token can
Feature activation+0.011
Top resid features:
't
Token't
Feature activation+0.063
Top resid features:
just
Token just
Feature activation+5.161
Top resid features:
look
Token look
Feature activation+0.127
Top resid features:
at
Token at
Feature activation+0.047
Top resid features:
projects
Token projects
Feature activation+0.008
Top resid features:
as
Token as
Feature activation+0.050
Top resid features:
purely
Token purely
Feature activation+0.422
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Black
TokenBlack
Feature activation+0.005
Top resid features:
Sands
Token Sands
Feature activation+0.003
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
more
Token more
Feature activation-0.000
Top resid features:
than
Token than
Feature activation+3.376
Top resid features:
just
Token just
Feature activation+2.313
Top resid features:
comic
Token comic
Feature activation+0.015
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
book
Tokenbook
Feature activation+0.013
Top resid features:
hero
Token hero
Feature activation+0.052
Top resid features:
secrets
Token secrets
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.092
Top resid features:
Secrets
Token Secrets
Feature activation+0.062
Top resid features:
aren
Token aren
Feature activation+0.064
Top resid features:
't
Token't
Feature activation+0.082
Top resid features:
just
Token just
Feature activation+4.755
Top resid features:
there
Token there
Feature activation+0.483
Top resid features:
for
Token for
Feature activation+0.111
Top resid features:
show
Token show
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.146
Top resid features:
though
Token though
Feature activation+0.088
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
But
Token But
Feature activation-0.005
Top resid features:
Putin
Token Putin
Feature activation+0.146
Top resid features:
isn
Token isn
Feature activation+0.015
Top resid features:
't
Token't
Feature activation+0.087
Top resid features:
just
Token just
Feature activation+5.011
Top resid features:
chasing
Token chasing
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.022
Top resid features:
advantageous
Token advantageous
Feature activation+0.055
Top resid features:
narrative
Token narrative
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.319
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
They
Token They
Feature activation+0.047
Top resid features:
were
Token were
Feature activation+0.016
Top resid features:
more
Token more
Feature activation-0.045
Top resid features:
than
Token than
Feature activation+1.376
Top resid features:
just
Token just
Feature activation+4.094
Top resid features:
client
Token client
Feature activation+0.090
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
attorney
Token attorney
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.102
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Don
TokenDon
Feature activation+0.055
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+0.014
Top resid features:
just
Token just
Feature activation+5.357
Top resid features:
play
Token play
Feature activation+0.113
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
Live
Token Live
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
game
Token game
Feature activation+0.000
Top resid features:
ago
Token ago
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
Miami
Token Miami
Feature activation+0.005
Top resid features:
isn
Token isn
Feature activation+0.024
Top resid features:
't
Token't
Feature activation+0.117
Top resid features:
just
Token just
Feature activation+4.847
Top resid features:
clinging
Token clinging
Feature activation+0.201
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
faint
Token faint
Feature activation+0.022
Top resid features:
hope
Token hope
Feature activation+0.050
Top resid features:
This
Token This
Feature activation-0.008
Top resid features:
isn
Token isn
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
t
Tokent
Feature activation+0.022
Top resid features:
just
Token just
Feature activation+2.973
Top resid features:
some
Token some
Feature activation+2.233
Top resid features:
remote
Token remote
Feature activation+0.055
Top resid features:
corner
Token corner
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.043
Top resid features:
an
Token an
Feature activation-0.006
Top resid features:
they
Token they
Feature activation+0.003
Top resid features:
don
Token don
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
t
Tokent
Feature activation+0.055
Top resid features:
simply
Token simply
Feature activation+5.511
Top resid features:
defy
Token defy
Feature activation-0.140
Top resid features:
logic
Token logic
Feature activation+0.023
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
any
Token any
Feature activation+0.121
Top resid features:
known
Token known
Feature activation+0.026
Top resid features:
own
Token own
Feature activation+0.023
Top resid features:
iTunes
Token iTunes
Feature activation-0.012
Top resid features:
is
Token is
Feature activation+0.021
Top resid features:
more
Token more
Feature activation-0.016
Top resid features:
than
Token than
Feature activation+1.269
Top resid features:
just
Token just
Feature activation+3.158
Top resid features:
a
Token a
Feature activation+0.549
Top resid features:
regular
Token regular
Feature activation+0.204
Top resid features:
media
Token media
Feature activation+0.019
Top resid features:
player
Token player
Feature activation+0.054
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
PO
TokenPO
Feature activation+0.126
Top resid features:
isn
Token isn
Feature activation+0.095
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
t
Tokent
Feature activation+0.065
Top resid features:
just
Token just
Feature activation+4.765
Top resid features:
intelligent
Token intelligent
Feature activation+0.137
Top resid features:
.
Token.
Feature activation+0.115
Top resid features:
He
Token He
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
saying
Token saying
Feature activation+0.012
Top resid features:
you
Token you
Feature activation-0.008
Top resid features:
can
Token can
Feature activation-0.000
Top resid features:
't
Token't
Feature activation+0.047
Top resid features:
just
Token just
Feature activation+4.370
Top resid features:
look
Token look
Feature activation+0.124
Top resid features:
at
Token at
Feature activation+0.050
Top resid features:
projects
Token projects
Feature activation+0.035
Top resid features:
as
Token as
Feature activation+0.045
Top resid features:
purely
Token purely
Feature activation+0.381
Top resid features:
evolve
Token evolve
Feature activation+0.008
Top resid features:
isn
Token isn
Feature activation-0.017
Top resid features:
âĢ
TokenâĢ
Feature activation+0.060
Top resid features:
Ļ
TokenĻ
Feature activation+0.024
Top resid features:
t
Tokent
Feature activation+0.069
Top resid features:
just
Token just
Feature activation+4.442
Top resid features:
speculation
Token speculation
Feature activation+0.390
Top resid features:
,
Token,
Feature activation+0.077
Top resid features:
we
Token we
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:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.07

Head 2: 0.03

Head 3: 0.46

Head 4: 0.02

Head 5: 0.10

Head 6: 0.05

Head 7: 0.07

Head 8: 0.05

Head 9: 0.02

Head 10: 0.02

Head 11: 0.07

Positive logits

Secondly2.06

riot2.00

!]1.97

riots1.95

rally1.88

destroying1.87

angering1.84

actually1.84

exploding1.84

expl1.81

secondly1.81

Secondly1.78

other1.77

beyond1.77

strateg1.76

apeshifter1.76

ALSO1.75

ricular1.74

OTHER1.74

everywhere1.72

Negative logits

soDeliveryDate-2.36

iatus-2.36

ilty-2.35

Tsukuyomi-2.29

usercontent-2.21

Plex-2.18

icho-2.09

iliar-2.02

ffic-2.02

BuyableInstoreAndOnline-2.01

Liquid-1.98

pmwiki-1.98

irect-1.95

mination-1.93

ドラ-1.92

Rating-1.90

ja-1.87

hesitant-1.87

Netflix-1.86

void-1.86

INTERVAL 6.597 - 7.330
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
,
Token,
Feature activation+4.360
we
Token we
Feature activation+7.330
âĢ
TokenâĢ
Feature activation+3.108
Ļ
TokenĻ
Feature activation+0.364
ve
Tokenve
Feature activation+0.147
actually
Token actually
Feature activation+1.738
discovered
Token discovered
Feature activation+0.419

INTERVAL 5.864 - 6.597
CONTAINS 0.000%

than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
get
Token get
Feature activation+0.000
by
Token by
Feature activation+0.000
--
Token --
Feature activation+2.292
you
Token you
Feature activation+6.048
can
Token can
Feature activation+3.875
get
Token get
Feature activation+2.817
ahead
Token ahead
Feature activation+0.000
.
Token.
Feature activation+1.086
And
Token And
Feature activation+0.076
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
divorce
Token divorce
Feature activation+0.538
laws
Token laws
Feature activation+0.710
.
Token.
Feature activation+6.483
It
Token It
Feature activation+5.416
âĢ
TokenâĢ
Feature activation+2.415
Ļ
TokenĻ
Feature activation+0.273
s
Tokens
Feature activation+4.221
also
Token also
Feature activation+1.527

INTERVAL 5.131 - 5.864
CONTAINS 0.001%

and
Token and
Feature activation+1.120
wild
Token wild
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.340
âĢĵ
Token âĢĵ
Feature activation+5.526
it
Token it
Feature activation+5.189
aims
Token aims
Feature activation+3.304
to
Token to
Feature activation+1.369
convey
Token convey
Feature activation+0.177
a
Token a
Feature activation+0.243
deeper
Token deeper
Feature activation+0.000
ics
Tokenics
Feature activation+0.000
and
Token and
Feature activation+1.120
wild
Token wild
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.340
âĢĵ
Token âĢĵ
Feature activation+5.526
it
Token it
Feature activation+5.189
aims
Token aims
Feature activation+3.304
to
Token to
Feature activation+1.369
convey
Token convey
Feature activation+0.177
a
Token a
Feature activation+0.243
as
Token as
Feature activation+0.224
purely
Token purely
Feature activation+0.000
transit
Token transit
Feature activation+0.000
projects
Token projects
Feature activation+0.689
,
Token,
Feature activation+2.392
you
Token you
Feature activation+5.195
've
Token've
Feature activation+4.391
got
Token got
Feature activation+3.753
to
Token to
Feature activation+3.247
look
Token look
Feature activation+0.430
at
Token at
Feature activation+0.858
just
Token just
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
divorce
Token divorce
Feature activation+0.538
laws
Token laws
Feature activation+0.710
.
Token.
Feature activation+6.483
It
Token It
Feature activation+5.416
âĢ
TokenâĢ
Feature activation+2.415
Ļ
TokenĻ
Feature activation+0.273
s
Tokens
Feature activation+4.221
also
Token also
Feature activation+1.527
the
Token the
Feature activation+0.000
land
Token land
Feature activation+0.000
you
Token you
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+5.610
You
Token You
Feature activation+4.188
can
Token can
Feature activation+1.124
also
Token also
Feature activation+0.467
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 4.398 - 5.131
CONTAINS 0.001%

chasing
Token chasing
Feature activation+0.000
an
Token an
Feature activation+0.000
advantageous
Token advantageous
Feature activation+0.000
narrative
Token narrative
Feature activation+0.000
.
Token.
Feature activation+2.740
He
Token He
Feature activation+5.024
genuinely
Token genuinely
Feature activation+1.634
believes
Token believes
Feature activation+0.887
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
is
Token is
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
client
Token client
Feature activation+0.000
and
Token and
Feature activation+1.187
attorney
Token attorney
Feature activation+0.000
.
Token.
Feature activation+4.947
The
Token The
Feature activation+1.978
two
Token two
Feature activation+0.615
were
Token were
Feature activation+1.949
joined
Token joined
Feature activation+0.000
at
Token at
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
play
Token play
Feature activation+0.000
.
Token.
Feature activation+4.904
Live
Token Live
Feature activation+0.197
the
Token the
Feature activation+0.054
game
Token game
Feature activation+0.000
-
Token -
Feature activation+1.089
From
TokenFrom
Feature activation+0.595
any
Token any
Feature activation+0.000
known
Token known
Feature activation+0.000
economic
Token economic
Feature activation+0.000
theories
Token theories
Feature activation+0.000
,
Token,
Feature activation+1.553
they
Token they
Feature activation+4.670
are
Token are
Feature activation+2.908
fantasy
Token fantasy
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.414
Ŀ
TokenĿ
Feature activation+0.000
"
Token "
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
competitive
Token competitive
Feature activation+0.000
",
Token",
Feature activation+3.203
there
Token there
Feature activation+4.747
's
Token's
Feature activation+3.304
belief
Token belief
Feature activation+2.165
the
Token the
Feature activation+1.385
Heat
Token Heat
Feature activation+0.000
can
Token can
Feature activation+0.225

INTERVAL 3.665 - 4.398
CONTAINS 0.002%

't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
compete
Token compete
Feature activation+0.000
against
Token against
Feature activation+0.000
books
Token books
Feature activation+0.000
.
Token.
Feature activation+4.121
Books
Token Books
Feature activation+3.714
compete
Token compete
Feature activation+2.773
against
Token against
Feature activation+0.269
mobile
Token mobile
Feature activation+0.000
games
Token games
Feature activation+0.000
gone
Token gone
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+1.127
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+4.182
does
Token does
Feature activation+2.763
not
Token not
Feature activation+0.428
appear
Token appear
Feature activation+0.000
to
Token to
Feature activation+0.018
be
Token be
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
,
Token,
Feature activation+4.360
we
Token we
Feature activation+7.330
âĢ
TokenâĢ
Feature activation+3.108
Ļ
TokenĻ
Feature activation+0.364
ve
Tokenve
Feature activation+0.147
actually
Token actually
Feature activation+1.738
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
ab
Token ab
Feature activation+0.000
ject
Tokenject
Feature activation+0.000
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+3.685
It
Token It
Feature activation+3.204
has
Token has
Feature activation+3.808
a
Token a
Feature activation+1.621
massive
Token massive
Feature activation+0.000
working
Token working
Feature activation+0.000
just
Token just
Feature activation+0.000
get
Token get
Feature activation+0.000
by
Token by
Feature activation+0.000
--
Token --
Feature activation+2.292
you
Token you
Feature activation+6.048
can
Token can
Feature activation+3.875
get
Token get
Feature activation+2.817
ahead
Token ahead
Feature activation+0.000
.
Token.
Feature activation+1.086
And
Token And
Feature activation+0.076
stay
Token stay
Feature activation+0.482

INTERVAL 2.932 - 3.665
CONTAINS 0.003%

-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Tokenone
Feature activation+0.000
matchups
Token matchups
Feature activation+0.000
;
Token;
Feature activation+2.967
there
Token there
Feature activation+2.583
were
Token were
Feature activation+2.917
other
Token other
Feature activation+1.349
great
Token great
Feature activation+0.000
players
Token players
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
competitive
Token competitive
Feature activation+0.000
",
Token",
Feature activation+3.203
there
Token there
Feature activation+4.747
's
Token's
Feature activation+3.304
belief
Token belief
Feature activation+2.165
the
Token the
Feature activation+1.385
Heat
Token Heat
Feature activation+0.000
can
Token can
Feature activation+0.225
still
Token still
Feature activation+0.000
go
Token go
Feature activation+0.000
there
Token there
Feature activation+0.190
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.000
,
Token,
Feature activation+3.064
they
Token they
Feature activation+2.929
'll
Token'll
Feature activation+1.648
be
Token be
Feature activation+1.462
there
Token there
Feature activation+1.197
for
Token for
Feature activation+0.097
that
Token that
Feature activation+0.000
bed
Token bed
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ils
Tokenils
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
.
Token.
Feature activation+3.112
In
Token In
Feature activation+0.972
the
Token the
Feature activation+0.204
fourth
Token fourth
Feature activation+0.000
century
Token century
Feature activation+0.000
,
Token,
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
demand
Token demand
Feature activation+0.000
a
Token a
Feature activation+0.000
winner
Token winner
Feature activation+0.000
.
Token.
Feature activation+3.415
In
Token In
Feature activation+0.534
exchange
Token exchange
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
high
Token high
Feature activation+0.000

INTERVAL 2.199 - 2.932
CONTAINS 0.005%

talk
Token talk
Feature activation+0.000
so
Token so
Feature activation+1.146
far
Token far
Feature activation+0.651
,
Token,
Feature activation+3.585
however
Token however
Feature activation+0.043
.
Token.
Feature activation+2.518
In
Token In
Feature activation+1.125
two
Token two
Feature activation+0.000
preseason
Token preseason
Feature activation+0.000
games
Token games
Feature activation+0.000
playing
Token playing
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
danger
Token danger
Feature activation+0.000
.
Token.
Feature activation+2.389
Everyone
Token Everyone
Feature activation+1.851
from
Token from
Feature activation+0.054
Amazon
Token Amazon
Feature activation+0.000
to
Token to
Feature activation+0.000
Google
Token Google
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
motions
Token motions
Feature activation+0.000
,
Token,
Feature activation+2.101
we
Token we
Feature activation+3.166
go
Token go
Feature activation+2.563
full
Token full
Feature activation+0.000
speed
Token speed
Feature activation+0.000
,
Token,
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
's
Token's
Feature activation+0.000
there
Token there
Feature activation+0.190
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.000
,
Token,
Feature activation+3.064
they
Token they
Feature activation+2.929
'll
Token'll
Feature activation+1.648
be
Token be
Feature activation+1.462
there
Token there
Feature activation+1.197
for
Token for
Feature activation+0.097
hours
Token hours
Feature activation+0.256
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Tokenone
Feature activation+0.000
matchups
Token matchups
Feature activation+0.000
;
Token;
Feature activation+2.967
there
Token there
Feature activation+2.583
were
Token were
Feature activation+2.917
other
Token other
Feature activation+1.349
great
Token great
Feature activation+0.000
players
Token players
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.000

INTERVAL 1.466 - 2.199
CONTAINS 0.010%

get
Token get
Feature activation+0.269
us
Token us
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+1.700
It
Token It
Feature activation+1.584
's
Token's
Feature activation+1.863
the
Token the
Feature activation+1.424
whole
Token whole
Feature activation+0.000
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.000
South
Token South
Feature activation+0.000
East
Token East
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
myself
Token myself
Feature activation+0.000
,
Token,
Feature activation+2.189
but
Token but
Feature activation+0.515
I
Token I
Feature activation+1.377
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.163
and
Token and
Feature activation+0.000
hope
Token hope
Feature activation+0.000
it
Token it
Feature activation+0.000
stays
Token stays
Feature activation+0.000
afloat
Token afloat
Feature activation+0.136
.
Token.
Feature activation+1.532
So
Token So
Feature activation+0.187
it
Token it
Feature activation+0.280
hired
Token hired
Feature activation+0.000
Dock
Token Dock
Feature activation+0.000
wise
Tokenwise
Feature activation+0.000
type
Token type
Feature activation+0.309
of
Token of
Feature activation+0.010
girl
Token girl
Feature activation+0.000
.
Token.
Feature activation+2.144
I
Token I
Feature activation+2.129
want
Token want
Feature activation+1.935
to
Token to
Feature activation+0.973
hear
Token hear
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
little
Token little
Feature activation+0.000
.
Token.
Feature activation+0.947
It
Token It
Feature activation+1.884
âĢ
TokenâĢ
Feature activation+0.217
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.470
about
Token about
Feature activation+2.180
how
Token how
Feature activation+0.371
that
Token that
Feature activation+0.000
person
Token person
Feature activation+0.004
is
Token is
Feature activation+0.000
portrayed
Token portrayed
Feature activation+0.000

INTERVAL 0.733 - 1.466
CONTAINS 0.021%

an
Token an
Feature activation+0.000
intellectual
Token intellectual
Feature activation+0.000
ghetto
Token ghetto
Feature activation+0.552
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.814
âĢĶ
TokenâĢĶ
Feature activation+5.256
the
Tokenthe
Feature activation+4.727
book
Token book
Feature activation+0.413
came
Token came
Feature activation+1.076
within
Token within
Feature activation+0.000
print
Token print
Feature activation+0.000
out
Tokenout
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+2.181
that
Tokenthat
Feature activation+1.649
thing
Token thing
Feature activation+0.976
is
Token is
Feature activation+0.784
professionally
Token professionally
Feature activation+0.000
framed
Token framed
Feature activation+0.000
.
Token.
Feature activation+0.116
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
become
Token become
Feature activation+1.952
more
Token more
Feature activation+0.436
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
nuisance
Token nuisance
Feature activation+0.579
.
Token.
Feature activation+0.769
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.120
Heavy
TokenHeavy
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
is
Token is
Feature activation+0.506
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
55
Token 55
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
disappear
Token disappear
Feature activation+0.000
.
Token.
Feature activation+1.382
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+1.349
may
Token may
Feature activation+0.187
not
Token not
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+1.512
and
Token and
Feature activation+1.335
in
Token in
Feature activation+0.858
fact
Token fact
Feature activation+1.042
,
Token,
Feature activation+0.000
that
Token that
Feature activation+1.026
streets
Token streets
Feature activation+0.487

INTERVAL 0.000 - 0.733
CONTAINS 99.957%

10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
and
Token and
Feature activation+0.000
17
Token 17
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
riders
Token riders
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
headache
Token headache
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Hubbard
Token Hubbard
Feature activation+0.000
,
Token,
Feature activation+0.000
moved
Token moved
Feature activation+0.000
his
Token his
Feature activation+0.000
operation
Token operation
Feature activation+0.000
there
Token there
Feature activation+0.000
after
Token after
Feature activation+0.000
spending
Token spending
Feature activation+0.000
Penn
Token Penn
Feature activation+0.000
East
TokenEast
Feature activation+0.000
pipeline
Token pipeline
Feature activation+0.000
project
Token project
Feature activation+0.000
from
Token from
Feature activation+0.000
Pennsylvania
Token Pennsylvania
Feature activation+0.000
to
Token to
Feature activation+0.000
Hop
Token Hop
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
remains
Token remains
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
droid
Token droid
Feature activation+0.000
,
Token,
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

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 H6.3: (feature 2541)

TOP ACTIVATIONS
MAX = 2.962

once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.178
are
Token are
Feature activation+2.079
now
Token now
Feature activation+2.763
calling
Token calling
Feature activation+0.312
for
Token for
Feature activation+0.291
action
Token action
Feature activation+0.249
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
taken
Token taken
Feature activation+0.000
a
Token a
Feature activation+0.231
mere
Token mere
Feature activation+0.000
five
Token five
Feature activation+0.446
minutes
Token minutes
Feature activation+0.890
can
Token can
Feature activation+2.631
turn
Token turn
Feature activation+1.543
into
Token into
Feature activation+2.288
mission
Token mission
Feature activation+0.107
impossible
Token impossible
Feature activation+0.632
when
Token when
Feature activation+0.000
slam
Token slam
Feature activation+0.000
dun
Token dun
Feature activation+0.000
ks
Tokenks
Feature activation+1.525
for
Token for
Feature activation+0.023
Trump
Token Trump
Feature activation+0.514
are
Token are
Feature activation+2.537
either
Token either
Feature activation+1.450
turning
Token turning
Feature activation+1.039
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
chief
Token chief
Feature activation+0.000
be
Token be
Feature activation+0.459
a
Token a
Feature activation+0.000
pipe
Token pipe
Feature activation+0.000
dream
Token dream
Feature activation+0.000
.
Token.
Feature activation+1.087
Now
Token Now
Feature activation+2.304
,
Token,
Feature activation+1.221
the
Token the
Feature activation+0.165
notion
Token notion
Feature activation+0.047
of
Token of
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
mere
Token mere
Feature activation+0.000
five
Token five
Feature activation+0.446
minutes
Token minutes
Feature activation+0.890
can
Token can
Feature activation+2.631
turn
Token turn
Feature activation+1.543
into
Token into
Feature activation+2.288
mission
Token mission
Feature activation+0.107
impossible
Token impossible
Feature activation+0.632
when
Token when
Feature activation+0.000
baby
Token baby
Feature activation+0.000
becomes
Token becomes
Feature activation+0.015
and
Token and
Feature activation+0.000
started
Token started
Feature activation+0.000
during
Token during
Feature activation+0.000
N
Token N
Feature activation+0.000
DA
TokenDA
Feature activation+0.023
was
Token was
Feature activation+2.266
appropriated
Token appropriated
Feature activation+0.968
by
Token by
Feature activation+0.317
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
PA
TokenPA
Feature activation+0.015
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
full
Tokenfull
Feature activation+0.000
stadiums
Token stadiums
Feature activation+0.000
--
Token --
Feature activation+1.837
are
Token are
Feature activation+2.151
mostly
Token mostly
Feature activation+1.153
dead
Token dead
Feature activation+0.846
.
Token.
Feature activation+0.326
Though
Token Though
Feature activation+0.000
there
Token there
Feature activation+0.000
who
Token who
Feature activation+0.000
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.178
are
Token are
Feature activation+2.079
now
Token now
Feature activation+2.763
calling
Token calling
Feature activation+0.312
for
Token for
Feature activation+0.291
action
Token action
Feature activation+0.249
to
Token to
Feature activation+0.000
thought
Token thought
Feature activation+0.232
,
Token,
Feature activation+0.066
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
speech
Token speech
Feature activation+0.076
,
Token,
Feature activation+2.010
now
Token now
Feature activation+0.942
universities
Token universities
Feature activation+0.532
are
Token are
Feature activation+1.076
training
Token training
Feature activation+0.065
centers
Token centers
Feature activation+0.000
viewed
Token viewed
Feature activation+0.000
as
Token as
Feature activation+0.009
witchcraft
Token witchcraft
Feature activation+0.350
or
Token or
Feature activation+0.000
sorcery
Token sorcery
Feature activation+0.882
were
Token were
Feature activation+1.964
laid
Token laid
Feature activation+0.385
bare
Token bare
Feature activation+0.668
in
Token in
Feature activation+0.312
the
Token the
Feature activation+0.017
terms
Token terms
Feature activation+0.000
had
Token had
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
draconian
Token draconian
Feature activation+0.000
budget
Token budget
Feature activation+0.000
cuts
Token cuts
Feature activation+1.005
was
Token was
Feature activation+1.872
Nor
Token Nor
Feature activation+0.000
ad
Tokenad
Feature activation+0.094
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
their
Token their
Feature activation+0.000
reach
Token reach
Feature activation+0.030
until
Token until
Feature activation+1.856
the
Token the
Feature activation+0.596
age
Token age
Feature activation+0.207
of
Token of
Feature activation+0.000
about
Token about
Feature activation+0.000
four
Token four
Feature activation+0.000
with
Token with
Feature activation+0.000
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
full
Tokenfull
Feature activation+0.000
stadiums
Token stadiums
Feature activation+0.000
--
Token --
Feature activation+1.837
are
Token are
Feature activation+2.151
mostly
Token mostly
Feature activation+1.153
dead
Token dead
Feature activation+0.846
.
Token.
Feature activation+0.326
Though
Token Though
Feature activation+0.000
reverse
Token reverse
Feature activation+0.000
narc
Token narc
Feature activation+0.000
otic
Tokenotic
Feature activation+0.000
intoxication
Token intoxication
Feature activation+0.000
.
Token.
Feature activation+0.595
However
Token However
Feature activation+1.827
,
Token,
Feature activation+0.874
its
Token its
Feature activation+0.000
use
Token use
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
rather
Token rather
Feature activation+0.000
good
Token good
Feature activation+0.000
completion
Token completion
Feature activation+0.000
rate
Token rate
Feature activation+0.109
,
Token,
Feature activation+1.764
has
Token has
Feature activation+1.268
worked
Token worked
Feature activation+0.604
out
Token out
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
a
Token a
Feature activation+0.000
protected
Token protected
Feature activation+0.000
space
Token space
Feature activation+0.000
for
Token for
Feature activation+0.033
truth
Token truth
Feature activation+0.000
,
Token,
Feature activation+1.755
independent
Token independent
Feature activation+0.000
thought
Token thought
Feature activation+0.232
,
Token,
Feature activation+0.066
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
intended
Token intended
Feature activation+0.000
for
Token for
Feature activation+0.000
children
Token children
Feature activation+0.000
were
Token were
Feature activation+1.732
toxic
Token toxic
Feature activation+0.091
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
example
Token example
Feature activation+0.000
bath
Token bath
Feature activation+0.000
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
its
Tokenits
Feature activation+0.000
luck
Token luck
Feature activation+0.198
club
Token club
Feature activation+1.695
playing
Token playing
Feature activation+0.537
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.494
s
Tokens
Feature activation+0.565
$
Token $
Feature activation+0.000
258
Token258
Feature activation+0.036
million
Token million
Feature activation+0.277
now
Token now
Feature activation+1.668
has
Token has
Feature activation+1.270
a
Token a
Feature activation+0.233
shot
Token shot
Feature activation+0.225
at
Token at
Feature activation+0.006
exceeding
Token exceeding
Feature activation+0.046
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.091
but
Token but
Feature activation+1.507
delivered
Token delivered
Feature activation+1.657
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.000
that
Token that
Feature activation+0.000

Top DFA by src position
MAX = 2.730

surprise
Token surprise
Feature activation-0.021
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
even
Token even
Feature activation-0.143
Top resid features:
economists
Token economists
Feature activation+0.042
Top resid features:
who
Token who
Feature activation+0.039
Top resid features:
once
Token once
Feature activation+2.730
Top resid features:
backed
Token backed
Feature activation+0.563
Top resid features:
George
Token George
Feature activation+0.020
Top resid features:
Osborne
Token Osborne
Feature activation+0.010
Top resid features:
are
Token are
Feature activation+0.109
Top resid features:
now
Token now
Feature activation+0.077
Top resid features:
popping
Token popping
Feature activation-0.008
Top resid features:
out
Token out
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
milk
Token milk
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.048
Top resid features:
would
Token would
Feature activation+1.170
Top resid features:
once
Token once
Feature activation+1.048
Top resid features:
have
Token have
Feature activation+0.667
Top resid features:
taken
Token taken
Feature activation+0.032
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
mere
Token mere
Feature activation+0.147
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
clear
Token clear
Feature activation+0.015
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
Papers
Token Papers
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
should
Token should
Feature activation+1.273
Top resid features:
theoretically
Token theoretically
Feature activation+0.877
Top resid features:
be
Token be
Feature activation+0.639
Top resid features:
slam
Token slam
Feature activation+0.025
Top resid features:
dun
Token dun
Feature activation+0.022
Top resid features:
ks
Tokenks
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
That
TokenThat
Feature activation+0.009
Top resid features:
used
Token used
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.857
Top resid features:
be
Token be
Feature activation+1.690
Top resid features:
a
Token a
Feature activation+0.051
Top resid features:
pipe
Token pipe
Feature activation+0.021
Top resid features:
dream
Token dream
Feature activation+0.080
Top resid features:
.
Token.
Feature activation+0.080
Top resid features:
Now
Token Now
Feature activation+0.012
Top resid features:
out
Token out
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
milk
Token milk
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
would
Token would
Feature activation+0.621
Top resid features:
once
Token once
Feature activation+1.192
Top resid features:
have
Token have
Feature activation+0.582
Top resid features:
taken
Token taken
Feature activation+0.074
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
mere
Token mere
Feature activation+0.111
Top resid features:
five
Token five
Feature activation+0.007
Top resid features:
available
Token available
Feature activation+0.014
Top resid features:
where
Token where
Feature activation-0.058
Top resid features:
something
Token something
Feature activation+0.033
Top resid features:
that
Token that
Feature activation+0.050
Top resid features:
was
Token was
Feature activation+0.340
Top resid features:
thought
Token thought
Feature activation+2.258
Top resid features:
through
Token through
Feature activation-0.067
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
started
Token started
Feature activation+0.058
Top resid features:
during
Token during
Feature activation+0.140
Top resid features:
N
Token N
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Whatever
TokenWhatever
Feature activation+0.110
Top resid features:
negative
Token negative
Feature activation+0.042
Top resid features:
perceptions
Token perceptions
Feature activation+0.116
Top resid features:
formerly
Token formerly
Feature activation+1.162
Top resid features:
were
Token were
Feature activation+0.696
Top resid features:
held
Token held
Feature activation+0.265
Top resid features:
about
Token about
Feature activation+0.169
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Pac
Token Pac
Feature activation+0.004
Top resid features:
surprise
Token surprise
Feature activation-0.020
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
even
Token even
Feature activation-0.215
Top resid features:
economists
Token economists
Feature activation+0.091
Top resid features:
who
Token who
Feature activation+0.096
Top resid features:
once
Token once
Feature activation+2.338
Top resid features:
backed
Token backed
Feature activation+0.393
Top resid features:
George
Token George
Feature activation+0.026
Top resid features:
Osborne
Token Osborne
Feature activation+0.017
Top resid features:
are
Token are
Feature activation+0.016
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
university
Token university
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Once
Token Once
Feature activation+0.406
Top resid features:
a
Token a
Feature activation+1.830
Top resid features:
protected
Token protected
Feature activation+0.108
Top resid features:
space
Token space
Feature activation+0.117
Top resid features:
for
Token for
Feature activation+0.123
Top resid features:
truth
Token truth
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
concepts
Token concepts
Feature activation+0.028
Top resid features:
that
Token that
Feature activation+0.060
Top resid features:
had
Token had
Feature activation+0.270
Top resid features:
long
Token long
Feature activation+0.392
Top resid features:
been
Token been
Feature activation+0.796
Top resid features:
viewed
Token viewed
Feature activation+0.325
Top resid features:
as
Token as
Feature activation+0.382
Top resid features:
witchcraft
Token witchcraft
Feature activation+0.061
Top resid features:
or
Token or
Feature activation+0.009
Top resid features:
sorcery
Token sorcery
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
one
Token one
Feature activation+0.117
Top resid features:
defense
Token defense
Feature activation+0.039
Top resid features:
agency
Token agency
Feature activation+0.088
Top resid features:
that
Token that
Feature activation+0.078
Top resid features:
had
Token had
Feature activation+1.178
Top resid features:
suffered
Token suffered
Feature activation+0.799
Top resid features:
draconian
Token draconian
Feature activation+0.035
Top resid features:
budget
Token budget
Feature activation+0.002
Top resid features:
cuts
Token cuts
Feature activation+0.028
Top resid features:
was
Token was
Feature activation+0.034
Top resid features:
logical
Token logical
Feature activation+0.011
Top resid features:
reasoning
Token reasoning
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.052
Top resid features:
previously
Token previously
Feature activation+1.527
Top resid features:
thought
Token thought
Feature activation+0.411
Top resid features:
to
Token to
Feature activation+0.115
Top resid features:
be
Token be
Feature activation+0.252
Top resid features:
beyond
Token beyond
Feature activation-0.014
Top resid features:
their
Token their
Feature activation+0.090
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Whatever
TokenWhatever
Feature activation+0.125
Top resid features:
negative
Token negative
Feature activation+0.098
Top resid features:
perceptions
Token perceptions
Feature activation+0.130
Top resid features:
formerly
Token formerly
Feature activation+0.994
Top resid features:
were
Token were
Feature activation+0.659
Top resid features:
held
Token held
Feature activation+0.221
Top resid features:
about
Token about
Feature activation+0.274
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
Pac
Token Pac
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.335
Top resid features:
used
Token used
Feature activation-0.031
Top resid features:
to
Token to
Feature activation+2.494
Top resid features:
reverse
Token reverse
Feature activation-0.083
Top resid features:
narc
Token narc
Feature activation+0.005
Top resid features:
otic
Tokenotic
Feature activation+0.009
Top resid features:
intoxication
Token intoxication
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
"
Token "
Feature activation-0.006
Top resid features:
Short
TokenShort
Feature activation+0.002
Top resid features:
",
Token",
Feature activation-0.115
Top resid features:
which
Token which
Feature activation+0.137
Top resid features:
used
Token used
Feature activation+0.135
Top resid features:
to
Token to
Feature activation+1.880
Top resid features:
have
Token have
Feature activation+0.582
Top resid features:
a
Token a
Feature activation+0.022
Top resid features:
rather
Token rather
Feature activation+0.013
Top resid features:
good
Token good
Feature activation+0.011
Top resid features:
completion
Token completion
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
university
Token university
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Once
Token Once
Feature activation+0.312
Top resid features:
a
Token a
Feature activation+1.812
Top resid features:
protected
Token protected
Feature activation+0.118
Top resid features:
space
Token space
Feature activation+0.057
Top resid features:
for
Token for
Feature activation+0.094
Top resid features:
truth
Token truth
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
13
Token 13
Feature activation-0.002
Top resid features:
products
Token products
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
were
Token were
Feature activation+0.119
Top resid features:
intended
Token intended
Feature activation+1.702
Top resid features:
for
Token for
Feature activation+0.188
Top resid features:
children
Token children
Feature activation+0.061
Top resid features:
were
Token were
Feature activation+0.049
Top resid features:
toxic
Token toxic
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
Paris
Token Paris
Feature activation-0.002
Top resid features:
ians
Tokenians
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
A
Token A
Feature activation+0.027
Top resid features:
once
Token once
Feature activation+2.096
Top resid features:
down
Token down
Feature activation+0.183
Top resid features:
âĢij
TokenâĢij
Feature activation+0.006
Top resid features:
at
Tokenat
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
he
Tokenhe
Feature activation+0.009
Top resid features:
5
Token 5
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
day
Tokenday
Feature activation-0.014
Top resid features:
frame
Token frame
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.132
Top resid features:
was
Token was
Feature activation+1.010
Top resid features:
destined
Token destined
Feature activation+0.602
Top resid features:
to
Token to
Feature activation+0.140
Top resid features:
play
Token play
Feature activation+0.031
Top resid features:
second
Token second
Feature activation-0.002
Top resid features:
f
Token f
Feature activation+0.003
Top resid features:
failed
Token failed
Feature activation+0.007
Top resid features:
austerity
Token austerity
Feature activation-0.040
Top resid features:
that
Token that
Feature activation-0.032
Top resid features:
was
Token was
Feature activation+0.045
Top resid features:
supposed
Token supposed
Feature activation+0.923
Top resid features:
to
Token to
Feature activation+1.595
Top resid features:
deliver
Token deliver
Feature activation+0.003
Top resid features:
growth
Token growth
Feature activation-0.061
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
but
Token but
Feature activation-0.050
Top resid features:
delivered
Token delivered
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.05

Head 2: 0.03

Head 3: 0.46

Head 4: 0.03

Head 5: 0.09

Head 6: 0.05

Head 7: 0.08

Head 8: 0.04

Head 9: 0.01

Head 10: 0.02

Head 11: 0.05

Positive logits

etheless2.88

nonetheless2.47

kefeller2.39

reversed2.38

alas2.28

nevertheless2.25

Instead2.24

deserted2.16

redo2.16

azard2.12

turned2.12

now2.11

now2.07

repair2.06

Instead2.06

itans2.05

uddenly2.05

vanished2.04

ursor2.00

olution2.00

Negative logits

chy-2.45

76561-2.21

soDeliveryDate-2.06

ONSORED-2.03

respons-1.99

":["-1.97

"]=>-1.93

ILCS-1.90

orem-1.87

XY-1.86

XXX-1.82

XX-1.81

-1.80

LV-1.80

Pad-1.73

code-1.71

encyclopedia-1.71

ogie-1.71

Ley-1.70

-1.69

INTERVAL 2.666 - 2.962
CONTAINS 0.000%

once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.178
are
Token are
Feature activation+2.079
now
Token now
Feature activation+2.763
calling
Token calling
Feature activation+0.312
for
Token for
Feature activation+0.291
action
Token action
Feature activation+0.249
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000

INTERVAL 2.370 - 2.666
CONTAINS 0.000%

taken
Token taken
Feature activation+0.000
a
Token a
Feature activation+0.231
mere
Token mere
Feature activation+0.000
five
Token five
Feature activation+0.446
minutes
Token minutes
Feature activation+0.890
can
Token can
Feature activation+2.631
turn
Token turn
Feature activation+1.543
into
Token into
Feature activation+2.288
mission
Token mission
Feature activation+0.107
impossible
Token impossible
Feature activation+0.632
when
Token when
Feature activation+0.000
slam
Token slam
Feature activation+0.000
dun
Token dun
Feature activation+0.000
ks
Tokenks
Feature activation+1.525
for
Token for
Feature activation+0.023
Trump
Token Trump
Feature activation+0.514
are
Token are
Feature activation+2.537
either
Token either
Feature activation+1.450
turning
Token turning
Feature activation+1.039
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
chief
Token chief
Feature activation+0.000

INTERVAL 2.074 - 2.370
CONTAINS 0.001%

and
Token and
Feature activation+0.000
started
Token started
Feature activation+0.000
during
Token during
Feature activation+0.000
N
Token N
Feature activation+0.000
DA
TokenDA
Feature activation+0.023
was
Token was
Feature activation+2.266
appropriated
Token appropriated
Feature activation+0.968
by
Token by
Feature activation+0.317
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
PA
TokenPA
Feature activation+0.015
be
Token be
Feature activation+0.459
a
Token a
Feature activation+0.000
pipe
Token pipe
Feature activation+0.000
dream
Token dream
Feature activation+0.000
.
Token.
Feature activation+1.087
Now
Token Now
Feature activation+2.304
,
Token,
Feature activation+1.221
the
Token the
Feature activation+0.165
notion
Token notion
Feature activation+0.047
of
Token of
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
mere
Token mere
Feature activation+0.000
five
Token five
Feature activation+0.446
minutes
Token minutes
Feature activation+0.890
can
Token can
Feature activation+2.631
turn
Token turn
Feature activation+1.543
into
Token into
Feature activation+2.288
mission
Token mission
Feature activation+0.107
impossible
Token impossible
Feature activation+0.632
when
Token when
Feature activation+0.000
baby
Token baby
Feature activation+0.000
becomes
Token becomes
Feature activation+0.015
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
full
Tokenfull
Feature activation+0.000
stadiums
Token stadiums
Feature activation+0.000
--
Token --
Feature activation+1.837
are
Token are
Feature activation+2.151
mostly
Token mostly
Feature activation+1.153
dead
Token dead
Feature activation+0.846
.
Token.
Feature activation+0.326
Though
Token Though
Feature activation+0.000
there
Token there
Feature activation+0.000
who
Token who
Feature activation+0.000
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.178
are
Token are
Feature activation+2.079
now
Token now
Feature activation+2.763
calling
Token calling
Feature activation+0.312
for
Token for
Feature activation+0.291
action
Token action
Feature activation+0.249
to
Token to
Feature activation+0.000

INTERVAL 1.777 - 2.074
CONTAINS 0.001%

had
Token had
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
draconian
Token draconian
Feature activation+0.000
budget
Token budget
Feature activation+0.000
cuts
Token cuts
Feature activation+1.005
was
Token was
Feature activation+1.872
Nor
Token Nor
Feature activation+0.000
ad
Tokenad
Feature activation+0.094
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
had
Token had
Feature activation+0.000
reverse
Token reverse
Feature activation+0.000
narc
Token narc
Feature activation+0.000
otic
Tokenotic
Feature activation+0.000
intoxication
Token intoxication
Feature activation+0.000
.
Token.
Feature activation+0.595
However
Token However
Feature activation+1.827
,
Token,
Feature activation+0.874
its
Token its
Feature activation+0.000
use
Token use
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
with
Token with
Feature activation+0.000
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
full
Tokenfull
Feature activation+0.000
stadiums
Token stadiums
Feature activation+0.000
--
Token --
Feature activation+1.837
are
Token are
Feature activation+2.151
mostly
Token mostly
Feature activation+1.153
dead
Token dead
Feature activation+0.846
.
Token.
Feature activation+0.326
Though
Token Though
Feature activation+0.000
viewed
Token viewed
Feature activation+0.000
as
Token as
Feature activation+0.009
witchcraft
Token witchcraft
Feature activation+0.350
or
Token or
Feature activation+0.000
sorcery
Token sorcery
Feature activation+0.882
were
Token were
Feature activation+1.964
laid
Token laid
Feature activation+0.385
bare
Token bare
Feature activation+0.668
in
Token in
Feature activation+0.312
the
Token the
Feature activation+0.017
terms
Token terms
Feature activation+0.000
thought
Token thought
Feature activation+0.232
,
Token,
Feature activation+0.066
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
speech
Token speech
Feature activation+0.076
,
Token,
Feature activation+2.010
now
Token now
Feature activation+0.942
universities
Token universities
Feature activation+0.532
are
Token are
Feature activation+1.076
training
Token training
Feature activation+0.065
centers
Token centers
Feature activation+0.000

INTERVAL 1.481 - 1.777
CONTAINS 0.001%

a
Token a
Feature activation+0.000
protected
Token protected
Feature activation+0.000
space
Token space
Feature activation+0.000
for
Token for
Feature activation+0.033
truth
Token truth
Feature activation+0.000
,
Token,
Feature activation+1.755
independent
Token independent
Feature activation+0.000
thought
Token thought
Feature activation+0.232
,
Token,
Feature activation+0.066
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.091
but
Token but
Feature activation+1.507
delivered
Token delivered
Feature activation+1.657
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.000
that
Token that
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
intended
Token intended
Feature activation+0.000
for
Token for
Feature activation+0.000
children
Token children
Feature activation+0.000
were
Token were
Feature activation+1.732
toxic
Token toxic
Feature activation+0.091
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
example
Token example
Feature activation+0.000
bath
Token bath
Feature activation+0.000
should
Token should
Feature activation+0.000
theoretically
Token theoretically
Feature activation+0.000
be
Token be
Feature activation+0.000
slam
Token slam
Feature activation+0.000
dun
Token dun
Feature activation+0.000
ks
Tokenks
Feature activation+1.525
for
Token for
Feature activation+0.023
Trump
Token Trump
Feature activation+0.514
are
Token are
Feature activation+2.537
either
Token either
Feature activation+1.450
turning
Token turning
Feature activation+1.039
Ļ
TokenĻ
Feature activation+0.494
s
Tokens
Feature activation+0.565
$
Token $
Feature activation+0.000
258
Token258
Feature activation+0.036
million
Token million
Feature activation+0.277
now
Token now
Feature activation+1.668
has
Token has
Feature activation+1.270
a
Token a
Feature activation+0.233
shot
Token shot
Feature activation+0.225
at
Token at
Feature activation+0.006
exceeding
Token exceeding
Feature activation+0.046

INTERVAL 1.185 - 1.481
CONTAINS 0.002%

a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.154
is
Token is
Feature activation+1.263
now
Token now
Feature activation+1.241
fetch
Token fetch
Feature activation+0.138
ing
Tokening
Feature activation+0.220
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
$
Token $
Feature activation+0.000
rather
Token rather
Feature activation+0.000
good
Token good
Feature activation+0.000
completion
Token completion
Feature activation+0.000
rate
Token rate
Feature activation+0.109
,
Token,
Feature activation+1.764
has
Token has
Feature activation+1.268
worked
Token worked
Feature activation+0.604
out
Token out
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
get
Token get
Feature activation+0.000
any
Token any
Feature activation+0.000
more
Token more
Feature activation+0.000
tone
Token tone
Feature activation+0.000
deaf
Token deaf
Feature activation+0.000
,
Token,
Feature activation+1.190
after
Token after
Feature activation+0.000
backing
Token backing
Feature activation+0.000
Little
Token Little
Feature activation+0.000
League
Token League
Feature activation+0.000
father
Token father
Feature activation+0.000
law
Token law
Feature activation+0.000
for
Token for
Feature activation+0.251
one
Token one
Feature activation+0.011
reason
Token reason
Feature activation+0.000
and
Token and
Feature activation+0.363
uses
Token uses
Feature activation+1.297
it
Token it
Feature activation+0.313
for
Token for
Feature activation+0.000
something
Token something
Feature activation+0.000
completely
Token completely
Feature activation+0.000
different
Token different
Feature activation+0.000
industry
Token industry
Feature activation+0.144
and
Token and
Feature activation+0.182
Mot
Token Mot
Feature activation+0.000
own
Tokenown
Feature activation+0.016
music
Token music
Feature activation+0.000
,
Token,
Feature activation+1.341
Detroit
Token Detroit
Feature activation+0.144
appears
Token appears
Feature activation+0.786
to
Token to
Feature activation+0.632
have
Token have
Feature activation+0.888
run
Token run
Feature activation+0.340

INTERVAL 0.889 - 1.185
CONTAINS 0.004%

respected
Token respected
Feature activation+0.000
professional
Token professional
Feature activation+0.000
Bruce
Token Bruce
Feature activation+0.000
Feldman
Token Feldman
Feature activation+0.000
,
Token,
Feature activation+0.616
now
Token now
Feature activation+1.025
comes
Token comes
Feature activation+0.372
this
Token this
Feature activation+0.000
inexplicable
Token inexplicable
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000
free
Token free
Feature activation+0.000
speech
Token speech
Feature activation+0.076
,
Token,
Feature activation+2.010
now
Token now
Feature activation+0.942
universities
Token universities
Feature activation+0.532
are
Token are
Feature activation+1.076
training
Token training
Feature activation+0.065
centers
Token centers
Feature activation+0.000
for
Token for
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
ks
Tokenks
Feature activation+1.525
for
Token for
Feature activation+0.023
Trump
Token Trump
Feature activation+0.514
are
Token are
Feature activation+2.537
either
Token either
Feature activation+1.450
turning
Token turning
Feature activation+1.039
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
chief
Token chief
Feature activation+0.000
rival
Token rival
Feature activation+0.000
or
Token or
Feature activation+0.000
nightmare
Token nightmare
Feature activation+0.000
in
Token in
Feature activation+0.000
T
Token T
Feature activation+0.000
amiya
Tokenamiya
Feature activation+0.000
kits
Token kits
Feature activation+0.000
are
Token are
Feature activation+1.160
only
Token only
Feature activation+0.382
a
Token a
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
piece
Tokenpiece
Feature activation+0.000
releases
Token releases
Feature activation+0.247
but
Token but
Feature activation+0.000
got
Token got
Feature activation+0.000
del
Token del
Feature activation+0.000
isted
Tokenisted
Feature activation+0.000
aren
Token aren
Feature activation+1.151
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.429
included
Token included
Feature activation+0.350
(
Token (
Feature activation+0.000

INTERVAL 0.592 - 0.889
CONTAINS 0.009%

just
Token just
Feature activation+0.085
a
Token a
Feature activation+0.027
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.011
ago
Token ago
Feature activation+0.346
,
Token,
Feature activation+0.671
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.325
been
Token been
Feature activation+0.000
viewed
Token viewed
Feature activation+0.000
as
Token as
Feature activation+0.009
witchcraft
Token witchcraft
Feature activation+0.350
or
Token or
Feature activation+0.000
sorcery
Token sorcery
Feature activation+0.882
were
Token were
Feature activation+1.964
laid
Token laid
Feature activation+0.385
bare
Token bare
Feature activation+0.668
in
Token in
Feature activation+0.312
the
Token the
Feature activation+0.017
his
Token his
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+0.000
setting
Tokensetting
Feature activation+0.000
pace
Token pace
Feature activation+0.000
.
Token.
Feature activation+0.669
The
Token The
Feature activation+0.000
Packers
Token Packers
Feature activation+0.000
would
Token would
Feature activation+0.000
head
Token head
Feature activation+0.000
back
Token back
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
red
Token red
Feature activation+0.000
shirt
Tokenshirt
Feature activation+0.000
freshman
Token freshman
Feature activation+0.836
in
Token in
Feature activation+0.669
2014
Token 2014
Feature activation+1.159
;
Token;
Feature activation+0.121
and
Token and
Feature activation+0.000
walk
Token walk
Feature activation+0.000
external
Token external
Feature activation+0.000
threats
Token threats
Feature activation+0.000
that
Token that
Feature activation+0.000
previously
Token previously
Feature activation+0.000
had
Token had
Feature activation+0.167
not
Token not
Feature activation+0.709
existed
Token existed
Feature activation+0.063
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.296 - 0.592
CONTAINS 0.031%

long
Token long
Feature activation+0.000
been
Token been
Feature activation+0.000
slated
Token slated
Feature activation+0.000
for
Token for
Feature activation+0.000
urban
Token urban
Feature activation+0.000
renewal
Token renewal
Feature activation+0.347
,
Token,
Feature activation+0.533
as
Token as
Feature activation+0.000
several
Token several
Feature activation+0.000
lots
Token lots
Feature activation+0.000
have
Token have
Feature activation+0.574
their
Token their
Feature activation+0.000
families
Token families
Feature activation+0.000
once
Token once
Feature activation+0.000
fled
Token fled
Feature activation+0.000
to
Token to
Feature activation+0.000
Syria
Token Syria
Feature activation+0.333
for
Token for
Feature activation+0.000
sanctuary
Token sanctuary
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1915
Token 1915
Feature activation+0.000
's
Token's
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
law
Token law
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.334
it
Token it
Feature activation+0.264
with
Token with
Feature activation+0.454
a
Token a
Feature activation+0.000
system
Token system
Feature activation+0.000
designed
Token designed
Feature activation+0.000
Dakota
Token Dakota
Feature activation+0.000
Access
Token Access
Feature activation+0.000
Pipeline
Token Pipeline
Feature activation+0.000
thing
Token thing
Feature activation+0.038
âĢĶ
TokenâĢĶ
Feature activation+0.000
no
Tokenno
Feature activation+0.339
more
Token more
Feature activation+0.000
delays
Token delays
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
by
Token by
Feature activation+0.000
design
Token design
Feature activation+0.000
,
Token,
Feature activation+0.555
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
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.296
CONTAINS 99.952%

,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
bad
Token bad
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
prepares
Token prepares
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
19
Token 19
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
woman
Token woman
Feature activation+0.000
,
Token,
Feature activation+0.000
raised
Token raised
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
is
Tokenis
Feature activation+0.000
mell
Token mell
Feature activation+0.000
ifer
Tokenifer
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token.
Feature activation+0.000
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
,
Token,
Feature activation+0.000
horn
Token horn
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
demand
Token demand
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
commun
Tokencommun
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
territories
Token territories
Feature activation+0.000
locally
Token locally
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
inferior
Token inferior
Feature activation+0.000
q
Tokenq
Feature activation+0.000
X
TokenX
Feature activation+0.000
n
Tokenn
Feature activation+0.000
8
Token8
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
L
Token L
Feature activation+0.000
w
Tokenw
Feature activation+0.000
azi
Tokenazi
Feature activation+0.000
(@
Token (@
Feature activation+0.000
L
TokenL
Feature activation+0.000
w
Tokenw
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 H6.3: (feature 6776)

TOP ACTIVATIONS
MAX = 5.440

ic
Tokenic
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
workers
Tokenworkers
Feature activation+0.000
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
informed
Tokeninformed
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000
."
Token."
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000
my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
serv
Tokenserv
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
informed
Tokeninformed
Feature activation+0.000
Worker
Token Worker
Feature activation+0.000
stock
Token stock
Feature activation+0.000
that
Token that
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.497
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
no
Token no
Feature activation+0.000
for
Token for
Feature activation+0.000
-
Token-
Feature activation+0.000
fee
Tokenfee
Feature activation+0.000
AV
Token AV
Feature activation+0.000
,
Token,
Feature activation+0.176
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
industry
Token industry
Feature activation+0.779
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
powered
Tokenpowered
Feature activation+0.000
microscope
Token microscope
Feature activation+0.000
,
Token,
Feature activation+0.097
these
Token these
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
"
Token "
Feature activation+0.000
te
Tokente
Feature activation+0.000
eth
Tokeneth
Feature activation+0.000
reach
Token reach
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
their
Tokentheir
Feature activation+0.000
bewild
Token bewild
Feature activation+0.000
er
Tokener
Feature activation+0.000
ment
Tokenment
Feature activation+0.092
deep
Token deep
Feature activation+0.000
ened
Tokenened
Feature activation+0.000
.
Token.
Feature activation+0.000
Was
Token Was
Feature activation+0.000
it
Token it
Feature activation+0.000
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000
Whether
Token Whether
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.039
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
car
Token car
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
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

Top DFA by src position
MAX = 5.520

that
Token that
Feature activation+0.118
Top resid features:
,
Token,
Feature activation-0.049
Top resid features:
were
Token were
Feature activation+0.600
Top resid features:
it
Token it
Feature activation+0.280
Top resid features:
not
Token not
Feature activation+1.506
Top resid features:
for
Token for
Feature activation+4.670
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
extremely
Token extremely
Feature activation+0.047
Top resid features:
courageous
Token courageous
Feature activation+0.074
Top resid features:
actions
Token actions
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
that
Token that
Feature activation+0.105
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
were
Token were
Feature activation+0.141
Top resid features:
it
Token it
Feature activation+0.278
Top resid features:
not
Token not
Feature activation+1.883
Top resid features:
for
Token for
Feature activation+3.828
Top resid features:
the
Token the
Feature activation+0.282
Top resid features:
extremely
Token extremely
Feature activation+0.083
Top resid features:
courageous
Token courageous
Feature activation+0.094
Top resid features:
actions
Token actions
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
it
Token it
Feature activation+0.075
Top resid features:
weren
Token weren
Feature activation+0.728
Top resid features:
âĢ
TokenâĢ
Feature activation+0.047
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
t
Tokent
Feature activation+0.459
Top resid features:
for
Token for
Feature activation+5.520
Top resid features:
some
Token some
Feature activation+0.064
Top resid features:
good
Token good
Feature activation+0.012
Top resid features:
co
Token co
Feature activation+0.011
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
workers
Tokenworkers
Feature activation-0.068
Top resid features:
it
Token it
Feature activation+0.087
Top resid features:
weren
Token weren
Feature activation+0.856
Top resid features:
âĢ
TokenâĢ
Feature activation+0.033
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
t
Tokent
Feature activation+0.267
Top resid features:
for
Token for
Feature activation+4.158
Top resid features:
some
Token some
Feature activation+0.082
Top resid features:
good
Token good
Feature activation+0.030
Top resid features:
co
Token co
Feature activation+0.027
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
workers
Tokenworkers
Feature activation-0.027
Top resid features:
it
Token it
Feature activation+0.049
Top resid features:
weren
Token weren
Feature activation+0.480
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+0.183
Top resid features:
for
Token for
Feature activation+3.651
Top resid features:
some
Token some
Feature activation+0.043
Top resid features:
good
Token good
Feature activation+0.019
Top resid features:
co
Token co
Feature activation+0.023
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
workers
Tokenworkers
Feature activation-0.020
Top resid features:
that
Token that
Feature activation+0.059
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
were
Token were
Feature activation+0.095
Top resid features:
it
Token it
Feature activation+0.100
Top resid features:
not
Token not
Feature activation+0.927
Top resid features:
for
Token for
Feature activation+2.069
Top resid features:
the
Token the
Feature activation+0.277
Top resid features:
extremely
Token extremely
Feature activation+0.121
Top resid features:
courageous
Token courageous
Feature activation+0.175
Top resid features:
actions
Token actions
Feature activation+0.106
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
that
Token that
Feature activation+0.078
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
were
Token were
Feature activation+0.162
Top resid features:
it
Token it
Feature activation+0.288
Top resid features:
not
Token not
Feature activation+1.299
Top resid features:
for
Token for
Feature activation+1.462
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
extremely
Token extremely
Feature activation+0.045
Top resid features:
courageous
Token courageous
Feature activation+0.090
Top resid features:
actions
Token actions
Feature activation+0.060
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
that
Token that
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
were
Token were
Feature activation+0.055
Top resid features:
it
Token it
Feature activation+0.101
Top resid features:
not
Token not
Feature activation+0.600
Top resid features:
for
Token for
Feature activation+2.285
Top resid features:
the
Token the
Feature activation+0.366
Top resid features:
extremely
Token extremely
Feature activation+0.107
Top resid features:
courageous
Token courageous
Feature activation+0.191
Top resid features:
actions
Token actions
Feature activation+0.074
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
it
Token it
Feature activation+0.125
Top resid features:
weren
Token weren
Feature activation+0.547
Top resid features:
âĢ
TokenâĢ
Feature activation+0.072
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
t
Tokent
Feature activation+0.228
Top resid features:
for
Token for
Feature activation+2.935
Top resid features:
some
Token some
Feature activation+0.058
Top resid features:
good
Token good
Feature activation+0.028
Top resid features:
co
Token co
Feature activation+0.034
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
workers
Tokenworkers
Feature activation-0.041
Top resid features:
that
Token that
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
were
Token were
Feature activation+0.048
Top resid features:
it
Token it
Feature activation+0.323
Top resid features:
not
Token not
Feature activation+0.841
Top resid features:
for
Token for
Feature activation+1.111
Top resid features:
the
Token the
Feature activation+0.262
Top resid features:
extremely
Token extremely
Feature activation+0.199
Top resid features:
courageous
Token courageous
Feature activation+0.231
Top resid features:
actions
Token actions
Feature activation+0.135
Top resid features:
of
Token of
Feature activation+0.208
Top resid features:
it
Token it
Feature activation+0.031
Top resid features:
weren
Token weren
Feature activation+0.138
Top resid features:
âĢ
TokenâĢ
Feature activation+0.016
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
t
Tokent
Feature activation+0.108
Top resid features:
for
Token for
Feature activation+1.544
Top resid features:
some
Token some
Feature activation+0.042
Top resid features:
good
Token good
Feature activation+0.005
Top resid features:
co
Token co
Feature activation+0.038
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
workers
Tokenworkers
Feature activation+0.002
Top resid features:
resist
Token resist
Feature activation+0.003
Top resid features:
this
Token this
Feature activation+0.020
Top resid features:
one
Token one
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.092
Top resid features:
Or
Token Or
Feature activation+0.065
Top resid features:
maybe
Token maybe
Feature activation+1.867
Top resid features:
the
Token the
Feature activation+0.130
Top resid features:
store
Token store
Feature activation+0.001
Top resid features:
just
Token just
Feature activation-0.002
Top resid features:
didn
Token didn
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.055
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.572
Top resid features:
"
Token"
Feature activation-0.006
Top resid features:
with
Token with
Feature activation+0.015
Top resid features:
Islamic
Token Islamic
Feature activation+0.007
Top resid features:
State
Token State
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
even
Token even
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.124
Top resid features:
If
Token If
Feature activation+0.522
Top resid features:
there
Token there
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.175
Top resid features:
no
Token no
Feature activation+1.429
Top resid features:
money
Token money
Feature activation-0.088
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
pay
Token pay
Feature activation+0.006
Top resid features:
AV
Token AV
Feature activation+0.068
Top resid features:
research
Token research
Feature activation-0.047
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
with
Token with
Feature activation-0.064
Top resid features:
a
Token a
Feature activation+0.063
Top resid features:
bit
Token bit
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.190
Top resid features:
help
Token help
Feature activation+0.711
Top resid features:
from
Token from
Feature activation+0.588
Top resid features:
a
Token a
Feature activation+0.146
Top resid features:
high
Token high
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.022
Top resid features:
powered
Tokenpowered
Feature activation+0.172
Top resid features:
virtually
Token virtually
Feature activation+0.003
Top resid features:
impossible
Token impossible
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
reach
Token reach
Feature activation+0.006
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.105
Top resid features:
their
Tokentheir
Feature activation+1.692
Top resid features:
bewild
Token bewild
Feature activation+0.229
Top resid features:
er
Tokener
Feature activation-0.141
Top resid features:
ment
Tokenment
Feature activation+0.325
Top resid features:
deep
Token deep
Feature activation+0.000
Top resid features:
ened
Tokenened
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
were
Token were
Feature activation+0.057
Top resid features:
it
Token it
Feature activation+0.046
Top resid features:
not
Token not
Feature activation+0.305
Top resid features:
for
Token for
Feature activation+0.573
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
extremely
Token extremely
Feature activation+0.071
Top resid features:
courageous
Token courageous
Feature activation+0.055
Top resid features:
actions
Token actions
Feature activation+0.033
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
a
Token a
Feature activation-0.009
Top resid features:
decision
Token decision
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.045
Top resid features:
Whether
Token Whether
Feature activation+0.055
Top resid features:
that
Token that
Feature activation+0.144
Top resid features:
âĢ
TokenâĢ
Feature activation+1.371
Top resid features:
Ļ
TokenĻ
Feature activation+0.355
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.048
Top resid features:
rik
Tokenrik
Feature activation-0.085
Top resid features:
ar
Tokenar
Feature activation-0.010
Top resid features:
said
Token said
Feature activation-0.095
Top resid features:
Saturday
Token Saturday
Feature activation-0.476
Top resid features:
.
Token.
Feature activation-0.495
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.971
Top resid features:
rik
Tokenrik
Feature activation-0.033
Top resid features:
ar
Tokenar
Feature activation-0.030
Top resid features:
said
Token said
Feature activation-0.156
Top resid features:
Saturday
Token Saturday
Feature activation-0.855
Top resid features:
.
Token.
Feature activation-0.297
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.02

Head 2: 0.04

Head 3: 0.45

Head 4: 0.05

Head 5: 0.06

Head 6: 0.05

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.04

Head 11: 0.07

Positive logits

thood3.06

=-2.48

arbon2.40

ggy2.40

EStreamFrame2.40

illusion2.34

gha2.34

sein2.34

ptions2.33

ynthesis2.31

geoning2.30

collapses2.29

cious2.27

ndra2.22

historic2.19

ramid2.19

)2.17

ocaust2.15

izons2.12

nea2.11

Negative logits

collabor-2.62

notes-2.42

prepar-2.34

caveats-2.32

solic-2.29

METHOD-2.27

note-2.27

corrobor-2.27

congrat-2.18

noting-2.16

reperc-2.14

instructions-2.14

optionally-2.11

reciproc-2.09

urging-2.09

caveat-2.08

kindly-2.07

followed-2.07

ensuring-2.06

reiter-2.06

INTERVAL 4.896 - 5.440
CONTAINS 0.000%

ic
Tokenic
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460

INTERVAL 4.352 - 4.896
CONTAINS 0.000%

Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000

INTERVAL 3.808 - 4.352
CONTAINS 0.000%

workers
Tokenworkers
Feature activation+0.000
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000

INTERVAL 3.264 - 3.808
CONTAINS 0.000%

at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.720 - 3.264
CONTAINS 0.000%

,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000
."
Token."
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
informed
Tokeninformed
Feature activation+0.000

INTERVAL 2.176 - 2.720
CONTAINS 0.000%

eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919
an
Token an
Feature activation+0.460
act
Token act
Feature activation+0.050
of
Token of
Feature activation+0.000
murder
Token murder
Feature activation+0.000

INTERVAL 1.632 - 2.176
CONTAINS 0.000%

my
Token my
Feature activation+0.000
past
Token past
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000

INTERVAL 1.088 - 1.632
CONTAINS 0.000%

serv
Tokenserv
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Fuller
Token Fuller
Feature activation+0.000
,
Token,
Feature activation+1.215
this
Token this
Feature activation+5.440
offence
Token offence
Feature activation+2.657
could
Token could
Feature activation+4.631
have
Token have
Feature activation+2.522
become
Token become
Feature activation+2.919

INTERVAL 0.544 - 1.088
CONTAINS 0.000%

jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+4.290
I
Token I
Feature activation+3.434
may
Token may
Feature activation+2.018
have
Token have
Feature activation+3.052
fallen
Token fallen
Feature activation+0.896
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
informed
Tokeninformed
Feature activation+0.000
Worker
Token Worker
Feature activation+0.000

INTERVAL 0.000 - 0.544
CONTAINS 99.999%

Uni
Token Uni
Feature activation+0.000
Mas
TokenMas
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
L
TokenL
Feature activation+0.000
amp
Tokenamp
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
greedy
Token greedy
Feature activation+0.000
about
Token about
Feature activation+0.000
owning
Token owning
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
search
Token search
Feature activation+0.000
capacities
Token capacities
Feature activation+0.000
,
Token,
Feature activation+0.000
video
Token video
Feature activation+0.000
and
Token and
Feature activation+0.000
maps
Token maps
Feature activation+0.000
OS
TokenOS
Feature activation+0.000
to
Token to
Feature activation+0.000
Mason
Token Mason
Feature activation+0.000
Crosby
Token Crosby
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
reason
Token reason
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
reg
Token reg
Feature activation+0.000
rade
Tokenrade
Feature activation+0.000
the
Token the
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
Looking
Token Looking
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.000
tougher
Token tougher
Feature activation+0.000
migration
Token migration
Feature activation+0.000
control
Token control
Feature activation+0.000
the
Token the
Feature activation+0.000
core
Token core
Feature activation+0.000
aim
Token aim
Feature activation+0.000
.
Token.
Feature activation+0.000
Major
Token Major
Feature activation+0.000
security
Token security
Feature activation+0.000
and
Token and
Feature activation+0.000
weapons
Token weapons
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 H6.3: (feature 8195)

TOP ACTIVATIONS
MAX = 3.929

got
Token got
Feature activation+0.000
such
Token such
Feature activation+0.000
dri
Token dri
Feature activation+0.000
vel
Tokenvel
Feature activation+0.010
,
Token,
Feature activation+3.338
she
Token she
Feature activation+3.929
said
Token said
Feature activation+2.113
that
Token that
Feature activation+0.016
her
Token her
Feature activation+0.128
teacher
Token teacher
Feature activation+0.107
had
Token had
Feature activation+0.163
debate
Token debate
Feature activation+0.014
me
Token me
Feature activation+0.000
on
Token on
Feature activation+0.000
TV
Token TV
Feature activation+0.000
.
Token.
Feature activation+2.498
She
Token She
Feature activation+3.685
never
Token never
Feature activation+0.908
did
Token did
Feature activation+0.778
answer
Token answer
Feature activation+0.240
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
Face
Token Face
Feature activation+0.000
to
Token to
Feature activation+0.000
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+2.176
W
Token W
Feature activation+1.980
augh
Tokenaugh
Feature activation+3.404
replies
Token replies
Feature activation+1.775
"
Token "
Feature activation+0.000
P
TokenP
Feature activation+0.000
overty
Tokenoverty
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
virtual
Token virtual
Feature activation+0.000
reality
Token reality
Feature activation+0.000
,
Token,
Feature activation+1.190
to
Token to
Feature activation+1.716
which
Token which
Feature activation+3.389
he
Token he
Feature activation+1.735
replied
Token replied
Feature activation+1.580
:
Token:
Feature activation+0.464
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
B
TokenB
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Pact
Token Pact
Feature activation+0.000
,
Token,
Feature activation+1.261
and
Token and
Feature activation+3.353
only
Token only
Feature activation+0.901
about
Token about
Feature activation+0.398
2
Token 2
Feature activation+1.833
or
Token or
Feature activation+0.000
3
Token 3
Feature activation+0.305
she
Token she
Feature activation+0.000
got
Token got
Feature activation+0.000
such
Token such
Feature activation+0.000
dri
Token dri
Feature activation+0.000
vel
Tokenvel
Feature activation+0.010
,
Token,
Feature activation+3.338
she
Token she
Feature activation+3.929
said
Token said
Feature activation+2.113
that
Token that
Feature activation+0.016
her
Token her
Feature activation+0.128
teacher
Token teacher
Feature activation+0.107
about
Token about
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
operations
Token operations
Feature activation+0.000
in
Token in
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+3.247
had
Token had
Feature activation+2.301
two
Token two
Feature activation+2.080
standard
Token standard
Feature activation+0.902
responses
Token responses
Feature activation+2.331
:
Token:
Feature activation+0.027
early
Token early
Feature activation+0.000
sales
Token sales
Feature activation+0.000
were
Token were
Feature activation+0.000
going
Token going
Feature activation+0.000
the
Token the
Feature activation+2.507
response
Token response
Feature activation+3.223
was
Token was
Feature activation+1.882
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
well
Tokenwell
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
her
Token her
Feature activation+0.000
un
Token un
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
aven
Tokenaven
Feature activation+0.000
legs
Token legs
Feature activation+0.000
.
Token.
Feature activation+3.207
âĢ
Token âĢ
Feature activation+0.231
ľ
Tokenľ
Feature activation+0.028
He
TokenHe
Feature activation+1.508
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
on
Token on
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+2.051
He
Token He
Feature activation+3.207
art
Token art
Feature activation+0.000
lessly
Tokenlessly
Feature activation+1.678
d
Token d
Feature activation+0.000
ucked
Tokenucked
Feature activation+0.608
the
Token the
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+2.909
one
Token one
Feature activation+3.063
asked
Token asked
Feature activation+1.451
:
Token:
Feature activation+1.366
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.000
terrorism
Token terrorism
Feature activation+0.000
,
Token,
Feature activation+2.534
Cohen
Token Cohen
Feature activation+2.981
had
Token had
Feature activation+2.130
this
Token this
Feature activation+1.286
to
Token to
Feature activation+0.632
say
Token say
Feature activation+2.040
as
Token as
Feature activation+0.000
know
Token know
Feature activation+0.345
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+2.909
one
Token one
Feature activation+3.063
asked
Token asked
Feature activation+1.451
:
Token:
Feature activation+1.366
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
dist
Tokendist
Feature activation+0.000
orted
Tokenorted
Feature activation+0.000
,
Token,
Feature activation+0.232
âĢ
TokenâĢ
Feature activation+0.092
Ŀ
TokenĿ
Feature activation+1.756
Podesta
Token Podesta
Feature activation+2.844
said
Token said
Feature activation+0.368
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
A
TokenA
Feature activation+0.000
year
Token year
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+2.113
we
Token we
Feature activation+2.388
would
Token would
Feature activation+2.804
probably
Token probably
Feature activation+2.131
politely
Token politely
Feature activation+1.092
answer
Token answer
Feature activation+1.134
that
Token that
Feature activation+0.252
it
Token it
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
.
Token.
Feature activation+2.678
âĢ
TokenâĢ
Feature activation+0.263
Ŀ
TokenĿ
Feature activation+0.854
Ċ
TokenĊ
Feature activation+2.365
Ċ
TokenĊ
Feature activation+2.793
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.576
never
Token never
Feature activation+0.000
get
Token get
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
contradiction
Token contradiction
Feature activation+0.000
,
Token,
Feature activation+1.150
and
Token and
Feature activation+1.944
he
Token he
Feature activation+2.771
said
Token said
Feature activation+0.738
Sam
Token Sam
Feature activation+0.000
was
Token was
Feature activation+0.000
lying
Token lying
Feature activation+0.000
to
Token to
Feature activation+0.000
issues
Token issues
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Catal
Token Catal
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
.
Token.
Feature activation+2.689
Ċ
TokenĊ
Feature activation+2.597
Ċ
TokenĊ
Feature activation+2.613
"
Token"
Feature activation+1.321
If
TokenIf
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
true
Tokentrue
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
.
Token.
Feature activation+2.678
âĢ
TokenâĢ
Feature activation+0.263
Ŀ
TokenĿ
Feature activation+0.854
Ċ
TokenĊ
Feature activation+2.365
Ċ
TokenĊ
Feature activation+2.793
âĢ
TokenâĢ
Feature activation+0.000
d
Tokend
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
drink
Token drink
Feature activation+0.000
.
Token.
Feature activation+2.154
He
Token He
Feature activation+2.663
stood
Token stood
Feature activation+1.330
there
Token there
Feature activation+0.289
,
Token,
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 3.529

.
Token.
Feature activation+0.037
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
When
Token When
Feature activation-0.067
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
asked
Token asked
Feature activation+3.529
Top resid features:
her
Token her
Feature activation+0.217
Top resid features:
where
Token where
Feature activation+0.565
Top resid features:
she
Token she
Feature activation+0.049
Top resid features:
got
Token got
Feature activation+0.061
Top resid features:
such
Token such
Feature activation+0.024
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
released
Token released
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
asked
Token asked
Feature activation+3.158
Top resid features:
her
Token her
Feature activation+0.051
Top resid features:
if
Token if
Feature activation+0.825
Top resid features:
she
Token she
Feature activation+0.033
Top resid features:
would
Token would
Feature activation+0.063
Top resid features:
be
Token be
Feature activation+0.025
Top resid features:
ease
Token ease
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
studio
Token studio
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Asked
Token Asked
Feature activation+1.566
Top resid features:
by
Token by
Feature activation+1.054
Top resid features:
John
Token John
Feature activation+0.022
Top resid features:
Freeman
Token Freeman
Feature activation+0.038
Top resid features:
why
Token why
Feature activation+1.312
Top resid features:
he
Token he
Feature activation+0.056
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
We
TokenWe
Feature activation-0.008
Top resid features:
also
Token also
Feature activation-0.000
Top resid features:
asked
Token asked
Feature activation+2.562
Top resid features:
Matt
Token Matt
Feature activation+0.012
Top resid features:
G
Token G
Feature activation+0.002
Top resid features:
oss
Tokenoss
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
asked
Token asked
Feature activation+0.940
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
students
Token students
Feature activation+0.046
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
professors
Token professors
Feature activation+0.011
Top resid features:
if
Token if
Feature activation+2.568
Top resid features:
they
Token they
Feature activation+0.109
Top resid features:
believed
Token believed
Feature activation+0.034
Top resid features:
war
Token war
Feature activation+0.004
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
illegal
Token illegal
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ŀ
TokenĿ
Feature activation-0.010
Top resid features:
When
Token When
Feature activation-0.108
Top resid features:
I
Token I
Feature activation+0.036
Top resid features:
asked
Token asked
Feature activation+2.591
Top resid features:
her
Token her
Feature activation+0.308
Top resid features:
where
Token where
Feature activation+0.885
Top resid features:
she
Token she
Feature activation+0.088
Top resid features:
got
Token got
Feature activation+0.054
Top resid features:
such
Token such
Feature activation+0.074
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Democrats
TokenDemocrats
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
when
Token when
Feature activation-0.033
Top resid features:
asked
Token asked
Feature activation+1.487
Top resid features:
a
Token a
Feature activation+0.632
Top resid features:
question
Token question
Feature activation+1.021
Top resid features:
about
Token about
Feature activation+0.458
Top resid features:
Israeli
Token Israeli
Feature activation+0.023
Top resid features:
operations
Token operations
Feature activation+0.057
Top resid features:
on
Token on
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
When
Token When
Feature activation-0.015
Top resid features:
I
Token I
Feature activation+0.032
Top resid features:
asked
Token asked
Feature activation+3.102
Top resid features:
N
Token N
Feature activation+0.011
Top resid features:
ECA
TokenECA
Feature activation-0.013
Top resid features:
on
Token on
Feature activation+0.077
Top resid features:
twitter
Token twitter
Feature activation+0.094
Top resid features:
how
Token how
Feature activation+0.629
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
stage
Token stage
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
I
Token I
Feature activation+0.034
Top resid features:
ask
Token ask
Feature activation+2.047
Top resid features:
if
Token if
Feature activation+1.548
Top resid features:
Simon
Token Simon
Feature activation+0.007
Top resid features:
K
Token K
Feature activation-0.001
Top resid features:
one
Tokenone
Feature activation-0.008
Top resid features:
cki
Tokencki
Feature activation+0.002
Top resid features:
FBI
Token FBI
Feature activation-0.019
Top resid features:
Director
Token Director
Feature activation+0.007
Top resid features:
Robert
Token Robert
Feature activation-0.001
Top resid features:
Mueller
Token Mueller
Feature activation-0.020
Top resid features:
was
Token was
Feature activation+0.016
Top resid features:
asked
Token asked
Feature activation+2.593
Top resid features:
about
Token about
Feature activation+0.502
Top resid features:
Eric
Token Eric
Feature activation+0.011
Top resid features:
Holder
Token Holder
Feature activation+0.011
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
position
Token position
Feature activation+0.016
Top resid features:
?
Token?
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
When
TokenWhen
Feature activation-0.036
Top resid features:
we
Token we
Feature activation+0.006
Top resid features:
asked
Token asked
Feature activation+1.795
Top resid features:
readers
Token readers
Feature activation+0.216
Top resid features:
what
Token what
Feature activation+1.212
Top resid features:
they
Token they
Feature activation+0.095
Top resid features:
wanted
Token wanted
Feature activation+0.104
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
Georgia
Token Georgia
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Athens
Token Athens
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
When
Token When
Feature activation-0.103
Top resid features:
asked
Token asked
Feature activation+1.248
Top resid features:
a
Token a
Feature activation+0.969
Top resid features:
question
Token question
Feature activation+1.159
Top resid features:
about
Token about
Feature activation+0.267
Top resid features:
terrorism
Token terrorism
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
When
TokenWhen
Feature activation-0.086
Top resid features:
we
Token we
Feature activation+0.003
Top resid features:
asked
Token asked
Feature activation+1.395
Top resid features:
readers
Token readers
Feature activation+0.378
Top resid features:
what
Token what
Feature activation+1.421
Top resid features:
they
Token they
Feature activation+0.161
Top resid features:
wanted
Token wanted
Feature activation+0.117
Top resid features:
to
Token to
Feature activation+0.058
Top resid features:
know
Token know
Feature activation+0.148
Top resid features:
about
Token about
Feature activation+0.072
Top resid features:
Podesta
Token Podesta
Feature activation-0.002
Top resid features:
responded
Token responded
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Asked
TokenAsked
Feature activation+2.221
Top resid features:
what
Token what
Feature activation+1.105
Top resid features:
he
Token he
Feature activation+0.165
Top resid features:
meant
Token meant
Feature activation+0.075
Top resid features:
by
Token by
Feature activation+0.020
Top resid features:
âĢ
Token âĢ
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
If
TokenIf
Feature activation-0.002
Top resid features:
someone
Token someone
Feature activation+0.017
Top resid features:
were
Token were
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.048
Top resid features:
ask
Token ask
Feature activation+2.131
Top resid features:
us
Token us
Feature activation+0.657
Top resid features:
what
Token what
Feature activation+0.472
Top resid features:
year
Token year
Feature activation+0.094
Top resid features:
it
Token it
Feature activation+0.038
Top resid features:
was
Token was
Feature activation+0.037
Top resid features:
News
Token News
Feature activation+0.020
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
host
Token host
Feature activation+0.046
Top resid features:
Chris
Token Chris
Feature activation+0.004
Top resid features:
Wallace
Token Wallace
Feature activation+0.018
Top resid features:
asked
Token asked
Feature activation+1.955
Top resid features:
Cardinal
Token Cardinal
Feature activation-0.000
Top resid features:
Donald
Token Donald
Feature activation-0.007
Top resid features:
W
Token W
Feature activation+0.002
Top resid features:
uer
Tokenuer
Feature activation-0.003
Top resid features:
l
Tokenl
Feature activation+0.002
Top resid features:
save
Token save
Feature activation-0.005
Top resid features:
demon
Token demon
Feature activation+0.003
Top resid features:
Dean
Token Dean
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
We
Token We
Feature activation-0.008
Top resid features:
asked
Token asked
Feature activation+2.954
Top resid features:
Pad
Token Pad
Feature activation-0.001
Top resid features:
ale
Tokenale
Feature activation+0.002
Top resid features:
cki
Tokencki
Feature activation+0.013
Top resid features:
about
Token about
Feature activation+0.439
Top resid features:
this
Token this
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Finally
TokenFinally
Feature activation-0.038
Top resid features:
,
Token,
Feature activation-0.023
Top resid features:
Suarez
Token Suarez
Feature activation-0.002
Top resid features:
was
Token was
Feature activation-0.014
Top resid features:
asked
Token asked
Feature activation+1.601
Top resid features:
about
Token about
Feature activation+0.467
Top resid features:
whether
Token whether
Feature activation+0.622
Top resid features:
Luis
Token Luis
Feature activation+0.018
Top resid features:
Enrique
Token Enrique
Feature activation+0.017
Top resid features:
should
Token should
Feature activation+0.074
Top resid features:
Cardinal
Token Cardinal
Feature activation-0.001
Top resid features:
Donald
Token Donald
Feature activation-0.001
Top resid features:
W
Token W
Feature activation-0.002
Top resid features:
uer
Tokenuer
Feature activation-0.001
Top resid features:
l
Tokenl
Feature activation+0.004
Top resid features:
if
Token if
Feature activation+1.412
Top resid features:
Mormons
Token Mormons
Feature activation+0.015
Top resid features:
were
Token were
Feature activation+0.065
Top resid features:
âĢ
Token âĢ
Feature activation+0.027
Top resid features:
ľ
Tokenľ
Feature activation+0.017
Top resid features:
true
Tokentrue
Feature activation+0.007
Top resid features:
not
Token not
Feature activation-0.005
Top resid features:
interesting
Token interesting
Feature activation+0.017
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
me
Token me
Feature activation-0.012
Top resid features:
and
Token and
Feature activation-0.026
Top resid features:
asked
Token asked
Feature activation+1.356
Top resid features:
him
Token him
Feature activation+0.106
Top resid features:
what
Token what
Feature activation+1.350
Top resid features:
he
Token he
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.04

Head 3: 0.45

Head 4: 0.07

Head 5: 0.09

Head 6: 0.05

Head 7: 0.12

Head 8: 0.03

Head 9: 0.01

Head 10: 0.03

Head 11: 0.04

Positive logits

answered4.54

answer4.44

reply4.37

answers4.28

replied4.19

Answer4.04

replies4.02

Answer3.93

answer3.91

answering3.77

responded3.44

answ3.41

Answers3.26

swers3.16

response3.10

swer3.05

reply2.83

hesitated2.80

reluctantly2.79

answered2.77

Negative logits

arantine-2.49

inventoryQuantity-2.42

ongevity-2.18

Enhance-2.18

Saharan-2.17

Alias-2.17

Reviewer-2.13

enhances-2.11

issance-2.10

rastructure-2.05

enhance-2.04

impair-2.01

Includes-1.98

-1.93

-1.92

soDeliveryDate-1.88

Used-1.87

REUTERS-1.87

blot-1.86

disadvant-1.86

INTERVAL 3.536 - 3.929
CONTAINS 0.000%

debate
Token debate
Feature activation+0.014
me
Token me
Feature activation+0.000
on
Token on
Feature activation+0.000
TV
Token TV
Feature activation+0.000
.
Token.
Feature activation+2.498
She
Token She
Feature activation+3.685
never
Token never
Feature activation+0.908
did
Token did
Feature activation+0.778
answer
Token answer
Feature activation+0.240
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
got
Token got
Feature activation+0.000
such
Token such
Feature activation+0.000
dri
Token dri
Feature activation+0.000
vel
Tokenvel
Feature activation+0.010
,
Token,
Feature activation+3.338
she
Token she
Feature activation+3.929
said
Token said
Feature activation+2.113
that
Token that
Feature activation+0.016
her
Token her
Feature activation+0.128
teacher
Token teacher
Feature activation+0.107
had
Token had
Feature activation+0.163

INTERVAL 3.143 - 3.536
CONTAINS 0.001%

Face
Token Face
Feature activation+0.000
to
Token to
Feature activation+0.000
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+2.176
W
Token W
Feature activation+1.980
augh
Tokenaugh
Feature activation+3.404
replies
Token replies
Feature activation+1.775
"
Token "
Feature activation+0.000
P
TokenP
Feature activation+0.000
overty
Tokenoverty
Feature activation+0.000
.
Token.
Feature activation+0.000
B
TokenB
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Pact
Token Pact
Feature activation+0.000
,
Token,
Feature activation+1.261
and
Token and
Feature activation+3.353
only
Token only
Feature activation+0.901
about
Token about
Feature activation+0.398
2
Token 2
Feature activation+1.833
or
Token or
Feature activation+0.000
3
Token 3
Feature activation+0.305
early
Token early
Feature activation+0.000
sales
Token sales
Feature activation+0.000
were
Token were
Feature activation+0.000
going
Token going
Feature activation+0.000
the
Token the
Feature activation+2.507
response
Token response
Feature activation+3.223
was
Token was
Feature activation+1.882
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
well
Tokenwell
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
on
Token on
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+2.051
He
Token He
Feature activation+3.207
art
Token art
Feature activation+0.000
lessly
Tokenlessly
Feature activation+1.678
d
Token d
Feature activation+0.000
ucked
Tokenucked
Feature activation+0.608
the
Token the
Feature activation+0.000
about
Token about
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
operations
Token operations
Feature activation+0.000
in
Token in
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+3.247
had
Token had
Feature activation+2.301
two
Token two
Feature activation+2.080
standard
Token standard
Feature activation+0.902
responses
Token responses
Feature activation+2.331
:
Token:
Feature activation+0.027

INTERVAL 2.750 - 3.143
CONTAINS 0.001%

about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
contradiction
Token contradiction
Feature activation+0.000
,
Token,
Feature activation+1.150
and
Token and
Feature activation+1.944
he
Token he
Feature activation+2.771
said
Token said
Feature activation+0.738
Sam
Token Sam
Feature activation+0.000
was
Token was
Feature activation+0.000
lying
Token lying
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.345
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+2.909
one
Token one
Feature activation+3.063
asked
Token asked
Feature activation+1.451
:
Token:
Feature activation+1.366
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
.
Token.
Feature activation+2.678
âĢ
TokenâĢ
Feature activation+0.263
Ŀ
TokenĿ
Feature activation+0.854
Ċ
TokenĊ
Feature activation+2.365
Ċ
TokenĊ
Feature activation+2.793
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.576
never
Token never
Feature activation+0.000
get
Token get
Feature activation+0.000
year
Token year
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+2.113
we
Token we
Feature activation+2.388
would
Token would
Feature activation+2.804
probably
Token probably
Feature activation+2.131
politely
Token politely
Feature activation+1.092
answer
Token answer
Feature activation+1.134
that
Token that
Feature activation+0.252
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.000
terrorism
Token terrorism
Feature activation+0.000
,
Token,
Feature activation+2.534
Cohen
Token Cohen
Feature activation+2.981
had
Token had
Feature activation+2.130
this
Token this
Feature activation+1.286
to
Token to
Feature activation+0.632
say
Token say
Feature activation+2.040
as
Token as
Feature activation+0.000

INTERVAL 2.358 - 2.750
CONTAINS 0.003%

of
Token of
Feature activation+0.000
ET
Token ET
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+2.662
just
Token just
Feature activation+1.954
over
Token over
Feature activation+0.682
four
Token four
Feature activation+1.447
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
asked
Token asked
Feature activation+0.000
what
Token what
Feature activation+0.000
caused
Token caused
Feature activation+0.000
the
Token the
Feature activation+0.000
deaths
Token deaths
Feature activation+0.000
,
Token,
Feature activation+2.606
Gupta
Token Gupta
Feature activation+0.414
replied
Token replied
Feature activation+0.816
,
Token,
Feature activation+0.219
"
Token "
Feature activation+0.000
In
TokenIn
Feature activation+0.000
true
Tokentrue
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
.
Token.
Feature activation+2.678
âĢ
TokenâĢ
Feature activation+0.263
Ŀ
TokenĿ
Feature activation+0.854
Ċ
TokenĊ
Feature activation+2.365
Ċ
TokenĊ
Feature activation+2.793
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.576
never
Token never
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000
minister
Token minister
Feature activation+0.000
.
Token.
Feature activation+2.577
Ċ
TokenĊ
Feature activation+0.276
Ċ
TokenĊ
Feature activation+0.477
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Well
TokenWell
Feature activation+0.390
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.276
factual
Token factual
Feature activation+0.000
premise
Token premise
Feature activation+0.000
and
Token and
Feature activation+1.835
Spicer
Token Spicer
Feature activation+2.425
seemed
Token seemed
Feature activation+1.434
to
Token to
Feature activation+0.937
affirm
Token affirm
Feature activation+0.394
that
Token that
Feature activation+0.000
inaccurate
Token inaccurate
Feature activation+0.000

INTERVAL 1.965 - 2.358
CONTAINS 0.006%

but
Token but
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
perform
Token perform
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
.
Token.
Feature activation+2.160
Just
Token Just
Feature activation+1.397
over
Token over
Feature activation+0.523
half
Token half
Feature activation+1.308
,
Token,
Feature activation+0.452
53
Token 53
Feature activation+0.000
euro
Token euro
Feature activation+0.000
-
Token-
Feature activation+0.000
zone
Tokenzone
Feature activation+0.000
pronounce
Token pronounce
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
,
Token,
Feature activation+1.999
Mr
Token Mr
Feature activation+0.853
.
Token.
Feature activation+1.059
Sch
Token Sch
Feature activation+0.000
ull
Tokenull
Feature activation+0.000
er
Tokener
Feature activation+1.150
Sh
TokenSh
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
Fired
Token Fired
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.194
with
Token with
Feature activation+2.000
a
Token a
Feature activation+1.918
statement
Token statement
Feature activation+0.602
:
Token:
Feature activation+0.109
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
operations
Token operations
Feature activation+0.000
in
Token in
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+3.247
had
Token had
Feature activation+2.301
two
Token two
Feature activation+2.080
standard
Token standard
Feature activation+0.902
responses
Token responses
Feature activation+2.331
:
Token:
Feature activation+0.027
irritation
Token irritation
Feature activation+0.000
,
Token,
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
we
Token we
Feature activation+0.000
had
Token had
Feature activation+0.000
walked
Token walked
Feature activation+0.000
,
Token,
Feature activation+1.968
they
Token they
Feature activation+2.301
exclaimed
Token exclaimed
Feature activation+0.366
at
Token at
Feature activation+0.031
how
Token how
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.572 - 1.965
CONTAINS 0.008%

virtual
Token virtual
Feature activation+0.000
reality
Token reality
Feature activation+0.000
,
Token,
Feature activation+1.190
to
Token to
Feature activation+1.716
which
Token which
Feature activation+3.389
he
Token he
Feature activation+1.735
replied
Token replied
Feature activation+1.580
:
Token:
Feature activation+0.464
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
their
Token their
Feature activation+0.513
sources
Token sources
Feature activation+0.000
,
Token,
Feature activation+0.774
and
Token and
Feature activation+1.715
you
Token you
Feature activation+2.017
might
Token might
Feature activation+1.698
even
Token even
Feature activation+0.407
be
Token be
Feature activation+0.934
given
Token given
Feature activation+0.501
a
Token a
Feature activation+0.060
wall
Token wall
Feature activation+0.000
large
Token large
Feature activation+0.000
group
Token group
Feature activation+0.000
raised
Token raised
Feature activation+0.149
their
Token their
Feature activation+0.000
hands
Token hands
Feature activation+0.198
.
Token.
Feature activation+1.626
But
Token But
Feature activation+0.193
what
Token what
Feature activation+0.000
really
Token really
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
and
Token and
Feature activation+1.606
len
Token len
Feature activation+0.000
iency
Tokeniency
Feature activation+0.000
and
Token and
Feature activation+2.650
hastily
Token hastily
Feature activation+1.871
sign
Token sign
Feature activation+0.000
it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
sincerely
Token sincerely
Feature activation+0.000
.
Token.
Feature activation+0.000
Enrique
Token Enrique
Feature activation+0.000
should
Token should
Feature activation+0.000
continue
Token continue
Feature activation+0.000
as
Token as
Feature activation+0.000
coach
Token coach
Feature activation+0.000
and
Token and
Feature activation+1.948
whether
Token whether
Feature activation+0.485
the
Token the
Feature activation+0.000
club
Token club
Feature activation+0.000
should
Token should
Feature activation+0.000
sign
Token sign
Feature activation+0.000

INTERVAL 1.179 - 1.572
CONTAINS 0.014%

like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
drink
Token drink
Feature activation+0.000
.
Token.
Feature activation+2.154
He
Token He
Feature activation+2.663
stood
Token stood
Feature activation+1.330
there
Token there
Feature activation+0.289
,
Token,
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
and
Token and
Feature activation+0.000
caught
Token caught
Feature activation+0.000
they
Token they
Feature activation+0.153
think
Token think
Feature activation+0.001
of
Token of
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+1.649
The
Token The
Feature activation+1.316
most
Token most
Feature activation+0.707
popular
Token popular
Feature activation+0.880
words
Token words
Feature activation+0.217
were
Token were
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.528
Step
Token Step
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+1.550
Step
Token Step
Feature activation+0.110
2
Token 2
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
send
Token send
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
up
Token up
Feature activation+0.000
my
Token my
Feature activation+0.000
seat
Token seat
Feature activation+0.000
,
Token,
Feature activation+1.560
I
Token I
Feature activation+1.649
would
Token would
Feature activation+1.674
have
Token have
Feature activation+1.514
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
aven
Tokenaven
Feature activation+0.000
legs
Token legs
Feature activation+0.000
.
Token.
Feature activation+3.207
âĢ
Token âĢ
Feature activation+0.231
ľ
Tokenľ
Feature activation+0.028
He
TokenHe
Feature activation+1.508
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.786 - 1.179
CONTAINS 0.023%

to
Token to
Feature activation+0.000
threaten
Token threaten
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
.
Token.
Feature activation+1.531
Ċ
TokenĊ
Feature activation+0.624
Ċ
TokenĊ
Feature activation+0.953
KEY
TokenKEY
Feature activation+0.000
E
TokenE
Feature activation+0.000
TV
Token TV
Feature activation+0.000
asked
Token asked
Feature activation+0.012
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
nature
Token nature
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.946
Ċ
TokenĊ
Feature activation+0.404
Ċ
TokenĊ
Feature activation+0.187
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
s
Token s
Feature activation+0.000
omb
Tokenomb
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ros
Tokenros
Feature activation+0.000
they
Token they
Feature activation+1.641
were
Token were
Feature activation+0.914
am
Token am
Feature activation+0.032
icable
Tokenicable
Feature activation+0.440
in
Token in
Feature activation+0.000
doing
Token doing
Feature activation+0.000
so
Token so
Feature activation+0.000
passes
Token passes
Feature activation+0.000
from
Token from
Feature activation+0.000
Rodgers
Token Rodgers
Feature activation+0.000
.
Token.
Feature activation+0.658
Ċ
TokenĊ
Feature activation+0.612
Ċ
TokenĊ
Feature activation+0.842
P
TokenP
Feature activation+0.000
onder
Tokenonder
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Eva
Token Eva
Feature activation+0.000
asks
Token asks
Feature activation+0.052
.
Token.
Feature activation+0.846
Ċ
TokenĊ
Feature activation+1.187
Ċ
TokenĊ
Feature activation+0.403
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 0.393 - 0.786
CONTAINS 0.054%

managed
Token managed
Feature activation+0.000
,
Token,
Feature activation+1.905
they
Token they
Feature activation+1.524
found
Token found
Feature activation+0.952
that
Token that
Feature activation+0.456
the
Token the
Feature activation+0.420
citizen
Token citizen
Feature activation+0.000
scientists
Token scientists
Feature activation+0.270
had
Token had
Feature activation+0.163
strong
Token strong
Feature activation+0.000
views
Token views
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
counter
Token counter
Feature activation+0.000
-
Token-
Feature activation+0.000
terrorism
Tokenterrorism
Feature activation+0.000
.
Token.
Feature activation+0.502
You
Token You
Feature activation+0.109
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
no
Token no
Feature activation+0.000
asking
Token asking
Feature activation+0.000
me
Token me
Feature activation+0.000
about
Token about
Feature activation+0.000
homosexuality
Token homosexuality
Feature activation+0.000
too
Token too
Feature activation+0.000
?
Token?
Feature activation+0.659
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.172
Ram
Token Ram
Feature activation+0.000
id
Tokenid
Feature activation+0.000
asked
Token asked
Feature activation+0.386
:
Token:
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
replace
Token replace
Feature activation+0.000
them
Token them
Feature activation+0.000
?
Token?
Feature activation+0.547
Often
Token Often
Feature activation+0.704
the
Token the
Feature activation+0.382
answer
Token answer
Feature activation+0.834
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
her
Token her
Feature activation+0.000
son
Token son
Feature activation+0.000
in
Token in
Feature activation+0.317
the
Token the
Feature activation+0.066
clip
Token clip
Feature activation+0.000
,
Token,
Feature activation+0.461
before
Token before
Feature activation+0.506
promising
Token promising
Feature activation+0.355
to
Token to
Feature activation+0.000
'
Token '
Feature activation+0.000
try
Tokentry
Feature activation+0.000

INTERVAL 0.000 - 0.393
CONTAINS 99.892%

2
Token2
Feature activation+0.000
yellow
Token yellow
Feature activation+0.000
/
Token/
Feature activation+0.000
green
Tokengreen
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
sl
Token sl
Feature activation+0.000
udge
Tokenudge
Feature activation+0.000
must
Token must
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
critical
Token critical
Feature activation+0.000
all
Token all
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
products
Token products
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
ban
Token ban
Feature activation+0.000
on
Token on
Feature activation+0.000
advertising
Token advertising
Feature activation+0.000
would
Token would
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
what
Token what
Feature activation+0.000
desperation
Token desperation
Feature activation+0.000
is
Token is
Feature activation+0.000
until
Token until
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
.
Token.
Feature activation+0.000
testing
Token testing
Feature activation+0.000
what
Token what
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
nerve
Token nerve
Feature activation+0.000
gas
Token gas
Feature activation+0.000
on
Token on
Feature activation+0.000
two
Token two
Feature activation+0.000
comedians
Token comedians
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
director
Token director
Feature activation+0.000
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
film
Token film
Feature activation+0.000
only
Token only
Feature activation+0.000
to
Token to
Feature activation+0.318
have
Token have
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 H6.3: (feature 11800)

TOP ACTIVATIONS
MAX = 4.641

into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
-
Token-
Feature activation+0.000
If
Token If
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
I
Token I
Feature activation+4.629
am
Token am
Feature activation+2.340
happy
Token happy
Feature activation+3.564
to
Token to
Feature activation+1.389
do
Token do
Feature activation+1.011
it
Token it
Feature activation+0.464
those
Token those
Feature activation+0.051
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
.
Token.
Feature activation+0.000
pose
Tokenpose
Feature activation+0.017
those
Token those
Feature activation+0.051
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
If
Token If
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.722
,
Token,
Feature activation+4.122
we
Token we
Feature activation+4.102
give
Token give
Feature activation+1.775
ourselves
Token ourselves
Feature activation+0.256
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.722
,
Token,
Feature activation+4.122
we
Token we
Feature activation+4.102
give
Token give
Feature activation+1.775
ourselves
Token ourselves
Feature activation+0.256
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
shot
Token shot
Feature activation+0.086
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
I
Token I
Feature activation+4.629
am
Token am
Feature activation+2.340
happy
Token happy
Feature activation+3.564
to
Token to
Feature activation+1.389
do
Token do
Feature activation+1.011
it
Token it
Feature activation+0.464
.
Token.
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
an
Token an
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
over
Token over
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+2.579
that
Token that
Feature activation+3.324
's
Token's
Feature activation+2.553
even
Token even
Feature activation+1.136
better
Token better
Feature activation+1.180
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sport
Token sport
Feature activation+0.000
longer
Token longer
Feature activation+0.000
t
Token t
Feature activation+0.000
resses
Tokenresses
Feature activation+0.000
,
Token,
Feature activation+1.383
we
Token we
Feature activation+2.885
think
Token think
Feature activation+1.260
it
Token it
Feature activation+0.931
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.866
an
Token an
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
place
Token place
Feature activation+0.244
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
then
Token then
Feature activation+2.864
I
Token I
Feature activation+1.548
think
Token think
Feature activation+0.990
you
Token you
Feature activation+1.545
will
Token will
Feature activation+1.292
make
Token make
Feature activation+0.501
could
Token could
Feature activation+0.000
roll
Token roll
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+1.060
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+2.005
you
Token you
Feature activation+2.779
're
Token're
Feature activation+1.315
pretty
Token pretty
Feature activation+0.938
much
Token much
Feature activation+1.114
wasting
Token wasting
Feature activation+0.000
your
Token your
Feature activation+0.000
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
roll
Token roll
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+0.000
I
Token I
Feature activation+2.657
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+1.026
love
Token love
Feature activation+0.953
it
Token it
Feature activation+0.980
getting
Token getting
Feature activation+0.000
an
Token an
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
over
Token over
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+2.579
that
Token that
Feature activation+3.324
's
Token's
Feature activation+2.553
even
Token even
Feature activation+1.136
better
Token better
Feature activation+1.180
."
Token."
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
over
Token over
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+2.579
that
Token that
Feature activation+3.324
's
Token's
Feature activation+2.553
even
Token even
Feature activation+1.136
better
Token better
Feature activation+1.180
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
,
Token,
Feature activation+2.511
update
Token update
Feature activation+0.004
them
Token them
Feature activation+1.564
âĢĶ
TokenâĢĶ
Feature activation+0.000
conserv
Tokenconserv
Feature activation+0.000
atively
Tokenatively
Feature activation+0.000
roll
Token roll
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
stop
Token stop
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+2.039
it
Token it
Feature activation+2.481
will
Token will
Feature activation+2.431
be
Token be
Feature activation+2.366
his
Token his
Feature activation+0.625
Waterloo
Token Waterloo
Feature activation+0.000
,"
Token,"
Feature activation+0.000

Top DFA by src position
MAX = 4.296

Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
"
Token"
Feature activation+0.014
Top resid features:
If
TokenIf
Feature activation+0.030
Top resid features:
we
Token we
Feature activation+0.159
Top resid features:
can
Token can
Feature activation+4.296
Top resid features:
identify
Token identify
Feature activation+0.442
Top resid features:
genes
Token genes
Feature activation-0.013
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
neurological
Token neurological
Feature activation+0.014
Top resid features:
disorders
Token disorders
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
way
Token way
Feature activation+0.019
Top resid features:
-
Token-
Feature activation+0.032
Top resid features:
If
Token If
Feature activation+0.048
Top resid features:
I
Token I
Feature activation+0.205
Top resid features:
can
Token can
Feature activation+3.576
Top resid features:
help
Token help
Feature activation+1.726
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
am
Token am
Feature activation+0.000
Top resid features:
happy
Token happy
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
"
Token"
Feature activation+0.036
Top resid features:
If
TokenIf
Feature activation+0.017
Top resid features:
we
Token we
Feature activation+0.162
Top resid features:
can
Token can
Feature activation+4.212
Top resid features:
identify
Token identify
Feature activation+0.451
Top resid features:
genes
Token genes
Feature activation-0.029
Top resid features:
for
Token for
Feature activation-0.004
Top resid features:
neurological
Token neurological
Feature activation+0.017
Top resid features:
disorders
Token disorders
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
If
TokenIf
Feature activation+0.032
Top resid features:
we
Token we
Feature activation+0.157
Top resid features:
can
Token can
Feature activation+4.106
Top resid features:
identify
Token identify
Feature activation+0.333
Top resid features:
genes
Token genes
Feature activation-0.019
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
neurological
Token neurological
Feature activation+0.018
Top resid features:
disorders
Token disorders
Feature activation+0.045
Top resid features:
common
Token common
Feature activation-0.017
Top resid features:
goal
Token goal
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
If
Token If
Feature activation+0.008
Top resid features:
we
Token we
Feature activation+0.230
Top resid features:
can
Token can
Feature activation+3.627
Top resid features:
do
Token do
Feature activation+0.936
Top resid features:
that
Token that
Feature activation+0.367
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
common
Token common
Feature activation-0.012
Top resid features:
goal
Token goal
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
If
Token If
Feature activation+0.039
Top resid features:
we
Token we
Feature activation+0.147
Top resid features:
can
Token can
Feature activation+3.621
Top resid features:
do
Token do
Feature activation+0.924
Top resid features:
that
Token that
Feature activation+0.392
Top resid features:
,
Token,
Feature activation+0.155
Top resid features:
we
Token we
Feature activation-0.014
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
way
Token way
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
If
Token If
Feature activation+0.058
Top resid features:
I
Token I
Feature activation+0.392
Top resid features:
can
Token can
Feature activation+3.138
Top resid features:
help
Token help
Feature activation+1.050
Top resid features:
I
Token I
Feature activation-0.064
Top resid features:
am
Token am
Feature activation+0.026
Top resid features:
happy
Token happy
Feature activation-0.068
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
win
Token win
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
If
Token If
Feature activation+0.031
Top resid features:
you
Token you
Feature activation+0.104
Top resid features:
can
Token can
Feature activation+3.382
Top resid features:
'
Token '
Feature activation+0.154
Top resid features:
h
Tokenh
Feature activation+0.022
Top resid features:
urt
Tokenurt
Feature activation+0.001
Top resid features:
'
Token'
Feature activation+0.028
Top resid features:
someone
Token someone
Feature activation+0.063
Top resid features:
inspirational
Token inspirational
Feature activation-0.001
Top resid features:
A
Token A
Feature activation+0.004
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
l
Tokenl
Feature activation+0.004
Top resid features:
isters
Tokenisters
Feature activation+0.020
Top resid features:
can
Token can
Feature activation+3.568
Top resid features:
sport
Token sport
Feature activation+0.156
Top resid features:
longer
Token longer
Feature activation+0.012
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
resses
Tokenresses
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
urban
Token urban
Feature activation-0.001
Top resid features:
ism
Tokenism
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
if
Token if
Feature activation+0.002
Top resid features:
you
Token you
Feature activation+0.125
Top resid features:
can
Token can
Feature activation+2.510
Top resid features:
make
Token make
Feature activation+0.930
Top resid features:
a
Token a
Feature activation+0.165
Top resid features:
city
Token city
Feature activation+0.135
Top resid features:
centre
Token centre
Feature activation+0.087
Top resid features:
an
Token an
Feature activation+0.074
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
I
Token I
Feature activation-0.015
Top resid features:
swear
Token swear
Feature activation+0.032
Top resid features:
if
Token if
Feature activation-0.031
Top resid features:
she
Token she
Feature activation+0.133
Top resid features:
could
Token could
Feature activation+3.331
Top resid features:
roll
Token roll
Feature activation+0.381
Top resid features:
her
Token her
Feature activation+0.058
Top resid features:
eyes
Token eyes
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
she
Token she
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
crack
Token crack
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Unless
Token Unless
Feature activation-0.015
Top resid features:
you
Token you
Feature activation+0.036
Top resid features:
can
Token can
Feature activation+2.896
Top resid features:
beat
Token beat
Feature activation+0.492
Top resid features:
the
Token the
Feature activation+0.098
Top resid features:
Kitt
Token Kitt
Feature activation-0.003
Top resid features:
els
Tokenels
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
swear
Token swear
Feature activation+0.110
Top resid features:
if
Token if
Feature activation-0.066
Top resid features:
she
Token she
Feature activation+0.179
Top resid features:
could
Token could
Feature activation+3.368
Top resid features:
roll
Token roll
Feature activation+0.289
Top resid features:
her
Token her
Feature activation+0.063
Top resid features:
eyes
Token eyes
Feature activation-0.079
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
too
Token too
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
If
Token If
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.186
Top resid features:
fight
Token fight
Feature activation+0.059
Top resid features:
can
Token can
Feature activation+2.411
Top resid features:
be
Token be
Feature activation+0.645
Top resid features:
made
Token made
Feature activation+0.515
Top resid features:
I
Token I
Feature activation+0.025
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.026
Top resid features:
win
Token win
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
If
Token If
Feature activation+0.040
Top resid features:
you
Token you
Feature activation+0.095
Top resid features:
can
Token can
Feature activation+2.825
Top resid features:
'
Token '
Feature activation+0.220
Top resid features:
h
Tokenh
Feature activation+0.023
Top resid features:
urt
Tokenurt
Feature activation+0.005
Top resid features:
'
Token'
Feature activation+0.049
Top resid features:
someone
Token someone
Feature activation+0.062
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
win
Token win
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
If
Token If
Feature activation+0.015
Top resid features:
you
Token you
Feature activation+0.153
Top resid features:
can
Token can
Feature activation+2.724
Top resid features:
'
Token '
Feature activation+0.147
Top resid features:
h
Tokenh
Feature activation+0.038
Top resid features:
urt
Tokenurt
Feature activation+0.003
Top resid features:
'
Token'
Feature activation+0.015
Top resid features:
someone
Token someone
Feature activation+0.047
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
swear
Token swear
Feature activation+0.030
Top resid features:
if
Token if
Feature activation-0.019
Top resid features:
she
Token she
Feature activation+0.111
Top resid features:
could
Token could
Feature activation+2.704
Top resid features:
roll
Token roll
Feature activation+0.453
Top resid features:
her
Token her
Feature activation+0.055
Top resid features:
eyes
Token eyes
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
she
Token she
Feature activation+0.095
Top resid features:
models
Token models
Feature activation-0.117
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.051
Top resid features:
when
Token when
Feature activation+0.046
Top resid features:
they
Token they
Feature activation+0.149
Top resid features:
can
Token can
Feature activation+3.507
Top resid features:
,
Token,
Feature activation+0.117
Top resid features:
update
Token update
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.000
Top resid features:
conserv
Tokenconserv
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
swear
Token swear
Feature activation+0.034
Top resid features:
if
Token if
Feature activation-0.021
Top resid features:
she
Token she
Feature activation+0.138
Top resid features:
could
Token could
Feature activation+2.745
Top resid features:
roll
Token roll
Feature activation+0.453
Top resid features:
her
Token her
Feature activation+0.073
Top resid features:
eyes
Token eyes
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
she
Token she
Feature activation+0.076
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
"
Token "
Feature activation+0.046
Top resid features:
If
TokenIf
Feature activation+0.001
Top resid features:
we
Token we
Feature activation+0.138
Top resid features:
're
Token're
Feature activation+0.302
Top resid features:
able
Token able
Feature activation+1.556
Top resid features:
to
Token to
Feature activation+1.002
Top resid features:
stop
Token stop
Feature activation+0.260
Top resid features:
Obama
Token Obama
Feature activation+0.032
Top resid features:
on
Token on
Feature activation-0.030
Top resid features:
this
Token this
Feature activation+0.057
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.03

Head 3: 0.44

Head 4: 0.04

Head 5: 0.08

Head 6: 0.06

Head 7: 0.12

Head 8: 0.04

Head 9: 0.01

Head 10: 0.02

Head 11: 0.05

Positive logits

improves2.60

avier2.41

redits2.10

gravy2.06

disadvantages2.05

thens2.04

would2.02

unbeat2.01

Tigers2.01

outweigh1.98

empowering1.94

strengthens1.94

improved1.94

better1.93

orest1.92

roses1.90

advantages1.90

improve1.90

unstoppable1.89

satisfying1.87

Negative logits

tyard-2.26

livious-2.22

ewitness-2.13

nai-1.98

discrep-1.96

tions-1.95

-1.93

unct-1.92

thouse-1.91

uscript-1.90

referen-1.88

govtrack-1.86

unpublished-1.84

incorrectly-1.84

spurious-1.83

pleaded-1.82

arium-1.82

comment-1.82

hoe-1.82

atan-1.81

INTERVAL 4.177 - 4.641
CONTAINS 0.000%

-
Token-
Feature activation+0.000
If
Token If
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
I
Token I
Feature activation+4.629
am
Token am
Feature activation+2.340
happy
Token happy
Feature activation+3.564
to
Token to
Feature activation+1.389
do
Token do
Feature activation+1.011
it
Token it
Feature activation+0.464
those
Token those
Feature activation+0.051
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
.
Token.
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 3.713 - 4.177
CONTAINS 0.000%

If
Token If
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.722
,
Token,
Feature activation+4.122
we
Token we
Feature activation+4.102
give
Token give
Feature activation+1.775
ourselves
Token ourselves
Feature activation+0.256
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.722
,
Token,
Feature activation+4.122
we
Token we
Feature activation+4.102
give
Token give
Feature activation+1.775
ourselves
Token ourselves
Feature activation+0.256
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
shot
Token shot
Feature activation+0.086
pose
Tokenpose
Feature activation+0.017
those
Token those
Feature activation+0.051
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
monkey
Token monkey
Feature activation+0.036
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710

INTERVAL 3.249 - 3.713
CONTAINS 0.000%

I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
I
Token I
Feature activation+4.629
am
Token am
Feature activation+2.340
happy
Token happy
Feature activation+3.564
to
Token to
Feature activation+1.389
do
Token do
Feature activation+1.011
it
Token it
Feature activation+0.464
.
Token.
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
an
Token an
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
over
Token over
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+2.579
that
Token that
Feature activation+3.324
's
Token's
Feature activation+2.553
even
Token even
Feature activation+1.136
better
Token better
Feature activation+1.180
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.785 - 3.249
CONTAINS 0.000%

an
Token an
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
place
Token place
Feature activation+0.244
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
then
Token then
Feature activation+2.864
I
Token I
Feature activation+1.548
think
Token think
Feature activation+0.990
you
Token you
Feature activation+1.545
will
Token will
Feature activation+1.292
make
Token make
Feature activation+0.501
could
Token could
Feature activation+0.000
roll
Token roll
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sport
Token sport
Feature activation+0.000
longer
Token longer
Feature activation+0.000
t
Token t
Feature activation+0.000
resses
Tokenresses
Feature activation+0.000
,
Token,
Feature activation+1.383
we
Token we
Feature activation+2.885
think
Token think
Feature activation+1.260
it
Token it
Feature activation+0.931
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.866

INTERVAL 2.320 - 2.785
CONTAINS 0.002%

improvis
Token improvis
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
again
Token again
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+2.321
I
Token I
Feature activation+2.454
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+1.128
do
Token do
Feature activation+1.138
my
Token my
Feature activation+0.000
stop
Token stop
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+2.039
it
Token it
Feature activation+2.481
will
Token will
Feature activation+2.431
be
Token be
Feature activation+2.366
his
Token his
Feature activation+0.625
Waterloo
Token Waterloo
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
roll
Token roll
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+2.039
it
Token it
Feature activation+2.481
will
Token will
Feature activation+2.431
be
Token be
Feature activation+2.366
his
Token his
Feature activation+0.625
Waterloo
Token Waterloo
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+2.758
she
Token she
Feature activation+2.785
would
Token would
Feature activation+2.503
have
Token have
Feature activation+2.553
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000

INTERVAL 1.856 - 2.320
CONTAINS 0.001%

me
Token me
Feature activation+0.000
,
Token,
Feature activation+1.643
or
Token or
Feature activation+0.000
tips
Token tips
Feature activation+0.000
,
Token,
Feature activation+0.291
it
Token it
Feature activation+2.152
's
Token's
Feature activation+1.514
great
Token great
Feature activation+0.674
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.035
work
Token work
Feature activation+0.000
,
Token,
Feature activation+1.875
they
Token they
Feature activation+1.528
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.867
leave
Token leave
Feature activation+0.288
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+2.039
it
Token it
Feature activation+2.481
will
Token will
Feature activation+2.431
be
Token be
Feature activation+2.366
his
Token his
Feature activation+0.625
Waterloo
Token Waterloo
Feature activation+0.000
people
Token people
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
reach
Token reach
Feature activation+0.000
,
Token,
Feature activation+0.853
the
Token the
Feature activation+2.117
stronger
Token stronger
Feature activation+1.257
the
Token the
Feature activation+0.139
64
Token 64
Feature activation+0.000
community
Token community
Feature activation+0.018
becomes
Token becomes
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
double
Token double
Feature activation+0.000
,
Token,
Feature activation+2.076
he
Token he
Feature activation+1.882
would
Token would
Feature activation+2.224
be
Token be
Feature activation+1.808
SN
Token SN
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
OP
Token OP
Feature activation+0.000

INTERVAL 1.392 - 1.856
CONTAINS 0.002%

remain
Token remain
Feature activation+0.000
uncomp
Token uncomp
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
,
Token,
Feature activation+1.140
then
Token then
Feature activation+1.501
you
Token you
Feature activation+1.312
can
Token can
Feature activation+0.754
use
Token use
Feature activation+0.154
a
Token a
Feature activation+0.000
software
Token software
Feature activation+0.000
it
Token it
Feature activation+4.154
would
Token would
Feature activation+4.459
be
Token be
Feature activation+4.641
of
Token of
Feature activation+1.657
massive
Token massive
Feature activation+0.554
benefit
Token benefit
Feature activation+1.710
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
know
Token know
Feature activation+0.000
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
then
Token then
Feature activation+2.864
I
Token I
Feature activation+1.548
think
Token think
Feature activation+0.990
you
Token you
Feature activation+1.545
will
Token will
Feature activation+1.292
make
Token make
Feature activation+0.501
it
Token it
Feature activation+0.006
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
place
Token place
Feature activation+0.244
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
then
Token then
Feature activation+2.864
I
Token I
Feature activation+1.548
think
Token think
Feature activation+0.990
you
Token you
Feature activation+1.545
will
Token will
Feature activation+1.292
make
Token make
Feature activation+0.501
it
Token it
Feature activation+0.006
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
island
Token island
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.098
will
Token will
Feature activation+1.480
automatically
Token automatically
Feature activation+0.377
be
Token be
Feature activation+0.502
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.928 - 1.392
CONTAINS 0.004%

place
Token place
Feature activation+0.244
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
then
Token then
Feature activation+2.864
I
Token I
Feature activation+1.548
think
Token think
Feature activation+0.990
you
Token you
Feature activation+1.545
will
Token will
Feature activation+1.292
make
Token make
Feature activation+0.501
it
Token it
Feature activation+0.006
a
Token a
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
,
Token,
Feature activation+0.863
the
Token the
Feature activation+1.396
Federal
Token Federal
Feature activation+0.059
Aviation
Token Aviation
Feature activation+0.000
Administration
Token Administration
Feature activation+1.173
could
Token could
Feature activation+1.307
withhold
Token withhold
Feature activation+0.506
a
Token a
Feature activation+0.000
launch
Token launch
Feature activation+0.000
license
Token license
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
give
Token give
Feature activation+0.000
will
Token will
Feature activation+1.278
undoubtedly
Token undoubtedly
Feature activation+0.525
be
Token be
Feature activation+0.743
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
could
Token could
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
data
Token data
Feature activation+0.204
âĢĶ
TokenâĢĶ
Feature activation+1.044
and
Tokenand
Feature activation+0.000
also
Token also
Feature activation+0.000
their
Token their
Feature activation+0.000
cost
Token cost
Feature activation+0.000
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.000
I
Token I
Feature activation+2.657
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+1.026
love
Token love
Feature activation+0.953
it
Token it
Feature activation+0.980
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
bring
Token bring
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000

INTERVAL 0.464 - 0.928
CONTAINS 0.006%

ang
Tokenang
Feature activation+0.000
w
Tokenw
Feature activation+0.000
ala
Tokenala
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
team
Token team
Feature activation+0.490
began
Token began
Feature activation+0.132
exploring
Token exploring
Feature activation+0.000
methods
Token methods
Feature activation+0.000
for
Token for
Feature activation+0.000
making
Token making
Feature activation+0.000
were
Token were
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
information
Token information
Feature activation+0.000
,
Token,
Feature activation+0.491
they
Token they
Feature activation+0.889
found
Token found
Feature activation+0.000
big
Token big
Feature activation+0.000
premium
Token premium
Feature activation+0.000
increases
Token increases
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
Volunteer
Token Volunteer
Feature activation+0.000
association
Token association
Feature activation+0.000
can
Token can
Feature activation+0.000
-
Token-
Feature activation+0.578
please
Tokenplease
Feature activation+1.045
donate
Token donate
Feature activation+0.799
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
powered
Tokenpowered
Feature activation+0.000
microscope
Token microscope
Feature activation+0.000
,
Token,
Feature activation+0.537
these
Token these
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
"
Token "
Feature activation+0.000
te
Tokente
Feature activation+0.000
eth
Tokeneth
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
plan
Token plan
Feature activation+0.000
I
Token I
Feature activation+0.872
'm
Token'm
Feature activation+0.773
sure
Token sure
Feature activation+0.759
he
Token he
Feature activation+0.325
's
Token's
Feature activation+0.000
got
Token got
Feature activation+0.000

INTERVAL 0.000 - 0.464
CONTAINS 99.984%

.
Token.
Feature activation+0.000
Cle
Token Cle
Feature activation+0.000
m
Tokenm
Feature activation+0.000
enjoyed
Token enjoyed
Feature activation+0.000
a
Token a
Feature activation+0.000
successful
Token successful
Feature activation+0.000
second
Token second
Feature activation+0.000
military
Token military
Feature activation+0.000
career
Token career
Feature activation+0.000
,
Token,
Feature activation+0.000
rising
Token rising
Feature activation+0.000
message
Token message
Feature activation+0.000
of
Token of
Feature activation+0.000
defiance
Token defiance
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
and
Token and
Feature activation+0.000
South
Token South
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
conduct
Token conduct
Feature activation+0.000
war
Token war
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ear
Tokenear
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
fr
Tokenfr
Feature activation+0.000
ustration
Tokenustration
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+0.000
threatening
Token threatening
Feature activation+0.000
in
Token in
Feature activation+0.000
society
Token society
Feature activation+0.000
(
Token (
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
www
Tokenwww
Feature activation+0.000
.
Token.
Feature activation+0.000
natural
Tokennatural
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
low
Token low
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
priority
Token priority
Feature activation+0.000
list
Token list
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
Obamacare
Token Obamacare
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