H3.11 top features

Top feature 0 in H3.11: (feature 7276)

TOP ACTIVATIONS
MAX = 4.837

the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.631
AP
Token AP
Feature activation+0.583
K
TokenK
Feature activation+0.000
,
Token,
Feature activation+3.177
but
Token but
Feature activation+4.819
everything
Token everything
Feature activation+0.547
looks
Token looks
Feature activation+0.000
different
Token different
Feature activation+0.000
because
Token because
Feature activation+0.000
apps
Token apps
Feature activation+0.000
will
Token will
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.105
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+4.578
and
Token and
Feature activation+0.208
over
Token over
Feature activation+3.837
again
Token again
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.199
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.045
thing
Token thing
Feature activation+2.484
over
Token over
Feature activation+4.429
and
Token and
Feature activation+0.759
over
Token over
Feature activation+3.487
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
perform
Token perform
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.208
services
Token services
Feature activation+1.554
but
Token but
Feature activation+4.415
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+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.068
policy
Token policy
Feature activation+1.744
applied
Token applied
Feature activation+4.337
to
Token to
Feature activation+2.155
a
Token a
Feature activation+0.035
family
Token family
Feature activation+0.000
with
Token with
Feature activation+0.000
only
Token only
Feature activation+0.279
I
Token I
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
point
Token point
Feature activation+2.153
about
Token about
Feature activation+4.228
flat
Token flat
Feature activation+0.000
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+0.000
in
Token in
Feature activation+0.000
books
Token books
Feature activation+0.000
Y
Token Y
Feature activation+0.000
I
TokenI
Feature activation+0.000
HI
TokenHI
Feature activation+0.000
CH
Token CH
Feature activation+0.000
IP
TokenIP
Feature activation+0.000
but
Token but
Feature activation+4.227
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
see
Token see
Feature activation+0.000
some
Token some
Feature activation+0.000
similarities
Token similarities
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.422
Pant
Token Pant
Feature activation+1.914
one
Tokenone
Feature activation+1.273
color
Token color
Feature activation+2.621
when
Token when
Feature activation+4.171
rec
Token rec
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
that
Token that
Feature activation+0.000
logo
Token logo
Feature activation+0.000
.
Token.
Feature activation+1.340
covers
Token covers
Feature activation+0.000
are
Token are
Feature activation+0.000
basically
Token basically
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.203
except
Token except
Feature activation+4.014
they
Token they
Feature activation+0.620
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
telling
Token telling
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
story
Token story
Feature activation+1.597
,
Token,
Feature activation+2.137
but
Token but
Feature activation+4.014
whereas
Token whereas
Feature activation+0.000
the
Token the
Feature activation+0.000
partner
Token partner
Feature activation+0.000
is
Token is
Feature activation+0.000
simply
Token simply
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
material
Token material
Feature activation+1.339
could
Token could
Feature activation+3.150
be
Token be
Feature activation+3.888
used
Token used
Feature activation+3.984
in
Token in
Feature activation+2.070
cars
Token cars
Feature activation+0.068
,
Token,
Feature activation+0.680
p
Token p
Feature activation+0.000
ips
Tokenips
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
material
Token material
Feature activation+1.339
could
Token could
Feature activation+3.150
be
Token be
Feature activation+3.888
used
Token used
Feature activation+3.984
in
Token in
Feature activation+2.070
cars
Token cars
Feature activation+0.068
,
Token,
Feature activation+0.680
p
Token p
Feature activation+0.000
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
roles
Token roles
Feature activation+1.931
apply
Token apply
Feature activation+3.870
as
Token as
Feature activation+1.132
is
Token is
Feature activation+1.777
ordained
Token ordained
Feature activation+0.361
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.104
site
Token site
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
process
Token process
Feature activation+1.617
but
Token but
Feature activation+3.864
whether
Token whether
Feature activation+0.077
Swe
Token Swe
Feature activation+0.000
fil
Tokenfil
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
will
Token will
Feature activation+0.000
taking
Token taking
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
route
Token route
Feature activation+1.320
,
Token,
Feature activation+2.110
but
Token but
Feature activation+3.847
both
Token both
Feature activation+0.000
airlines
Token airlines
Feature activation+0.000
later
Token later
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
they
Token they
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.105
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+4.578
and
Token and
Feature activation+0.208
over
Token over
Feature activation+3.837
again
Token again
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.199
same
Token same
Feature activation+0.000
person
Token person
Feature activation+0.000
naturally
Token naturally
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.401
is
Token is
Feature activation+2.369
true
Token true
Feature activation+3.777
of
Token of
Feature activation+1.320
making
Token making
Feature activation+0.000
games
Token games
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
feelings
Token feelings
Feature activation+1.986
about
Token about
Feature activation+3.739
it
Token it
Feature activation+0.961
that
Token that
Feature activation+0.000
Churchill
Token Churchill
Feature activation+0.000
did
Token did
Feature activation+0.000
about
Token about
Feature activation+1.354
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.032
can
Token can
Feature activation+1.578
be
Token be
Feature activation+2.659
said
Token said
Feature activation+3.620
for
Token for
Feature activation+1.939
sophomore
Token sophomore
Feature activation+0.000
Aust
Token Aust
Feature activation+0.000
on
Tokenon
Feature activation+0.000
B
Token B
Feature activation+0.000
Researchers
Token Researchers
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.546
are
Token are
Feature activation+3.610
active
Token active
Feature activation+0.485
during
Token during
Feature activation+0.644
both
Token both
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.049

Top DFA by src position
MAX = 5.395

CS
TokenCS
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
It
Token It
Feature activation-0.016
Top resid features:
's
Token's
Feature activation-0.025
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
same
Token same
Feature activation+5.395
Top resid features:
AP
Token AP
Feature activation-0.080
Top resid features:
K
TokenK
Feature activation-0.060
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
but
Token but
Feature activation-0.052
Top resid features:
everything
Token everything
Feature activation+0.000
Top resid features:
cers
Tokencers
Feature activation+0.016
Top resid features:
who
Token who
Feature activation+0.033
Top resid features:
will
Token will
Feature activation-0.013
Top resid features:
use
Token use
Feature activation-0.014
Top resid features:
the
Token the
Feature activation-0.058
Top resid features:
same
Token same
Feature activation+5.045
Top resid features:
needle
Token needle
Feature activation-0.085
Top resid features:
over
Token over
Feature activation+0.116
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
insanity
Token insanity
Feature activation+0.022
Top resid features:
is
Token is
Feature activation+0.036
Top resid features:
doing
Token doing
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.118
Top resid features:
same
Token same
Feature activation+4.812
Top resid features:
thing
Token thing
Feature activation+0.019
Top resid features:
over
Token over
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
community
Token community
Feature activation-0.010
Top resid features:
clinics
Token clinics
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.159
Top resid features:
perform
Token perform
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.044
Top resid features:
same
Token same
Feature activation+5.238
Top resid features:
services
Token services
Feature activation-0.009
Top resid features:
but
Token but
Feature activation-0.056
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
perform
Token perform
Feature activation+0.000
Top resid features:
all
Token all
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
The
TokenThe
Feature activation-0.109
Top resid features:
same
Token same
Feature activation+4.641
Top resid features:
policy
Token policy
Feature activation+0.108
Top resid features:
applied
Token applied
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
ly
Tokenly
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
I
Token I
Feature activation+0.053
Top resid features:
made
Token made
Feature activation-0.058
Top resid features:
the
Token the
Feature activation-0.087
Top resid features:
same
Token same
Feature activation+4.183
Top resid features:
point
Token point
Feature activation+0.288
Top resid features:
about
Token about
Feature activation+0.210
Top resid features:
flat
Token flat
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
sharing
Tokensharing
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation-0.031
Top resid features:
think
Token think
Feature activation+0.112
Top resid features:
it
Token it
Feature activation+0.016
Top resid features:
works
Token works
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
same
Token same
Feature activation+4.808
Top resid features:
way
Token way
Feature activation+0.078
Top resid features:
as
Token as
Feature activation-0.067
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
Y
Token Y
Feature activation-0.027
Top resid features:
I
TokenI
Feature activation+0.004
Top resid features:
com
Tokencom
Feature activation-0.021
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
I
Token I
Feature activation-0.052
Top resid features:
used
Token used
Feature activation-0.043
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
same
Token same
Feature activation+4.596
Top resid features:
Pant
Token Pant
Feature activation-0.058
Top resid features:
one
Tokenone
Feature activation-0.006
Top resid features:
color
Token color
Feature activation-0.064
Top resid features:
when
Token when
Feature activation+0.220
Top resid features:
rec
Token rec
Feature activation+0.000
Top resid features:
release
Token release
Feature activation+0.011
Top resid features:
covers
Token covers
Feature activation+0.015
Top resid features:
are
Token are
Feature activation-0.006
Top resid features:
basically
Token basically
Feature activation+0.015
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
same
Token same
Feature activation+4.460
Top resid features:
except
Token except
Feature activation-0.070
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
don
Token don
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:
Ļ
TokenĻ
Feature activation-0.030
Top resid features:
re
Tokenre
Feature activation-0.019
Top resid features:
both
Token both
Feature activation-0.037
Top resid features:
telling
Token telling
Feature activation-0.021
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
same
Token same
Feature activation+4.496
Top resid features:
story
Token story
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
but
Token but
Feature activation-0.100
Top resid features:
whereas
Token whereas
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.037
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
earth
Token earth
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.077
Top resid features:
same
Token same
Feature activation+4.364
Top resid features:
material
Token material
Feature activation-0.120
Top resid features:
could
Token could
Feature activation+0.254
Top resid features:
be
Token be
Feature activation-0.118
Top resid features:
used
Token used
Feature activation+0.031
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.055
Top resid features:
on
Token on
Feature activation+0.026
Top resid features:
earth
Token earth
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
the
Token the
Feature activation-0.139
Top resid features:
same
Token same
Feature activation+4.148
Top resid features:
material
Token material
Feature activation-0.118
Top resid features:
could
Token could
Feature activation+0.210
Top resid features:
be
Token be
Feature activation+0.012
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.001
Top resid features:
In
Token In
Feature activation+0.065
Top resid features:
society
Token society
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
the
Token the
Feature activation-0.133
Top resid features:
same
Token same
Feature activation+4.238
Top resid features:
roles
Token roles
Feature activation-0.018
Top resid features:
apply
Token apply
Feature activation+0.029
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
ordained
Token ordained
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.079
Top resid features:
streaming
Token streaming
Feature activation-0.020
Top resid features:
site
Token site
Feature activation-0.013
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
same
Token same
Feature activation+4.684
Top resid features:
process
Token process
Feature activation+0.045
Top resid features:
but
Token but
Feature activation-0.086
Top resid features:
whether
Token whether
Feature activation+0.000
Top resid features:
Swe
Token Swe
Feature activation+0.000
Top resid features:
fil
Tokenfil
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.451
Top resid features:
as
Token as
Feature activation-0.129
Top resid features:
taking
Token taking
Feature activation-0.052
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
same
Token same
Feature activation+4.528
Top resid features:
route
Token route
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
but
Token but
Feature activation-0.154
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
airlines
Token airlines
Feature activation+0.000
Top resid features:
cers
Tokencers
Feature activation+0.013
Top resid features:
who
Token who
Feature activation+0.007
Top resid features:
will
Token will
Feature activation-0.008
Top resid features:
use
Token use
Feature activation-0.033
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
same
Token same
Feature activation+4.428
Top resid features:
needle
Token needle
Feature activation-0.036
Top resid features:
over
Token over
Feature activation+0.101
Top resid features:
and
Token and
Feature activation-0.152
Top resid features:
over
Token over
Feature activation+0.111
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
happens
Token happens
Feature activation+0.004
Top resid features:
so
Token so
Feature activation+0.002
Top resid features:
naturally
Token naturally
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.094
Top resid features:
The
Token The
Feature activation-0.154
Top resid features:
same
Token same
Feature activation+4.201
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
true
Token true
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
critics
Token critics
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
We
Token We
Feature activation+0.035
Top resid features:
have
Token have
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.079
Top resid features:
same
Token same
Feature activation+3.937
Top resid features:
feelings
Token feelings
Feature activation+0.178
Top resid features:
about
Token about
Feature activation+0.116
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Churchill
Token Churchill
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
weekend
Token weekend
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
while
Token while
Feature activation-0.066
Top resid features:
the
Token the
Feature activation-0.159
Top resid features:
same
Token same
Feature activation+4.395
Top resid features:
can
Token can
Feature activation+0.245
Top resid features:
be
Token be
Feature activation-0.210
Top resid features:
said
Token said
Feature activation-0.133
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
sophomore
Token sophomore
Feature activation+0.000
Top resid features:
game
Token game
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Researchers
Token Researchers
Feature activation-0.031
Top resid features:
think
Token think
Feature activation+0.098
Top resid features:
the
Token the
Feature activation-0.167
Top resid features:
same
Token same
Feature activation+4.022
Top resid features:
neurons
Token neurons
Feature activation-0.122
Top resid features:
are
Token are
Feature activation+0.109
Top resid features:
active
Token active
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.06

Head 3: 0.02

Head 4: 0.02

Head 5: 0.04

Head 6: 0.05

Head 7: 0.06

Head 8: 0.04

Head 9: 0.05

Head 10: 0.07

Head 11: 0.52

Positive logits

same1.77

Same1.65

kefeller1.44

Berm1.42

Same1.34

afia1.27

WithNo1.27

DAQ1.25

soever1.25

ablishment1.16

Neurolog1.16

NEY1.15

:\1.14

Bottom1.14

CentOS1.11

nor1.10

same1.09

eton1.09

Unix1.08

1.08

Negative logits

skirts-1.27

stabilized-1.16

reservoirs-1.12

exacerbate-1.11

calcul-1.11

deserts-1.10

Samar-1.09

escal-1.09

pal-1.07

elephants-1.07

gardens-1.06

pets-1.06

helicop-1.06

izons-1.06

gif-1.05

iti-1.05

plac-1.05

sufficiently-1.04

kin-1.04

caches-1.03

INTERVAL 4.353 - 4.837
CONTAINS 0.001%

the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.631
AP
Token AP
Feature activation+0.583
K
TokenK
Feature activation+0.000
,
Token,
Feature activation+3.177
but
Token but
Feature activation+4.819
everything
Token everything
Feature activation+0.547
looks
Token looks
Feature activation+0.000
different
Token different
Feature activation+0.000
because
Token because
Feature activation+0.000
apps
Token apps
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.045
thing
Token thing
Feature activation+2.484
over
Token over
Feature activation+4.429
and
Token and
Feature activation+0.759
over
Token over
Feature activation+3.487
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.105
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+4.578
and
Token and
Feature activation+0.208
over
Token over
Feature activation+3.837
again
Token again
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.199
that
Token that
Feature activation+0.000
perform
Token perform
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.208
services
Token services
Feature activation+1.554
but
Token but
Feature activation+4.415
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+0.000

INTERVAL 3.870 - 4.353
CONTAINS 0.001%

society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
roles
Token roles
Feature activation+1.931
apply
Token apply
Feature activation+3.870
as
Token as
Feature activation+1.132
is
Token is
Feature activation+1.777
ordained
Token ordained
Feature activation+0.361
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.104
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.068
policy
Token policy
Feature activation+1.744
applied
Token applied
Feature activation+4.337
to
Token to
Feature activation+2.155
a
Token a
Feature activation+0.035
family
Token family
Feature activation+0.000
with
Token with
Feature activation+0.000
only
Token only
Feature activation+0.279
Y
Token Y
Feature activation+0.000
I
TokenI
Feature activation+0.000
HI
TokenHI
Feature activation+0.000
CH
Token CH
Feature activation+0.000
IP
TokenIP
Feature activation+0.000
but
Token but
Feature activation+4.227
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
see
Token see
Feature activation+0.000
some
Token some
Feature activation+0.000
similarities
Token similarities
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.422
Pant
Token Pant
Feature activation+1.914
one
Tokenone
Feature activation+1.273
color
Token color
Feature activation+2.621
when
Token when
Feature activation+4.171
rec
Token rec
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
that
Token that
Feature activation+0.000
logo
Token logo
Feature activation+0.000
.
Token.
Feature activation+1.340
covers
Token covers
Feature activation+0.000
are
Token are
Feature activation+0.000
basically
Token basically
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.203
except
Token except
Feature activation+4.014
they
Token they
Feature activation+0.620
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000

INTERVAL 3.386 - 3.870
CONTAINS 0.002%

pastor
Token pastor
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.168
goes
Token goes
Feature activation+1.018
for
Token for
Feature activation+3.447
political
Token political
Feature activation+0.000
parties
Token parties
Feature activation+0.000
.
Token.
Feature activation+0.804
Members
Token Members
Feature activation+0.000
of
Token of
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.032
can
Token can
Feature activation+1.578
be
Token be
Feature activation+2.659
said
Token said
Feature activation+3.620
for
Token for
Feature activation+1.939
sophomore
Token sophomore
Feature activation+0.000
Aust
Token Aust
Feature activation+0.000
on
Tokenon
Feature activation+0.000
B
Token B
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.105
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+4.578
and
Token and
Feature activation+0.208
over
Token over
Feature activation+3.837
again
Token again
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.199
same
Token same
Feature activation+0.000
person
Token person
Feature activation+0.000
quick
Tokenquick
Feature activation+0.000
_
Token_
Feature activation+0.000
error
Tokenerror
Feature activation+0.000
!
Token!
Feature activation+0.000
`,
Token`,
Feature activation+0.069
but
Token but
Feature activation+3.430
the
Token the
Feature activation+0.091
`
Token `
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
()
Token()
Feature activation+0.000
`
Token`
Feature activation+0.000
Researchers
Token Researchers
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.546
are
Token are
Feature activation+3.610
active
Token active
Feature activation+0.485
during
Token during
Feature activation+0.644
both
Token both
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.049

INTERVAL 2.902 - 3.386
CONTAINS 0.003%

Peterson
Token Peterson
Feature activation+0.000
was
Token was
Feature activation+0.000
inflicting
Token inflicting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+3.003
he
Token he
Feature activation+3.072
endured
Token endured
Feature activation+1.692
as
Token as
Feature activation+1.037
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
airline
Token airline
Feature activation+0.928
had
Token had
Feature activation+1.790
been
Token been
Feature activation+3.296
identified
Token identified
Feature activation+1.615
and
Token and
Feature activation+0.771
found
Token found
Feature activation+2.340
on
Token on
Feature activation+0.434
Friday
Token Friday
Feature activation+0.000
taken
Token taken
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
lighting
Token lighting
Feature activation+0.000
conditions
Token conditions
Feature activation+3.263
,
Token,
Feature activation+3.115
and
Token and
Feature activation+1.121
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
normalized
Token normalized
Feature activation+0.000
same
Token same
Feature activation+0.267
rule
Token rule
Feature activation+2.815
that
Token that
Feature activation+2.094
must
Token must
Feature activation+0.575
be
Token be
Feature activation+1.081
applied
Token applied
Feature activation+2.922
in
Token in
Feature activation+0.265
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+0.000
rich
Token rich
Feature activation+0.000
men
Token men
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ran
Token ran
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.301
offense
Token offense
Feature activation+2.272
for
Token for
Feature activation+2.948
35
Token 35
Feature activation+0.000
years
Token years
Feature activation+0.000
or
Token or
Feature activation+0.000
however
Token however
Feature activation+0.000
long
Token long
Feature activation+0.000

INTERVAL 2.419 - 2.902
CONTAINS 0.005%

think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
works
Token works
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.057
way
Token way
Feature activation+2.869
as
Token as
Feature activation+0.122
the
Token the
Feature activation+0.586
Y
Token Y
Feature activation+0.000
I
TokenI
Feature activation+0.000
HI
TokenHI
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
nuances
Token nuances
Feature activation+2.835
that
Token that
Feature activation+0.290
a
Token a
Feature activation+0.735
bear
Token bear
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.226
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.417
things
Token things
Feature activation+2.582
that
Token that
Feature activation+1.132
we
Token we
Feature activation+1.740
used
Token used
Feature activation+0.512
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+0.000
graduating
Token graduating
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
class
Token class
Feature activation+2.603
as
Token as
Feature activation+1.524
Robert
Token Robert
Feature activation+0.000
E
Token E
Feature activation+0.000
.
Token.
Feature activation+0.000
Lee
Token Lee
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Swiss
Token Swiss
Feature activation+1.657
cam
Token cam
Feature activation+0.619
o
Tokeno
Feature activation+0.000
pattern
Token pattern
Feature activation+2.564
.
Token.
Feature activation+0.540
The
Token The
Feature activation+0.000
crappy
Token crappy
Feature activation+0.000
PM
Token PM
Feature activation+0.000
C
TokenC
Feature activation+0.000

INTERVAL 1.935 - 2.419
CONTAINS 0.010%

houses
Token houses
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
area
Token area
Feature activation+1.461
designed
Token designed
Feature activation+2.182
under
Token under
Feature activation+0.752
the
Token the
Feature activation+1.422
same
Token same
Feature activation+0.000
guidelines
Token guidelines
Feature activation+2.309
and
Token and
Feature activation+2.580
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.088
,
Token,
Feature activation+2.270
because
Token because
Feature activation+2.760
this
Token this
Feature activation+0.045
is
Token is
Feature activation+0.000
what
Token what
Feature activation+0.324
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.378
thing
Token thing
Feature activation+1.138
could
Token could
Feature activation+2.194
be
Token be
Feature activation+3.192
done
Token done
Feature activation+2.609
in
Token in
Feature activation+2.083
the
Token the
Feature activation+1.564
former
Token former
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+2.206
as
Token as
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
follow
Token follow
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
scope
Token scope
Feature activation+2.050
of
Token of
Feature activation+0.000
actions
Token actions
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.002
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.044
would
Token would
Feature activation+0.000
see
Token see
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
way
Token way
Feature activation+2.083
and
Token and
Feature activation+0.781
realize
Token realize
Feature activation+0.638
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 1.451 - 1.935
CONTAINS 0.016%

same
Token same
Feature activation+0.187
app
Token app
Feature activation+1.802
on
Token on
Feature activation+3.293
the
Token the
Feature activation+2.716
phone
Token phone
Feature activation+0.000
,
Token,
Feature activation+1.921
laptop
Token laptop
Feature activation+0.000
or
Token or
Feature activation+0.000
tablet
Token tablet
Feature activation+0.053
,
Token,
Feature activation+0.118
desktop
Token desktop
Feature activation+0.000
sm
Token sm
Feature activation+0.000
acks
Tokenacks
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
kind
Token kind
Feature activation+1.729
of
Token of
Feature activation+1.432
imper
Token imper
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+1.423
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.910
tools
Token tools
Feature activation+1.595
Bethesda
Token Bethesda
Feature activation+0.598
used
Token used
Feature activation+1.231
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
the
Token the
Feature activation+0.096
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
same
Token same
Feature activation+0.076
attitude
Token attitude
Feature activation+1.552
that
Token that
Feature activation+1.874
led
Token led
Feature activation+0.156
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
instances
Token instances
Feature activation+0.000
like
Token like
Feature activation+0.000
flat
Token flat
Feature activation+0.000
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+0.000
in
Token in
Feature activation+0.000
books
Token books
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.557
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.000
something
Token something
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000

INTERVAL 0.967 - 1.451
CONTAINS 0.017%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
anth
Token anth
Feature activation+0.000
rax
Tokenrax
Feature activation+0.000
strain
Token strain
Feature activation+1.215
were
Token were
Feature activation+1.256
shipped
Token shipped
Feature activation+0.107
by
Token by
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.214
to
Token to
Feature activation+2.292
an
Token an
Feature activation+1.250
extent
Token extent
Feature activation+1.262
with
Token with
Feature activation+1.461
the
Token the
Feature activation+0.375
h
Token h
Feature activation+0.000
iat
Tokeniat
Feature activation+0.000
in
Token in
Feature activation+0.000
much
Token much
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
way
Token way
Feature activation+1.726
he
Token he
Feature activation+1.236
hum
Token hum
Feature activation+0.000
bled
Tokenbled
Feature activation+0.000
hitters
Token hitters
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
again
Token again
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.199
same
Token same
Feature activation+0.000
person
Token person
Feature activation+0.000
,
Token,
Feature activation+1.327
just
Token just
Feature activation+1.297
to
Token to
Feature activation+0.000
save
Token save
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
when
Token when
Feature activation+4.171
rec
Token rec
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
that
Token that
Feature activation+0.000
logo
Token logo
Feature activation+0.000
.
Token.
Feature activation+1.340
When
Token When
Feature activation+0.000
Santa
Token Santa
Feature activation+0.000
packed
Token packed
Feature activation+0.000
every
Token every
Feature activation+0.000
thing
Token thing
Feature activation+0.000

INTERVAL 0.484 - 0.967
CONTAINS 0.031%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.536
was
Token was
Feature activation+0.933
when
Token when
Feature activation+1.977
I
Token I
Feature activation+0.122
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
quite
Token quite
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
without
Token without
Feature activation+0.752
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.283
but
Token but
Feature activation+1.787
if
Token if
Feature activation+0.013
you
Token you
Feature activation+0.000
face
Token face
Feature activation+0.000
value
Token value
Feature activation+0.000
remains
Token remains
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
.
Token.
Feature activation+0.687
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Coin
TokenCoin
Feature activation+0.000
counterfe
Token counterfe
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.100
time
Token time
Feature activation+0.023
,
Token,
Feature activation+0.683
Henderson
Token Henderson
Feature activation+0.000
was
Token was
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
Kentucky
Token Kentucky
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
day
Token day
Feature activation+0.838
this
Token this
Feature activation+0.924
spring
Token spring
Feature activation+0.879
.
Token.
Feature activation+0.134
Waters
Token Waters
Feature activation+0.000
described
Token described
Feature activation+0.000

INTERVAL 0.000 - 0.484
CONTAINS 99.916%

s
Tokens
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
tin
Tokentin
Feature activation+0.000
Hein
Token Hein
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
rich
Tokenrich
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.000
Vir
Token Vir
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
could
Token could
Feature activation+0.000
more
Token more
Feature activation+0.000
autonom
Token autonom
Feature activation+0.000
ously
Tokenously
Feature activation+0.000
restore
Token restore
Feature activation+0.000
a
Token a
Feature activation+0.000
context
Token context
Feature activation+0.000
-
Token-
Feature activation+0.000
oriented
Tokenoriented
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
data
Token data
Feature activation+0.000
log
Token log
Feature activation+0.000
gers
Tokengers
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
running
Token running
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
coast
Token coast
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
islands
Token islands
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
reass
Token reass
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
begins
Token begins
Feature activation+0.000
with
Token with
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.000
including
Token including
Feature activation+0.000
fever
Token fever
Feature activation+0.000
and
Token and
Feature activation+0.000
sore
Token sore
Feature activation+0.000
throat
Token throat
Feature activation+0.000
but
Token but
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H3.11: (feature 6003)

TOP ACTIVATIONS
MAX = 3.960

former
Token former
Feature activation+0.934
Trump
Token Trump
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
officials
Token officials
Feature activation+0.560
âĢĶ
Token âĢĶ
Feature activation+3.960
former
Token former
Feature activation+0.501
deputy
Token deputy
Feature activation+0.000
chief
Token chief
Feature activation+0.000
of
Token of
Feature activation+0.000
staff
Token staff
Feature activation+0.000
director
Token director
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Dub
Token Dub
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.586
are
Token are
Feature activation+3.917
helping
Token helping
Feature activation+0.000
coordinate
Token coordinate
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.000
.
Token.
Feature activation+0.687
actually
Token actually
Feature activation+0.000
two
Token two
Feature activation+0.000
separate
Token separate
Feature activation+1.477
problems
Token problems
Feature activation+1.215
.
Token.
Feature activation+2.939
First
Token First
Feature activation+3.839
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.357
form
Token form
Feature activation+0.000
library
Token library
Feature activation+0.000
is
Token is
Feature activation+0.000
global
Token global
Feature activation+0.112
surface
Token surface
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
observational
Token observational
Feature activation+0.100
datasets
Token datasets
Feature activation+2.837
,
Token,
Feature activation+3.814
the
Token the
Feature activation+2.396
UK
Token UK
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.954
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.021
Western
Token Western
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+1.858
Ċ
TokenĊ
Feature activation+2.177
Ċ
TokenĊ
Feature activation+2.187
First
TokenFirst
Feature activation+3.754
,
Token,
Feature activation+0.000
India
Token India
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
merely
Token merely
Feature activation+0.000
ASCII
Token ASCII
Feature activation+0.000
text
Token text
Feature activation+0.000
files
Token files
Feature activation+2.773
are
Token are
Feature activation+3.060
necessary
Token necessary
Feature activation+2.004
:
Token:
Feature activation+3.725
(
Token (
Feature activation+2.264
1
Token1
Feature activation+2.601
)
Token)
Feature activation+0.624
The
Token The
Feature activation+0.493
graph
Token graph
Feature activation+0.000
music
Token music
Feature activation+0.000
that
Token that
Feature activation+0.884
are
Token are
Feature activation+1.241
critically
Token critically
Feature activation+0.000
important
Token important
Feature activation+0.000
:
Token:
Feature activation+3.689
who
Token who
Feature activation+0.322
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
who
Token who
Feature activation+0.000
that
Token that
Feature activation+0.000
includes
Token includes
Feature activation+0.000
two
Token two
Feature activation+0.000
hard
Token hard
Feature activation+0.000
forks
Token forks
Feature activation+0.665
:
Token:
Feature activation+3.680
Byz
Token Byz
Feature activation+0.086
ant
Tokenant
Feature activation+0.000
ium
Tokenium
Feature activation+0.874
and
Token and
Feature activation+0.826
Constantinople
Token Constantinople
Feature activation+0.212
revealed
Token revealed
Feature activation+0.000
two
Token two
Feature activation+0.064
character
Token character
Feature activation+0.000
designs
Token designs
Feature activation+0.805
âĢĶ
Token âĢĶ
Feature activation+3.337
one
Token one
Feature activation+3.662
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
character
Token character
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.000
contexts
Token contexts
Feature activation+2.482
:
Token:
Feature activation+3.649
either
Token either
Feature activation+0.000
regime
Token regime
Feature activation+0.000
forces
Token forces
Feature activation+0.000
have
Token have
Feature activation+0.000
besieged
Token besieged
Feature activation+0.000
be
Token be
Feature activation+0.000
skewed
Token skewed
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.022
ways
Token ways
Feature activation+2.282
:
Token:
Feature activation+3.625
1
Token 1
Feature activation+3.157
)
Token)
Feature activation+0.431
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
testim
Token testim
Feature activation+0.000
on
Tokenon
Feature activation+0.000
ials
Tokenials
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.469
one
Token one
Feature activation+3.614
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
military
Token military
Feature activation+0.000
medic
Token medic
Feature activation+0.000
two
Token two
Feature activation+0.000
simple
Token simple
Feature activation+1.589
public
Token public
Feature activation+0.000
commitments
Token commitments
Feature activation+0.187
.
Token.
Feature activation+2.449
First
Token First
Feature activation+3.596
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
can
Token can
Feature activation+0.000
for
Token for
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
examination
Token examination
Feature activation+0.000
.
Token.
Feature activation+3.217
The
Token The
Feature activation+2.607
first
Token first
Feature activation+3.559
,
Token,
Feature activation+0.000
dubbed
Token dubbed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
P
TokenP
Feature activation+0.000
appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.897
versions
Token versions
Feature activation+2.099
:
Token :
Feature activation+2.985
One
Token One
Feature activation+3.555
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000
that
Token that
Feature activation+2.652
come
Token come
Feature activation+0.478
with
Token with
Feature activation+0.000
unlimited
Token unlimited
Feature activation+0.000
users
Token users
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+3.541
for
Token for
Feature activation+0.179
$
Token $
Feature activation+0.000
99
Token99
Feature activation+0.000
/
Token/
Feature activation+0.000
mo
Tokenmo
Feature activation+0.000
complained
Token complained
Feature activation+0.000
about
Token about
Feature activation+0.000
two
Token two
Feature activation+0.000
officials
Token officials
Feature activation+0.591
-
Token -
Feature activation+3.231
one
Token one
Feature activation+3.518
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Corbyn
Token Corbyn
Feature activation+0.000
and
Token and
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
two
Token two
Feature activation+0.752
aims
Token aims
Feature activation+2.178
:
Token:
Feature activation+3.517
to
Token to
Feature activation+2.702
promote
Token promote
Feature activation+0.208
atheism
Token atheism
Feature activation+0.000
and
Token and
Feature activation+0.511
reason
Token reason
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.276
people
Token people
Feature activation+1.010
.
Token.
Feature activation+2.537
The
Token The
Feature activation+3.087
first
Token first
Feature activation+3.505
person
Token person
Feature activation+0.000
has
Token has
Feature activation+0.000
lived
Token lived
Feature activation+0.000
on
Token on
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
DS
Token DS
Feature activation+0.000
9
Token9
Feature activation+0.000
universe
Token universe
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.269
one
Token one
Feature activation+3.502
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
unpredictable
Token unpredictable
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 4.853

the
Token the
Feature activation+0.002
Top resid features:
day
Token day
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Two
TokenTwo
Feature activation+4.599
Top resid features:
former
Token former
Feature activation+0.052
Top resid features:
Trump
Token Trump
Feature activation+0.005
Top resid features:
White
Token White
Feature activation+0.008
Top resid features:
House
Token House
Feature activation+0.015
Top resid features:
officials
Token officials
Feature activation+0.153
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
day
Token day
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Two
TokenTwo
Feature activation+4.580
Top resid features:
former
Token former
Feature activation+0.029
Top resid features:
Trump
Token Trump
Feature activation+0.001
Top resid features:
White
Token White
Feature activation+0.003
Top resid features:
House
Token House
Feature activation+0.003
Top resid features:
officials
Token officials
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
This
TokenThis
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
actually
Token actually
Feature activation-0.003
Top resid features:
two
Token two
Feature activation+4.842
Top resid features:
separate
Token separate
Feature activation+0.062
Top resid features:
problems
Token problems
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.071
Top resid features:
First
Token First
Feature activation-0.072
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
This
TokenThis
Feature activation-0.014
Top resid features:
graph
Token graph
Feature activation+0.005
Top resid features:
depicts
Token depicts
Feature activation-0.041
Top resid features:
two
Token two
Feature activation+4.315
Top resid features:
well
Token well
Feature activation+0.012
Top resid features:
known
Token known
Feature activation+0.025
Top resid features:
global
Token global
Feature activation+0.005
Top resid features:
surface
Token surface
Feature activation+0.010
Top resid features:
temperature
Token temperature
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
This
TokenThis
Feature activation+0.001
Top resid features:
reveals
Token reveals
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+4.853
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
things
Token things
Feature activation-0.006
Top resid features:
about
Token about
Feature activation-0.002
Top resid features:
India
Token India
Feature activation-0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
within
Token within
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
R
Token R
Feature activation-0.001
Top resid features:
console
Token console
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Two
Token Two
Feature activation+4.607
Top resid features:
ASCII
Token ASCII
Feature activation+0.027
Top resid features:
text
Token text
Feature activation-0.003
Top resid features:
files
Token files
Feature activation+0.028
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
necessary
Token necessary
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Specifically
Token Specifically
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
there
Token there
Feature activation-0.010
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
two
Token two
Feature activation+4.712
Top resid features:
types
Token types
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
information
Token information
Feature activation+0.011
Top resid features:
about
Token about
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
Ethereum
Token Ethereum
Feature activation+0.010
Top resid features:
development
Token development
Feature activation+0.010
Top resid features:
phase
Token phase
Feature activation+0.007
Top resid features:
that
Token that
Feature activation-0.011
Top resid features:
includes
Token includes
Feature activation-0.037
Top resid features:
two
Token two
Feature activation+4.393
Top resid features:
hard
Token hard
Feature activation+0.110
Top resid features:
forks
Token forks
Feature activation+0.066
Top resid features:
:
Token:
Feature activation+0.020
Top resid features:
Byz
Token Byz
Feature activation+0.000
Top resid features:
ant
Tokenant
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.003
Top resid features:
film
Token film
Feature activation-0.005
Top resid features:
's
Token's
Feature activation+0.005
Top resid features:
website
Token website
Feature activation-0.002
Top resid features:
revealed
Token revealed
Feature activation+0.009
Top resid features:
two
Token two
Feature activation+4.635
Top resid features:
character
Token character
Feature activation-0.015
Top resid features:
designs
Token designs
Feature activation+0.078
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.022
Top resid features:
one
Token one
Feature activation-0.197
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.031
Top resid features:
tended
Token tended
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
come
Token come
Feature activation-0.020
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+4.371
Top resid features:
contexts
Token contexts
Feature activation+0.041
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
either
Token either
Feature activation+0.000
Top resid features:
regime
Token regime
Feature activation+0.000
Top resid features:
forces
Token forces
Feature activation+0.000
Top resid features:
going
Token going
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
be
Token be
Feature activation-0.013
Top resid features:
skewed
Token skewed
Feature activation+0.009
Top resid features:
in
Token in
Feature activation-0.018
Top resid features:
two
Token two
Feature activation+4.461
Top resid features:
ways
Token ways
Feature activation+0.095
Top resid features:
:
Token:
Feature activation-0.035
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
George
Token George
Feature activation+0.003
Top resid features:
Qu
Token Qu
Feature activation-0.000
Top resid features:
amo
Tokenamo
Feature activation+0.001
Top resid features:
hope
Token hope
Feature activation-0.002
Top resid features:
two
Token two
Feature activation+4.523
Top resid features:
more
Token more
Feature activation+0.023
Top resid features:
testim
Token testim
Feature activation+0.039
Top resid features:
on
Tokenon
Feature activation+0.004
Top resid features:
ials
Tokenials
Feature activation+0.067
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.057
Top resid features:
can
Token can
Feature activation-0.003
Top resid features:
take
Token take
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
form
Token form
Feature activation-0.015
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
two
Token two
Feature activation+4.642
Top resid features:
simple
Token simple
Feature activation+0.007
Top resid features:
public
Token public
Feature activation+0.012
Top resid features:
commitments
Token commitments
Feature activation+0.021
Top resid features:
.
Token.
Feature activation-0.106
Top resid features:
First
Token First
Feature activation-0.082
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
So
TokenSo
Feature activation-0.004
Top resid features:
far
Token far
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
two
Token two
Feature activation+4.729
Top resid features:
specific
Token specific
Feature activation+0.019
Top resid features:
areas
Token areas
Feature activation+0.017
Top resid features:
have
Token have
Feature activation+0.014
Top resid features:
been
Token been
Feature activation+0.004
Top resid features:
identified
Token identified
Feature activation+0.004
Top resid features:
speed
Token speed
Feature activation-0.000
Top resid features:
boost
Tokenboost
Feature activation+0.011
Top resid features:
can
Token can
Feature activation-0.009
Top resid features:
appear
Token appear
Feature activation-0.009
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+4.570
Top resid features:
versions
Token versions
Feature activation+0.057
Top resid features:
:
Token :
Feature activation+0.032
Top resid features:
One
Token One
Feature activation-0.224
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.022
Top resid features:
space
Token space
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
There
Token There
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+4.321
Top resid features:
paid
Token paid
Feature activation+0.026
Top resid features:
editions
Token editions
Feature activation+0.051
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
come
Token come
Feature activation-0.008
Top resid features:
with
Token with
Feature activation-0.026
Top resid features:
leadership
Token leadership
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
complained
Token complained
Feature activation-0.008
Top resid features:
about
Token about
Feature activation-0.009
Top resid features:
two
Token two
Feature activation+4.460
Top resid features:
officials
Token officials
Feature activation+0.075
Top resid features:
-
Token -
Feature activation+0.025
Top resid features:
one
Token one
Feature activation-0.185
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.004
Top resid features:
We
TokenWe
Feature activation-0.037
Top resid features:
have
Token have
Feature activation+0.033
Top resid features:
two
Token two
Feature activation+4.394
Top resid features:
aims
Token aims
Feature activation+0.078
Top resid features:
:
Token:
Feature activation-0.028
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
promote
Token promote
Feature activation+0.000
Top resid features:
atheism
Token atheism
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
There
TokenThere
Feature activation-0.007
Top resid features:
are
Token are
Feature activation-0.003
Top resid features:
two
Token two
Feature activation+4.514
Top resid features:
people
Token people
Feature activation+0.025
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
The
Token The
Feature activation-0.057
Top resid features:
first
Token first
Feature activation-0.080
Top resid features:
person
Token person
Feature activation+0.000
Top resid features:
've
Token've
Feature activation+0.008
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
struck
Token struck
Feature activation-0.006
Top resid features:
particularly
Token particularly
Feature activation-0.007
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+4.540
Top resid features:
things
Token things
Feature activation+0.036
Top resid features:
missing
Token missing
Feature activation+0.012
Top resid features:
from
Token from
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
DS
Token DS
Feature activation-0.030
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.06

Head 3: 0.02

Head 4: 0.02

Head 5: 0.06

Head 6: 0.06

Head 7: 0.05

Head 8: 0.04

Head 9: 0.04

Head 10: 0.06

Head 11: 0.52

Positive logits

halves1.82

apiece1.38

twins1.38

handguns1.36

viz1.36

namely1.35

brothers1.34

ouple1.33

sides1.28

starters1.26

separated1.25

poons1.25

ilion1.23

totaling1.23

thirds1.20

pairs1.19

couples1.19

complementary1.19

identical1.19

sexes1.19

Negative logits

SPONSORED-1.76

ゴン-1.42

-1.29

Awoken-1.24

ゼウス-1.19

Outs-1.17

tra-1.17

Tribal-1.15

Pesh-1.14

utory-1.14

Tune-1.11

Shape-1.11

ens-1.11

tal-1.08

Prospect-1.06

adder-1.06

odi-1.06

tun-1.05

suff-1.05

Events-1.05

INTERVAL 3.564 - 3.960
CONTAINS 0.001%

to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.000
contexts
Token contexts
Feature activation+2.482
:
Token:
Feature activation+3.649
either
Token either
Feature activation+0.000
regime
Token regime
Feature activation+0.000
forces
Token forces
Feature activation+0.000
have
Token have
Feature activation+0.000
besieged
Token besieged
Feature activation+0.000
actually
Token actually
Feature activation+0.000
two
Token two
Feature activation+0.000
separate
Token separate
Feature activation+1.477
problems
Token problems
Feature activation+1.215
.
Token.
Feature activation+2.939
First
Token First
Feature activation+3.839
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.357
form
Token form
Feature activation+0.000
library
Token library
Feature activation+0.000
is
Token is
Feature activation+0.000
director
Token director
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Dub
Token Dub
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.586
are
Token are
Feature activation+3.917
helping
Token helping
Feature activation+0.000
coordinate
Token coordinate
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.000
.
Token.
Feature activation+0.687
Western
Token Western
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+1.858
Ċ
TokenĊ
Feature activation+2.177
Ċ
TokenĊ
Feature activation+2.187
First
TokenFirst
Feature activation+3.754
,
Token,
Feature activation+0.000
India
Token India
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
merely
Token merely
Feature activation+0.000
two
Token two
Feature activation+0.000
simple
Token simple
Feature activation+1.589
public
Token public
Feature activation+0.000
commitments
Token commitments
Feature activation+0.187
.
Token.
Feature activation+2.449
First
Token First
Feature activation+3.596
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 3.168 - 3.564
CONTAINS 0.004%

for
Token for
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
examination
Token examination
Feature activation+0.000
.
Token.
Feature activation+3.217
The
Token The
Feature activation+2.607
first
Token first
Feature activation+3.559
,
Token,
Feature activation+0.000
dubbed
Token dubbed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
P
TokenP
Feature activation+0.000
water
Tokenwater
Feature activation+0.000
is
Token is
Feature activation+0.000
two
Token two
Feature activation+0.000
parts
Token parts
Feature activation+0.000
:
Token:
Feature activation+3.103
one
Token one
Feature activation+3.318
celestial
Token celestial
Feature activation+0.000
and
Token and
Feature activation+0.000
lush
Token lush
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
divided
Token divided
Feature activation+0.000
into
Token into
Feature activation+0.000
two
Token two
Feature activation+0.000
parts
Token parts
Feature activation+1.416
:
Token:
Feature activation+3.267
meal
Token meal
Feature activation+0.000
,
Token,
Feature activation+0.405
which
Token which
Feature activation+0.000
mainly
Token mainly
Feature activation+0.000
goes
Token goes
Feature activation+0.000
himself
Token himself
Feature activation+0.000
into
Token into
Feature activation+0.097
two
Token two
Feature activation+0.000
autonomous
Token autonomous
Feature activation+0.803
components
Token components
Feature activation+1.951
:
Token:
Feature activation+3.447
a
Token a
Feature activation+2.392
walking
Token walking
Feature activation+0.000
lyn
Token lyn
Feature activation+0.000
x
Tokenx
Feature activation+0.000
and
Token and
Feature activation+0.000
appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.897
versions
Token versions
Feature activation+2.099
:
Token :
Feature activation+2.985
One
Token One
Feature activation+3.555
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000

INTERVAL 2.772 - 3.168
CONTAINS 0.006%

of
Token of
Feature activation+0.483
the
Token the
Feature activation+0.060
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
technology
Token technology
Feature activation+0.000
,
Token,
Feature activation+2.825
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.482
A
Token A
Feature activation+1.163
New
Token New
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
has
Token has
Feature activation+0.000
two
Token two
Feature activation+0.502
desired
Token desired
Feature activation+0.346
effects
Token effects
Feature activation+2.159
,
Token,
Feature activation+2.932
one
Token one
Feature activation+3.414
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.276
people
Token people
Feature activation+1.010
.
Token.
Feature activation+2.537
The
Token The
Feature activation+3.087
first
Token first
Feature activation+3.505
person
Token person
Feature activation+0.000
has
Token has
Feature activation+0.000
lived
Token lived
Feature activation+0.000
on
Token on
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
should
Token should
Feature activation+0.000
underscore
Token underscore
Feature activation+0.000
two
Token two
Feature activation+0.000
things
Token things
Feature activation+1.162
:
Token:
Feature activation+3.016
His
Token His
Feature activation+1.670
treatment
Token treatment
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
programmers
Token programmers
Feature activation+1.287
,
Token,
Feature activation+2.970
one
Token one
Feature activation+3.232
systems
Token systems
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.759

INTERVAL 2.376 - 2.772
CONTAINS 0.008%

?
Token?
Feature activation+0.000
For
Token For
Feature activation+0.000
two
Token two
Feature activation+0.000
reasons
Token reasons
Feature activation+1.924
:
Token:
Feature activation+2.894
Ċ
TokenĊ
Feature activation+2.561
Ċ
TokenĊ
Feature activation+2.399
Fin
TokenFin
Feature activation+0.000
land
Tokenland
Feature activation+0.000
has
Token has
Feature activation+0.000
reached
Token reached
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.234
skills
Token skills
Feature activation+1.979
that
Token that
Feature activation+2.405
transf
Token transf
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
over
Token over
Feature activation+0.000
after
Token after
Feature activation+0.119
he
Token he
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.000
two
Token two
Feature activation+0.000
largest
Token largest
Feature activation+2.522
economies
Token economies
Feature activation+1.705
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.000
Xi
Token Xi
Feature activation+0.000
Jinping
Token Jinping
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
kinds
Token kinds
Feature activation+2.594
,
Token,
Feature activation+1.954
intellectual
Token intellectual
Feature activation+0.452
and
Token and
Feature activation+0.000
moral
Token moral
Feature activation+0.000
,
Token,
Feature activation+0.329
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.175
example
Token example
Feature activation+1.122
types
Token types
Feature activation+1.395
that
Token that
Feature activation+2.386
use
Token use
Feature activation+0.000
object
Token object
Feature activation+0.000
subscript
Token subscript
Feature activation+0.000
ing
Tokening
Feature activation+0.000
are
Token are
Feature activation+2.534

INTERVAL 1.980 - 2.376
CONTAINS 0.013%

threads
Token threads
Feature activation+2.309
tie
Token tie
Feature activation+0.000
them
Token them
Feature activation+0.000
together
Token together
Feature activation+0.000
.
Token.
Feature activation+1.888
The
Token The
Feature activation+2.273
stories
Token stories
Feature activation+0.000
explore
Token explore
Feature activation+0.000
questions
Token questions
Feature activation+0.000
of
Token of
Feature activation+0.000
determin
Token determin
Feature activation+0.000
ensures
Token ensures
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
pictures
Token pictures
Feature activation+0.222
are
Token are
Feature activation+2.241
perfectly
Token perfectly
Feature activation+0.000
aligned
Token aligned
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.225
Ċ
TokenĊ
Feature activation+0.332
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
two
Token two
Feature activation+0.000
full
Token full
Feature activation+0.000
seasons
Token seasons
Feature activation+2.247
,
Token,
Feature activation+0.871
an
Token an
Feature activation+0.182
MLB
Token MLB
Feature activation+0.000
Record
Token Record
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
we
Token we
Feature activation+0.000
-
Token -
Feature activation+0.000
our
Token our
Feature activation+0.000
two
Token two
Feature activation+0.000
countries
Token countries
Feature activation+2.039
together
Token together
Feature activation+0.000
-
Token -
Feature activation+1.442
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.000
our
Token our
Feature activation+0.000
controls
Token controls
Feature activation+0.000
.
Token.
Feature activation+1.463
Ċ
TokenĊ
Feature activation+0.497
Ċ
TokenĊ
Feature activation+0.409
One
TokenOne
Feature activation+2.358
version
Token version
Feature activation+0.000
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
new
Token new
Feature activation+0.000
standard
Token standard
Feature activation+0.000

INTERVAL 1.584 - 1.980
CONTAINS 0.021%

air
Token air
Feature activation+0.000
temperatures
Token temperatures
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
two
Token two
Feature activation+0.000
main
Token main
Feature activation+1.683
ice
Token ice
Feature activation+0.000
sheets
Token sheets
Feature activation+1.611
on
Token on
Feature activation+0.694
Earth
Token Earth
Feature activation+0.000
cover
Token cover
Feature activation+0.092
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
highlighted
Token highlighted
Feature activation+0.000
by
Token by
Feature activation+0.000
two
Token two
Feature activation+0.000
recent
Token recent
Feature activation+1.745
incidents
Token incidents
Feature activation+2.082
at
Token at
Feature activation+1.485
two
Token two
Feature activation+0.431
of
Token of
Feature activation+0.014
the
Token the
Feature activation+0.338
Each
TokenEach
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
scripted
Token scripted
Feature activation+1.214
paths
Token paths
Feature activation+1.640
(
Token (
Feature activation+0.693
script
Tokenscript
Feature activation+0.000
ed
Tokened
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
been
Token been
Feature activation+0.000
struck
Token struck
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
by
Token by
Feature activation+0.000
two
Token two
Feature activation+0.000
things
Token things
Feature activation+1.621
missing
Token missing
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
DS
Token DS
Feature activation+0.000
9
Token9
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.129
groups
Token groups
Feature activation+1.472
are
Token are
Feature activation+1.646
urging
Token urging
Feature activation+0.000
doctors
Token doctors
Feature activation+0.000
to
Token to
Feature activation+0.000
inform
Token inform
Feature activation+0.000
patients
Token patients
Feature activation+0.000

INTERVAL 1.188 - 1.584
CONTAINS 0.029%

last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.058
The
Token The
Feature activation+0.000
two
Token two
Feature activation+0.000
companies
Token companies
Feature activation+1.490
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
30
Token 30
Feature activation+0.000
startup
Token startup
Feature activation+0.000
companies
Token companies
Feature activation+0.000
28
Token 28
Feature activation+0.000
th
Tokenth
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
two
Token two
Feature activation+0.000
prisoners
Token prisoners
Feature activation+1.233
,
Token,
Feature activation+1.887
as
Token as
Feature activation+0.272
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.007
a
Token a
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
completely
Token completely
Feature activation+1.158
different
Token different
Feature activation+1.796
environments
Token environments
Feature activation+0.995
.
Token.
Feature activation+1.556
Sheffield
Token Sheffield
Feature activation+0.000
,
Token,
Feature activation+0.419
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
plaintiffs
Token plaintiffs
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
seemingly
Token seemingly
Feature activation+1.409
un
Token un
Feature activation+0.000
connected
Tokenconnected
Feature activation+0.120
people
Token people
Feature activation+0.236
from
Token from
Feature activation+0.055
different
Token different
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
only
Token only
Feature activation+0.000
two
Token two
Feature activation+0.026
images
Token images
Feature activation+0.780
are
Token are
Feature activation+1.239
used
Token used
Feature activation+0.178
.
Token.
Feature activation+2.070
Ċ
TokenĊ
Feature activation+0.481
Ċ
TokenĊ
Feature activation+0.314
Apple
TokenApple
Feature activation+0.000

INTERVAL 0.792 - 1.188
CONTAINS 0.046%

states
Token states
Feature activation+0.004
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.364
human
Token human
Feature activation+0.000
emoji
Token emoji
Feature activation+0.000
:
Token:
Feature activation+1.010
Ċ
TokenĊ
Feature activation+0.954
Ċ
TokenĊ
Feature activation+0.878
Base
TokenBase
Feature activation+0.000
Character
Token Character
Feature activation+0.000
(
Token (
Feature activation+0.000
two
Token two
Feature activation+0.000
big
Token big
Feature activation+0.855
prototype
Token prototype
Feature activation+0.148
lenses
Token lenses
Feature activation+0.707
that
Token that
Feature activation+1.849
were
Token were
Feature activation+0.949
on
Token on
Feature activation+0.000
display
Token display
Feature activation+0.000
at
Token at
Feature activation+0.000
Phot
Token Phot
Feature activation+0.000
ok
Tokenok
Feature activation+0.000
playing
Token playing
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
factions
Token factions
Feature activation+1.133
of
Token of
Feature activation+0.000
home
Token home
Feature activation+0.000
fans
Token fans
Feature activation+0.165
who
Token who
Feature activation+0.365
used
Token used
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
provided
Token provided
Feature activation+0.000
two
Token two
Feature activation+0.150
singles
Token singles
Feature activation+1.453
which
Token which
Feature activation+0.922
also
Token also
Feature activation+0.000
did
Token did
Feature activation+0.000
well
Token well
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
forks
Token forks
Feature activation+0.665
:
Token:
Feature activation+3.680
Byz
Token Byz
Feature activation+0.086
ant
Tokenant
Feature activation+0.000
ium
Tokenium
Feature activation+0.874
and
Token and
Feature activation+0.826
Constantinople
Token Constantinople
Feature activation+0.212
.
Token.
Feature activation+1.614
Byz
Token Byz
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
ium
Tokenium
Feature activation+0.000

INTERVAL 0.396 - 0.792
CONTAINS 0.080%

telev
Token telev
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
two
Token two
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
-
Token-
Feature activation+0.125
style
Tokenstyle
Feature activation+0.541
advertisements
Token advertisements
Feature activation+0.000
that
Token that
Feature activation+0.929
emphasize
Token emphasize
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
's
Token's
Feature activation+0.000
records
Token records
Feature activation+0.429
per
Token per
Feature activation+0.591
event
Token event
Feature activation+0.000
.
Token.
Feature activation+0.624
Ċ
TokenĊ
Feature activation+0.786
Ċ
TokenĊ
Feature activation+0.730
Each
TokenEach
Feature activation+0.000
record
Token record
Feature activation+0.000
contains
Token contains
Feature activation+0.000
some
Token some
Feature activation+0.000
keyword
Token keyword
Feature activation+0.000
the
Token the
Feature activation+0.000
Desktop
Token Desktop
Feature activation+0.000
got
Token got
Feature activation+0.000
hit
Token hit
Feature activation+0.000
twice
Token twice
Feature activation+0.000
.
Token.
Feature activation+0.412
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ex
Token Ex
Feature activation+0.000
otic
Tokenotic
Feature activation+0.000
calling
Token calling
Feature activation+1.226
.
Token.
Feature activation+0.976
Here
Token Here
Feature activation+0.423
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.683
general
Token general
Feature activation+0.000
news
Token news
Feature activation+0.000
bulletin
Token bulletin
Feature activation+0.000
,
Token,
Feature activation+0.000
copyright
Token copyright
Feature activation+0.000
the
Token the
Feature activation+0.000
English
Token English
Feature activation+0.000
language
Token language
Feature activation+0.000
contain
Token contain
Feature activation+0.000
two
Token two
Feature activation+0.535
u
Token u
Feature activation+0.587
's
Token's
Feature activation+1.731
in
Token in
Feature activation+1.063
a
Token a
Feature activation+1.631
row
Token row
Feature activation+0.043
?
Token?
Feature activation+0.000

INTERVAL 0.000 - 0.396
CONTAINS 99.792%

which
Token which
Feature activation+0.000
were
Token were
Feature activation+0.000
now
Token now
Feature activation+0.000
also
Token also
Feature activation+0.000
contaminated
Token contaminated
Feature activation+0.000
.
Token.
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Am
Token Am
Feature activation+0.000
u
Tokenu
Feature activation+0.000
said
Token said
Feature activation+0.000
while
Token while
Feature activation+0.000
Justin
Token Justin
Feature activation+0.000
Fu
Token Fu
Feature activation+0.000
ente
Tokenente
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
Tech
Token Tech
Feature activation+0.000
team
Token team
Feature activation+0.000
presently
Token presently
Feature activation+0.000
boast
Token boast
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
squad
Token squad
Feature activation+0.000
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
First
TokenFirst
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
aser
Tokenaser
Feature activation+0.000
International
Token International
Feature activation+0.000
changed
Token changed
Feature activation+0.000
its
Token its
Feature activation+0.000
name
Token name
Feature activation+0.000
to
Token to
Feature activation+0.000
Ax
Token Ax
Feature activation+0.000
on
Tokenon
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
Center
Token Center
Feature activation+0.000
for
Token for
Feature activation+0.000
Data
Token Data
Feature activation+0.000
Science
Token Science
Feature activation+0.000
team
Token team
Feature activation+0.000
began
Token began
Feature activation+0.000
developing
Token developing
Feature activation+0.000
initial
Token initial
Feature activation+0.000
models
Token models
Feature activation+0.000
in
Token in
Feature activation+0.000
collaboration
Token collaboration
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H3.11: (feature 6479)

TOP ACTIVATIONS
MAX = 3.767

and
Token and
Feature activation+0.000
Jonah
Token Jonah
Feature activation+0.000
Nolan
Token Nolan
Feature activation+0.000
did
Token did
Feature activation+2.596
reveal
Token reveal
Feature activation+0.242
was
Token was
Feature activation+3.767
the
Token the
Feature activation+0.221
show
Token show
Feature activation+0.000
's
Token's
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
place
Token place
Feature activation+1.264
we
Token we
Feature activation+1.843
see
Token see
Feature activation+0.966
it
Token it
Feature activation+0.745
used
Token used
Feature activation+0.022
is
Token is
Feature activation+3.513
in
Token in
Feature activation+0.608
those
Token those
Feature activation+0.619
[
Token [
Feature activation+0.000
A
TokenA
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
us
Token us
Feature activation+0.051
expect
Token expect
Feature activation+0.016
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+3.398
to
Token to
Feature activation+0.000
remain
Token remain
Feature activation+0.000
ignorant
Token ignorant
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+2.201
participate
Token participate
Feature activation+1.697
in
Token in
Feature activation+0.222
the
Token the
Feature activation+0.334
court
Token court
Feature activation+0.000
are
Token are
Feature activation+3.156
Jordan
Token Jordan
Feature activation+0.000
,
Token,
Feature activation+0.000
Dj
Token Dj
Feature activation+0.000
ib
Tokenib
Feature activation+0.000
out
Tokenout
Feature activation+0.000
world
Token world
Feature activation+0.942
Michael
Token Michael
Feature activation+0.313
F
Token F
Feature activation+0.000
ass
Tokenass
Feature activation+0.000
bender
Tokenbender
Feature activation+0.588
can
Token can
Feature activation+3.149
call
Token call
Feature activation+0.919
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.036
"
Token "
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
stimulation
Token stimulation
Feature activation+1.921
they
Token they
Feature activation+2.639
receive
Token receive
Feature activation+0.723
is
Token is
Feature activation+3.113
when
Token when
Feature activation+0.919
you
Token you
Feature activation+0.000
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
only
Token only
Feature activation+0.000
material
Token material
Feature activation+1.600
that
Token that
Feature activation+2.311
they
Token they
Feature activation+2.054
have
Token have
Feature activation+1.577
are
Token are
Feature activation+3.100
comparisons
Token comparisons
Feature activation+2.184
comprised
Token comprised
Feature activation+1.020
of
Token of
Feature activation+0.000
media
Token media
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
only
Token only
Feature activation+0.000
person
Token person
Feature activation+0.248
to
Token to
Feature activation+1.580
have
Token have
Feature activation+1.394
seen
Token seen
Feature activation+1.300
any
Token any
Feature activation+3.070
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
replies
Token replies
Feature activation+0.000
until
Token until
Feature activation+0.000
now
Token now
Feature activation+0.000
from
Token from
Feature activation+0.406
the
Token the
Feature activation+0.941
list
Token list
Feature activation+0.809
below
Token below
Feature activation+0.637
would
Token would
Feature activation+2.757
be
Token be
Feature activation+3.066
a
Token a
Feature activation+1.069
How
Token How
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
twitter
Token twitter
Feature activation+0.000
from
Token from
Feature activation+0.334
the
Token the
Feature activation+0.771
EV
Token EV
Feature activation+0.000
A
TokenA
Feature activation+0.000
1
Token1
Feature activation+0.000
are
Token are
Feature activation+3.034
labeled
Token labeled
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Shot
TokenShot
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
witnesses
Token witnesses
Feature activation+2.190
investigators
Token investigators
Feature activation+2.205
have
Token have
Feature activation+2.259
are
Token are
Feature activation+3.020
the
Token the
Feature activation+2.171
three
Token three
Feature activation+0.694
children
Token children
Feature activation+0.028
who
Token who
Feature activation+0.374
were
Token were
Feature activation+0.530
compiler
Token compiler
Feature activation+1.118
flag
Token flag
Feature activation+1.176
we
Token we
Feature activation+2.475
are
Token are
Feature activation+2.338
using
Token using
Feature activation+0.939
is
Token is
Feature activation+2.990
-
Token -
Feature activation+0.007
o
Tokeno
Feature activation+0.000
to
Token to
Feature activation+0.335
name
Token name
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+2.139
invest
Token invest
Feature activation+0.000
and
Token and
Feature activation+0.000
create
Token create
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
are
Token are
Feature activation+2.947
large
Token large
Feature activation+0.000
institutions
Token institutions
Feature activation+0.000
,
Token,
Feature activation+0.000
banks
Token banks
Feature activation+0.000
and
Token and
Feature activation+0.000
public
Token public
Feature activation+1.598
atheists
Token atheists
Feature activation+1.396
in
Token in
Feature activation+2.792
pro
Token pro
Feature activation+0.255
sports
Token sports
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.829
I
Token I
Feature activation+0.756
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
public
Token public
Feature activation+1.598
atheists
Token atheists
Feature activation+1.396
in
Token in
Feature activation+2.792
pro
Token pro
Feature activation+0.255
sports
Token sports
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.829
I
Token I
Feature activation+0.756
âĢ
TokenâĢ
Feature activation+0.000
route
Token route
Feature activation+1.385
to
Token to
Feature activation+0.964
having
Token having
Feature activation+1.099
a
Token a
Feature activation+0.351
baby
Token baby
Feature activation+0.000
is
Token is
Feature activation+2.787
international
Token international
Feature activation+0.000
surrog
Token surrog
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
missing
Token missing
Feature activation+2.184
from
Token from
Feature activation+0.406
the
Token the
Feature activation+0.941
list
Token list
Feature activation+0.809
below
Token below
Feature activation+0.637
would
Token would
Feature activation+2.757
be
Token be
Feature activation+3.066
a
Token a
Feature activation+1.069
How
Token How
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
without
Token without
Feature activation+1.952
funnel
Token funnel
Feature activation+0.000
-
Token-
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
bs
Tokenbs
Feature activation+0.000
are
Token are
Feature activation+2.753
Western
Token Western
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
[
Token[
Feature activation+0.000
8
Token8
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
people
Token people
Feature activation+0.834
fleeting
Token fleeting
Feature activation+1.603
war
Token war
Feature activation+0.369
were
Token were
Feature activation+2.732
those
Token those
Feature activation+1.091
who
Token who
Feature activation+0.873
had
Token had
Feature activation+0.683
been
Token been
Feature activation+0.280
terror
Token terror
Feature activation+0.000
12
Token12
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
backups
Token backups
Feature activation+2.470
are
Token are
Feature activation+2.726
Kell
Token Kell
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
,
Token,
Feature activation+0.605
who
Token who
Feature activation+1.117

Top DFA by src position
MAX = 5.293

details
Token details
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
only
Token only
Feature activation+5.164
Top resid features:
thing
Token thing
Feature activation+0.630
Top resid features:
show
Token show
Feature activation+0.019
Top resid features:
runners
Tokenrunners
Feature activation+0.009
Top resid features:
Lisa
Token Lisa
Feature activation+0.023
Top resid features:
Joy
Token Joy
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
used
Token used
Feature activation-0.002
Top resid features:
elsewhere
Token elsewhere
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
The
Token The
Feature activation+0.039
Top resid features:
only
Token only
Feature activation+5.013
Top resid features:
place
Token place
Feature activation+0.246
Top resid features:
we
Token we
Feature activation+0.018
Top resid features:
see
Token see
Feature activation+0.020
Top resid features:
it
Token it
Feature activation+0.054
Top resid features:
used
Token used
Feature activation-0.216
Top resid features:
our
Token our
Feature activation+0.001
Top resid features:
sleep
Token sleep
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
only
Token only
Feature activation+4.872
Top resid features:
thing
Token thing
Feature activation+0.552
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
powers
Token powers
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.038
Top resid features:
oppress
Token oppress
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
Dar
Token Dar
Feature activation-0.001
Top resid features:
fur
Tokenfur
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
The
Token The
Feature activation-0.023
Top resid features:
only
Token only
Feature activation+5.033
Top resid features:
Arab
Token Arab
Feature activation+0.096
Top resid features:
states
Token states
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.077
Top resid features:
participate
Token participate
Feature activation-0.031
Top resid features:
in
Token in
Feature activation-0.012
Top resid features:
unseen
Token unseen
Feature activation+0.036
Top resid features:
bathroom
Token bathroom
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.033
Top resid features:
are
Tokenare
Feature activation-0.033
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
only
Token only
Feature activation+4.423
Top resid features:
ones
Token ones
Feature activation+0.136
Top resid features:
in
Token in
Feature activation+0.099
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
world
Token world
Feature activation+0.018
Top resid features:
Michael
Token Michael
Feature activation+0.165
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
quickly
Token quickly
Feature activation-0.008
Top resid features:
consumed
Token consumed
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.076
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
only
Token only
Feature activation+5.293
Top resid features:
stimulation
Token stimulation
Feature activation+0.058
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
receive
Token receive
Feature activation-0.243
Top resid features:
is
Token is
Feature activation-0.297
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
want
Token want
Feature activation-0.039
Top resid features:
answers
Token answers
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
and
Token and
Feature activation-0.047
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
only
Token only
Feature activation+4.867
Top resid features:
material
Token material
Feature activation+0.068
Top resid features:
that
Token that
Feature activation+0.108
Top resid features:
they
Token they
Feature activation-0.008
Top resid features:
have
Token have
Feature activation-0.140
Top resid features:
are
Token are
Feature activation-0.152
Top resid features:
note
Token note
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
The
TokenThe
Feature activation+0.031
Top resid features:
only
Token only
Feature activation+4.822
Top resid features:
person
Token person
Feature activation+0.100
Top resid features:
to
Token to
Feature activation+0.041
Top resid features:
have
Token have
Feature activation-0.042
Top resid features:
seen
Token seen
Feature activation-0.049
Top resid features:
any
Token any
Feature activation-0.198
Top resid features:
Network
Token Network
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Perhaps
TokenPerhaps
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
only
Token only
Feature activation+4.575
Top resid features:
thing
Token thing
Feature activation+0.375
Top resid features:
missing
Token missing
Feature activation+0.152
Top resid features:
from
Token from
Feature activation+0.032
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
list
Token list
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
GH
Token GH
Feature activation+0.002
Top resid features:
5
Token5
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
The
Token The
Feature activation-0.023
Top resid features:
only
Token only
Feature activation+4.704
Top resid features:
shots
Token shots
Feature activation+0.023
Top resid features:
that
Token that
Feature activation+0.103
Top resid features:
you
Token you
Feature activation+0.015
Top resid features:
see
Token see
Feature activation+0.097
Top resid features:
from
Token from
Feature activation+0.024
Top resid features:
but
Token but
Feature activation-0.028
Top resid features:
so
Token so
Feature activation-0.004
Top resid features:
far
Token far
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
only
Token only
Feature activation+5.225
Top resid features:
witnesses
Token witnesses
Feature activation+0.034
Top resid features:
investigators
Token investigators
Feature activation-0.054
Top resid features:
have
Token have
Feature activation-0.233
Top resid features:
are
Token are
Feature activation-0.289
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
linked
Token linked
Feature activation+0.005
Top resid features:
automatically
Token automatically
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
and
Token and
Feature activation-0.118
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
only
Token only
Feature activation+5.209
Top resid features:
compiler
Token compiler
Feature activation+0.025
Top resid features:
flag
Token flag
Feature activation+0.018
Top resid features:
we
Token we
Feature activation+0.017
Top resid features:
are
Token are
Feature activation-0.014
Top resid features:
using
Token using
Feature activation-0.424
Top resid features:
flows
Tokenflows
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
And
Token And
Feature activation-0.013
Top resid features:
so
Token so
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.039
Top resid features:
only
Token only
Feature activation+5.016
Top resid features:
people
Token people
Feature activation+0.044
Top resid features:
with
Token with
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
apparatus
Token apparatus
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.123
Top resid features:
becoming
Token becoming
Feature activation-0.020
Top resid features:
one
Token one
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
only
Token only
Feature activation+4.263
Top resid features:
public
Token public
Feature activation+0.021
Top resid features:
atheists
Token atheists
Feature activation+0.050
Top resid features:
in
Token in
Feature activation+0.033
Top resid features:
pro
Token pro
Feature activation-0.005
Top resid features:
sports
Token sports
Feature activation-0.020
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.004
Top resid features:
becoming
Token becoming
Feature activation+0.013
Top resid features:
one
Token one
Feature activation+0.033
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.092
Top resid features:
only
Token only
Feature activation+4.129
Top resid features:
public
Token public
Feature activation+0.023
Top resid features:
atheists
Token atheists
Feature activation+0.145
Top resid features:
in
Token in
Feature activation+0.094
Top resid features:
pro
Token pro
Feature activation+0.000
Top resid features:
sports
Token sports
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
developed
Token developed
Feature activation+0.008
Top resid features:
world
Token world
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
the
Token the
Feature activation-0.035
Top resid features:
only
Token only
Feature activation+4.704
Top resid features:
route
Token route
Feature activation+0.040
Top resid features:
to
Token to
Feature activation+0.085
Top resid features:
having
Token having
Feature activation+0.007
Top resid features:
a
Token a
Feature activation-0.190
Top resid features:
baby
Token baby
Feature activation-0.030
Top resid features:
Network
Token Network
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Perhaps
TokenPerhaps
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
only
Token only
Feature activation+4.313
Top resid features:
thing
Token thing
Feature activation+0.135
Top resid features:
missing
Token missing
Feature activation+0.164
Top resid features:
from
Token from
Feature activation+0.044
Top resid features:
the
Token the
Feature activation-0.022
Top resid features:
list
Token list
Feature activation-0.012
Top resid features:
3
Token3
Feature activation+0.001
Top resid features:
][
Token][
Feature activation-0.017
Top resid features:
7
Token7
Feature activation+0.001
Top resid features:
]
Token]
Feature activation+0.019
Top resid features:
The
Token The
Feature activation-0.023
Top resid features:
only
Token only
Feature activation+4.719
Top resid features:
Australian
Token Australian
Feature activation+0.035
Top resid features:
states
Token states
Feature activation+0.020
Top resid features:
or
Token or
Feature activation-0.073
Top resid features:
territories
Token territories
Feature activation-0.002
Top resid features:
without
Token without
Feature activation+0.051
Top resid features:
carefully
Token carefully
Feature activation+0.003
Top resid features:
crafted
Token crafted
Feature activation+0.009
Top resid features:
story
Token story
Feature activation+0.003
Top resid features:
that
Token that
Feature activation+0.056
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
only
Token only
Feature activation+3.878
Top resid features:
people
Token people
Feature activation+0.049
Top resid features:
fleeting
Token fleeting
Feature activation+0.237
Top resid features:
war
Token war
Feature activation+0.072
Top resid features:
were
Token were
Feature activation-0.046
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
12
Token12
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
The
Token The
Feature activation-0.263
Top resid features:
only
Token only
Feature activation+4.421
Top resid features:
backups
Token backups
Feature activation+0.138
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
Kell
Token Kell
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation+0.000
Top resid features:
Moore
Token Moore
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.05

Head 3: 0.03

Head 4: 0.02

Head 5: 0.06

Head 6: 0.06

Head 7: 0.05

Head 8: 0.04

Head 9: 0.04

Head 10: 0.05

Head 11: 0.52

Positive logits

conceivable1.87

imaginable1.81

ever1.74

besides1.72

EVER1.67

feasible1.52

redeem1.51

possible1.47

Possible1.46

soever1.43

available1.42

覚醒1.41

survives1.40

whatsoever1.38

lasts1.36

remaining1.35

Ever1.35

surviving1.33

viable1.33

exception1.31

Negative logits

unfocusedRange-1.59

herty-1.49

entimes-1.44

etc-1.44

ustomed-1.40

iddles-1.40

joice-1.38

oother-1.37

actionDate-1.37

xtap-1.33

oxide-1.32

ullivan-1.31

inances-1.31

ructose-1.30

dayName-1.30

arta-1.29

��-1.28

brace-1.28

utterstock-1.26

ensor-1.26

INTERVAL 3.390 - 3.767
CONTAINS 0.000%

us
Token us
Feature activation+0.051
expect
Token expect
Feature activation+0.016
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+3.398
to
Token to
Feature activation+0.000
remain
Token remain
Feature activation+0.000
ignorant
Token ignorant
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
Jonah
Token Jonah
Feature activation+0.000
Nolan
Token Nolan
Feature activation+0.000
did
Token did
Feature activation+2.596
reveal
Token reveal
Feature activation+0.242
was
Token was
Feature activation+3.767
the
Token the
Feature activation+0.221
show
Token show
Feature activation+0.000
's
Token's
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
place
Token place
Feature activation+1.264
we
Token we
Feature activation+1.843
see
Token see
Feature activation+0.966
it
Token it
Feature activation+0.745
used
Token used
Feature activation+0.022
is
Token is
Feature activation+3.513
in
Token in
Feature activation+0.608
those
Token those
Feature activation+0.619
[
Token [
Feature activation+0.000
A
TokenA
Feature activation+0.000
ur
Tokenur
Feature activation+0.000

INTERVAL 3.014 - 3.390
CONTAINS 0.001%

from
Token from
Feature activation+0.334
the
Token the
Feature activation+0.771
EV
Token EV
Feature activation+0.000
A
TokenA
Feature activation+0.000
1
Token1
Feature activation+0.000
are
Token are
Feature activation+3.034
labeled
Token labeled
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Shot
TokenShot
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
witnesses
Token witnesses
Feature activation+2.190
investigators
Token investigators
Feature activation+2.205
have
Token have
Feature activation+2.259
are
Token are
Feature activation+3.020
the
Token the
Feature activation+2.171
three
Token three
Feature activation+0.694
children
Token children
Feature activation+0.028
who
Token who
Feature activation+0.374
were
Token were
Feature activation+0.530
world
Token world
Feature activation+0.942
Michael
Token Michael
Feature activation+0.313
F
Token F
Feature activation+0.000
ass
Tokenass
Feature activation+0.000
bender
Tokenbender
Feature activation+0.588
can
Token can
Feature activation+3.149
call
Token call
Feature activation+0.919
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.036
"
Token "
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
stimulation
Token stimulation
Feature activation+1.921
they
Token they
Feature activation+2.639
receive
Token receive
Feature activation+0.723
is
Token is
Feature activation+3.113
when
Token when
Feature activation+0.919
you
Token you
Feature activation+0.000
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
from
Token from
Feature activation+0.406
the
Token the
Feature activation+0.941
list
Token list
Feature activation+0.809
below
Token below
Feature activation+0.637
would
Token would
Feature activation+2.757
be
Token be
Feature activation+3.066
a
Token a
Feature activation+1.069
How
Token How
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
twitter
Token twitter
Feature activation+0.000

INTERVAL 2.637 - 3.014
CONTAINS 0.002%

consumed
Token consumed
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
stimulation
Token stimulation
Feature activation+1.921
they
Token they
Feature activation+2.639
receive
Token receive
Feature activation+0.723
is
Token is
Feature activation+3.113
when
Token when
Feature activation+0.919
you
Token you
Feature activation+0.000
return
Token return
Feature activation+0.000
they
Token they
Feature activation+1.484
are
Token are
Feature activation+1.985
in
Token in
Feature activation+1.144
the
Token the
Feature activation+1.233
news
Token news
Feature activation+0.358
is
Token is
Feature activation+2.707
when
Token when
Feature activation+0.741
we
Token we
Feature activation+0.000
hear
Token hear
Feature activation+0.000
another
Token another
Feature activation+0.000
report
Token report
Feature activation+0.000
to
Token to
Feature activation+2.139
invest
Token invest
Feature activation+0.000
and
Token and
Feature activation+0.000
create
Token create
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
are
Token are
Feature activation+2.947
large
Token large
Feature activation+0.000
institutions
Token institutions
Feature activation+0.000
,
Token,
Feature activation+0.000
banks
Token banks
Feature activation+0.000
and
Token and
Feature activation+0.000
drastic
Token drastic
Feature activation+0.000
career
Token career
Feature activation+0.000
change
Token change
Feature activation+0.000
first
Token first
Feature activation+0.000
)
Token)
Feature activation+0.000
are
Token are
Feature activation+2.669
the
Token the
Feature activation+0.000
logging
Token logging
Feature activation+0.000
dudes
Token dudes
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
public
Token public
Feature activation+1.598
atheists
Token atheists
Feature activation+1.396
in
Token in
Feature activation+2.792
pro
Token pro
Feature activation+0.255
sports
Token sports
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.829
I
Token I
Feature activation+0.756
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000

INTERVAL 2.260 - 2.637
CONTAINS 0.004%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
material
Token material
Feature activation+1.600
that
Token that
Feature activation+2.311
they
Token they
Feature activation+2.054
have
Token have
Feature activation+1.577
are
Token are
Feature activation+3.100
comparisons
Token comparisons
Feature activation+2.184
comprised
Token comprised
Feature activation+1.020
only
Token only
Feature activation+0.000
such
Token such
Feature activation+0.885
fossil
Token fossil
Feature activation+0.681
ized
Tokenized
Feature activation+1.276
dinosaur
Token dinosaur
Feature activation+1.656
from
Token from
Feature activation+2.437
a
Token a
Feature activation+0.371
marine
Token marine
Feature activation+0.000
str
Token str
Feature activation+0.000
atum
Tokenatum
Feature activation+0.000
that
Token that
Feature activation+1.240
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
compiler
Token compiler
Feature activation+1.118
flag
Token flag
Feature activation+1.176
we
Token we
Feature activation+2.475
are
Token are
Feature activation+2.338
using
Token using
Feature activation+0.939
is
Token is
Feature activation+2.990
-
Token -
Feature activation+0.007
o
Tokeno
Feature activation+0.000
be
Token be
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
countries
Token countries
Feature activation+2.288
that
Token that
Feature activation+2.585
exists
Token exists
Feature activation+1.941
to
Token to
Feature activation+1.639
have
Token have
Feature activation+0.967
gained
Token gained
Feature activation+0.279
Z
TokenZ
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.095
musician
Token musician
Feature activation+1.483
who
Token who
Feature activation+2.400
didn
Token didn
Feature activation+0.912
't
Token't
Feature activation+1.533
change
Token change
Feature activation+0.000
instruments
Token instruments
Feature activation+0.000
between
Token between
Feature activation+0.000

INTERVAL 1.883 - 2.260
CONTAINS 0.006%

under
Tokenunder
Feature activation+0.033
-
Token-
Feature activation+0.000
M
TokenM
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
lin
Tokenlin
Feature activation+0.029
who
Token who
Feature activation+2.218
âĢ
TokenâĢ
Feature activation+0.454
Ļ
TokenĻ
Feature activation+0.050
s
Tokens
Feature activation+0.268
actually
Token actually
Feature activation+1.347
seen
Token seen
Feature activation+0.000
is
Token is
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
thing
Token thing
Feature activation+0.638
funny
Token funny
Feature activation+1.931
about
Token about
Feature activation+2.029
this
Token this
Feature activation+0.971
.
Token.
Feature activation+0.571
Rape
Token Rape
Feature activation+0.000
jokes
Token jokes
Feature activation+0.000
only
Token only
Feature activation+0.000
witnesses
Token witnesses
Feature activation+2.190
investigators
Token investigators
Feature activation+2.205
have
Token have
Feature activation+2.259
are
Token are
Feature activation+3.020
the
Token the
Feature activation+2.171
three
Token three
Feature activation+0.694
children
Token children
Feature activation+0.028
who
Token who
Feature activation+0.374
were
Token were
Feature activation+0.530
involved
Token involved
Feature activation+0.195
quickly
Token quickly
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
stimulation
Token stimulation
Feature activation+1.921
they
Token they
Feature activation+2.639
receive
Token receive
Feature activation+0.723
is
Token is
Feature activation+3.113
when
Token when
Feature activation+0.919
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
frequency
Token frequency
Feature activation+1.147
in
Token in
Feature activation+1.483
between
Token between
Feature activation+1.935
is
Token is
Feature activation+2.670
El
Token El
Feature activation+0.041
ver
Tokenver
Feature activation+0.150
um
Tokenum
Feature activation+0.000
,
Token,
Feature activation+0.349

INTERVAL 1.507 - 1.883
CONTAINS 0.007%

only
Token only
Feature activation+0.000
reason
Token reason
Feature activation+0.428
we
Token we
Feature activation+0.693
were
Token were
Feature activation+0.993
there
Token there
Feature activation+0.946
was
Token was
Feature activation+1.695
because
Token because
Feature activation+0.602
my
Token my
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
N
Token N
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
countries
Token countries
Feature activation+2.288
that
Token that
Feature activation+2.585
exists
Token exists
Feature activation+1.941
to
Token to
Feature activation+1.639
have
Token have
Feature activation+0.967
gained
Token gained
Feature activation+0.279
its
Token its
Feature activation+0.000
sovereignty
Token sovereignty
Feature activation+0.000
unw
Token unw
Feature activation+0.000
only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.773
I
Token I
Feature activation+0.691
see
Token see
Feature activation+0.206
him
Token him
Feature activation+0.570
not
Token not
Feature activation+1.578
starting
Token starting
Feature activation+0.000
in
Token in
Feature activation+0.000
Week
Token Week
Feature activation+0.000
1
Token 1
Feature activation+0.000
is
Token is
Feature activation+1.433
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
blue
Token blue
Feature activation+1.524
planet
Token planet
Feature activation+1.590
.
Token.
Feature activation+0.541
But
Token But
Feature activation+0.105
out
Token out
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
Saturn
Token Saturn
Feature activation+0.000
-
Token-
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
film
Token film
Feature activation+0.124
that
Token that
Feature activation+2.449
I
Token I
Feature activation+1.778
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
swing
Token swing
Feature activation+0.000

INTERVAL 1.130 - 1.507
CONTAINS 0.009%

,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
way
Token way
Feature activation+1.320
we
Token we
Feature activation+0.003
can
Token can
Feature activation+1.077
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.500
.
Token.
Feature activation+0.649
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.418
reason
Token reason
Feature activation+1.174
we
Token we
Feature activation+1.049
know
Token know
Feature activation+0.875
of
Token of
Feature activation+1.221
her
Token her
Feature activation+0.784
actions
Token actions
Feature activation+0.260
that
Token that
Feature activation+1.357
day
Token day
Feature activation+0.210
.
Token.
Feature activation+0.196
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
time
Token time
Feature activation+0.791
they
Token they
Feature activation+1.484
are
Token are
Feature activation+1.985
in
Token in
Feature activation+1.144
the
Token the
Feature activation+1.233
news
Token news
Feature activation+0.358
is
Token is
Feature activation+2.707
when
Token when
Feature activation+0.741
we
Token we
Feature activation+0.000
js
Tokenjs
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.382
sane
Token sane
Feature activation+0.542
way
Token way
Feature activation+1.420
to
Token to
Feature activation+0.437
handle
Token handle
Feature activation+0.000
a
Token a
Feature activation+0.185
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
only
Token only
Feature activation+0.000
compelling
Token compelling
Feature activation+1.097
speeches
Token speeches
Feature activation+1.187
and
Token and
Feature activation+0.821
storylines
Token storylines
Feature activation+0.472
of
Token of
Feature activation+1.360
the
Token the
Feature activation+1.088
night
Token night
Feature activation+0.000
came
Token came
Feature activation+1.952
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.753 - 1.130
CONTAINS 0.014%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.229
remarkable
Token remarkable
Feature activation+1.837
thing
Token thing
Feature activation+0.457
about
Token about
Feature activation+0.827
those
Token those
Feature activation+0.914
outcomes
Token outcomes
Feature activation+0.180
is
Token is
Feature activation+2.514
that
Token that
Feature activation+0.630
few
Token few
Feature activation+0.000
only
Token only
Feature activation+0.000
thing
Token thing
Feature activation+0.639
standing
Token standing
Feature activation+1.529
in
Token in
Feature activation+1.575
my
Token my
Feature activation+0.717
way
Token way
Feature activation+0.936
is
Token is
Feature activation+1.676
myself
Token myself
Feature activation+0.000
.
Token.
Feature activation+0.000
Past
Token Past
Feature activation+0.000
events
Token events
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
negative
Token negative
Feature activation+0.443
rested
Token rested
Feature activation+1.711
in
Token in
Feature activation+1.098
the
Token the
Feature activation+0.824
tax
Token tax
Feature activation+0.000
it
Token it
Feature activation+1.378
would
Token would
Feature activation+1.184
levy
Token levy
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
only
Token only
Feature activation+0.000
being
Token being
Feature activation+1.054
allowed
Token allowed
Feature activation+1.332
supervised
Token supervised
Feature activation+0.841
visits
Token visits
Feature activation+0.269
,
Token,
Feature activation+0.344
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
game
Token game
Feature activation+1.348
you
Token you
Feature activation+2.645
can
Token can
Feature activation+2.282
play
Token play
Feature activation+0.788
on
Token on
Feature activation+1.416
these
Token these
Feature activation+1.171
machines
Token machines
Feature activation+0.277
,
Token,
Feature activation+0.966
either
Token either
Feature activation+0.000

INTERVAL 0.377 - 0.753
CONTAINS 0.019%

Su
Token Su
Feature activation+0.000
ika
Tokenika
Feature activation+0.000
Bag
Token Bag
Feature activation+0.000
els
Tokenels
Feature activation+0.000
are
Token are
Feature activation+0.000
available
Token available
Feature activation+0.609
each
Token each
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
MJ
Token MJ
Feature activation+1.621
figure
Token figure
Feature activation+1.567
currently
Token currently
Feature activation+1.558
out
Token out
Feature activation+0.238
in
Token in
Feature activation+0.504
the
Token the
Feature activation+1.043
Marvel
Token Marvel
Feature activation+0.000
Legends
Token Legends
Feature activation+0.000
line
Token line
Feature activation+1.048
,
Token,
Feature activation+1.050
-
Token-
Feature activation+0.000
M
TokenM
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
lin
Tokenlin
Feature activation+0.029
who
Token who
Feature activation+2.218
âĢ
TokenâĢ
Feature activation+0.454
Ļ
TokenĻ
Feature activation+0.050
s
Tokens
Feature activation+0.268
actually
Token actually
Feature activation+1.347
seen
Token seen
Feature activation+0.000
the
Token the
Feature activation+0.000
males
Token males
Feature activation+0.000
losers
Token losers
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
males
Token males
Feature activation+0.666
in
Token in
Feature activation+2.200
this
Token this
Feature activation+1.354
world
Token world
Feature activation+0.965
who
Token who
Feature activation+2.190
put
Token put
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
solution
Token solution
Feature activation+0.000
that
Token that
Feature activation+0.000
kept
Token kept
Feature activation+0.593
one
Token one
Feature activation+0.097
character
Token character
Feature activation+0.000
alive
Token alive
Feature activation+0.000
and
Token and
Feature activation+0.042
allowed
Token allowed
Feature activation+0.000

INTERVAL 0.000 - 0.377
CONTAINS 99.937%

iants
Tokeniants
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
First
TokenFirst
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
crab
Token crab
Feature activation+0.000
looked
Token looked
Feature activation+0.000
as
Token as
Feature activation+0.000
though
Token though
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
touch
Token touch
Feature activation+0.000
base
Token base
Feature activation+0.000
with
Token with
Feature activation+0.000
and
Token and
Feature activation+0.000
rear
Token rear
Feature activation+0.000
view
Token view
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
D
Token D
Feature activation+0.000
Luther
Token Luther
Feature activation+0.000
King
Token King
Feature activation+0.000
Jr
Token Jr
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Once
TokenOnce
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ander
Tokenander
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
4
Token4
Feature activation+0.000
teaspoon
Token teaspoon
Feature activation+0.000
c
Token c
Feature activation+0.000
umin
Tokenumin
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 3 in H3.11: (feature 443)

TOP ACTIVATIONS
MAX = 4.134

Ped
Token Ped
Feature activation+0.130
h
Tokenh
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
took
Token took
Feature activation+2.047
was
Token was
Feature activation+4.134
to
Token to
Feature activation+2.855
vac
Token vac
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
the
Token the
Feature activation+0.000
offices
Token offices
Feature activation+0.000
an
Token an
Feature activation+0.421
oil
Token oil
Feature activation+0.000
and
Token and
Feature activation+0.000
gas
Token gas
Feature activation+0.000
producer
Token producer
Feature activation+0.000
since
Token since
Feature activation+4.090
prices
Token prices
Feature activation+0.000
started
Token started
Feature activation+0.000
falling
Token falling
Feature activation+0.000
last
Token last
Feature activation+0.000
summer
Token summer
Feature activation+0.000
first
Token first
Feature activation+0.000
African
Token African
Feature activation+2.265
-
Token-
Feature activation+1.304
American
TokenAmerican
Feature activation+2.289
Republican
Token Republican
Feature activation+2.766
to
Token to
Feature activation+3.953
serve
Token serve
Feature activation+0.679
in
Token in
Feature activation+0.619
the
Token the
Feature activation+0.525
Oregon
Token Oregon
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.009
ever
Token ever
Feature activation+2.022
BMW
Token BMW
Feature activation+2.507
i
Token i
Feature activation+3.816
3
Token3
Feature activation+2.215
s
Tokens
Feature activation+2.916
features
Token features
Feature activation+1.848
an
Token an
Feature activation+0.407
output
Token output
Feature activation+0.000
made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
prisoner
Token prisoner
Feature activation+3.591
transfer
Token transfer
Feature activation+3.780
on
Token on
Feature activation+2.446
Tuesday
Token Tuesday
Feature activation+0.459
,
Token,
Feature activation+0.500
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
offer
Token offer
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.202
commercial
Token commercial
Feature activation+2.651
Vive
Token Vive
Feature activation+2.408
units
Token units
Feature activation+3.761
via
Token via
Feature activation+1.610
a
Token a
Feature activation+0.799
limited
Token limited
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
of
Token of
Feature activation+0.000
major
Token major
Feature activation+0.000
professional
Token professional
Feature activation+0.000
sports
Token sports
Feature activation+0.000
league
Token league
Feature activation+0.000
in
Token in
Feature activation+2.033
any
Token any
Feature activation+3.626
Latin
Token Latin
Feature activation+0.000
American
Token American
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.113
person
Token person
Feature activation+1.570
in
Token in
Feature activation+2.716
the
Token the
Feature activation+2.887
world
Token world
Feature activation+1.084
to
Token to
Feature activation+3.617
be
Token be
Feature activation+3.508
legally
Token legally
Feature activation+0.681
executed
Token executed
Feature activation+0.000
using
Token using
Feature activation+0.220
an
Token an
Feature activation+0.000
first
Token first
Feature activation+0.133
kn
Token kn
Feature activation+1.224
uckle
Tokenuckle
Feature activation+0.519
ball
Tokenball
Feature activation+0.000
pitcher
Token pitcher
Feature activation+1.041
to
Token to
Feature activation+3.600
win
Token win
Feature activation+1.758
the
Token the
Feature activation+0.000
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.000
tournament
Token tournament
Feature activation+2.939
game
Token game
Feature activation+3.597
,
Token,
Feature activation+1.149
and
Token and
Feature activation+0.266
many
Token many
Feature activation+0.000
people
Token people
Feature activation+0.000
put
Token put
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
prisoner
Token prisoner
Feature activation+3.591
transfer
Token transfer
Feature activation+3.780
on
Token on
Feature activation+2.446
Tuesday
Token Tuesday
Feature activation+0.459
,
Token,
Feature activation+0.500
ahead
Token ahead
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+0.255
image
Token image
Feature activation+2.216
of
Token of
Feature activation+3.568
the
Token the
Feature activation+3.268
release
Token release
Feature activation+1.558
we
Token we
Feature activation+2.382
see
Token see
Feature activation+2.630
a
Token a
Feature activation+0.403
challenges
Token challenges
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Tesla
Token Tesla
Feature activation+1.539
car
Token car
Feature activation+3.526
,
Token,
Feature activation+1.794
von
Token von
Feature activation+0.000
Hol
Token Hol
Feature activation+0.000
z
Tokenz
Feature activation+0.000
haus
Tokenhaus
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.274
service
Token service
Feature activation+2.186
user
Token user
Feature activation+2.823
involvement
Token involvement
Feature activation+3.524
movement
Token movement
Feature activation+2.223
.
Token.
Feature activation+0.810
Founder
Token Founder
Feature activation+0.000
member
Token member
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
person
Token person
Feature activation+1.570
in
Token in
Feature activation+2.716
the
Token the
Feature activation+2.887
world
Token world
Feature activation+1.084
to
Token to
Feature activation+3.617
be
Token be
Feature activation+3.508
legally
Token legally
Feature activation+0.681
executed
Token executed
Feature activation+0.000
using
Token using
Feature activation+0.220
an
Token an
Feature activation+0.000
electric
Token electric
Feature activation+0.000
OP
Token OP
Feature activation+0.000
OY
TokenOY
Feature activation+0.000
to
Token to
Feature activation+2.947
do
Token do
Feature activation+1.398
it
Token it
Feature activation+0.180
since
Token since
Feature activation+3.481
Kurt
Token Kurt
Feature activation+0.000
Warner
Token Warner
Feature activation+0.000
did
Token did
Feature activation+0.000
so
Token so
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Retro
Token Retro
Feature activation+0.000
Fitness
Token Fitness
Feature activation+0.000
gym
Token gym
Feature activation+2.821
in
Token in
Feature activation+3.469
Chicago
Token Chicago
Feature activation+0.230
,
Token,
Feature activation+1.177
C
Token C
Feature activation+0.000
ui
Tokenui
Feature activation+0.000
said
Token said
Feature activation+0.000
U
Token U
Feature activation+0.391
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
city
Token city
Feature activation+0.657
to
Token to
Feature activation+3.449
file
Token file
Feature activation+1.340
for
Token for
Feature activation+0.182
bankruptcy
Token bankruptcy
Feature activation+0.000
,
Token,
Feature activation+1.108
pressured
Token pressured
Feature activation+0.000
of
Token of
Feature activation+2.457
the
Token the
Feature activation+1.820
NSA
Token NSA
Feature activation+0.619
's
Token's
Feature activation+0.396
powers
Token powers
Feature activation+0.287
since
Token since
Feature activation+3.430
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
first
Token first
Feature activation+0.201
drive
Token drive
Feature activation+1.609
-
Token-
Feature activation+0.000
through
Tokenthrough
Feature activation+0.000
restaurant
Token restaurant
Feature activation+3.008
in
Token in
Feature activation+3.425
the
Token the
Feature activation+2.619
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000

Top DFA by src position
MAX = 4.923

âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.019
Top resid features:
first
Token first
Feature activation+4.923
Top resid features:
course
Token course
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.072
Top resid features:
action
Token action
Feature activation+0.011
Top resid features:
Ped
Token Ped
Feature activation-0.002
Top resid features:
h
Tokenh
Feature activation-0.003
Top resid features:
billion
Token billion
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
It
Token It
Feature activation+0.047
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
first
Token first
Feature activation+4.675
Top resid features:
major
Token major
Feature activation-0.007
Top resid features:
deal
Token deal
Feature activation+0.017
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
an
Token an
Feature activation-0.017
Top resid features:
oil
Token oil
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.032
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
first
Token first
Feature activation+4.256
Top resid features:
African
Token African
Feature activation+0.052
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
American
TokenAmerican
Feature activation+0.056
Top resid features:
Republican
Token Republican
Feature activation+0.148
Top resid features:
to
Token to
Feature activation+0.091
Top resid features:
BMW
Token BMW
Feature activation+0.016
Top resid features:
i
Token i
Feature activation+0.016
Top resid features:
3
Token3
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
The
Token The
Feature activation-0.016
Top resid features:
first
Token first
Feature activation+3.959
Top resid features:
ever
Token ever
Feature activation-0.005
Top resid features:
BMW
Token BMW
Feature activation+0.162
Top resid features:
i
Token i
Feature activation+0.060
Top resid features:
3
Token3
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
Norwegian
Token Norwegian
Feature activation+0.016
Top resid features:
inmates
Token inmates
Feature activation+0.042
Top resid features:
made
Token made
Feature activation-0.005
Top resid features:
up
Token up
Feature activation-0.065
Top resid features:
the
Token the
Feature activation-0.031
Top resid features:
first
Token first
Feature activation+3.830
Top resid features:
prisoner
Token prisoner
Feature activation+0.356
Top resid features:
transfer
Token transfer
Feature activation+0.083
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.001
Top resid features:
TC
TokenTC
Feature activation-0.003
Top resid features:
will
Token will
Feature activation-0.007
Top resid features:
offer
Token offer
Feature activation+0.087
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
first
Token first
Feature activation+3.690
Top resid features:
commercial
Token commercial
Feature activation+0.106
Top resid features:
Vive
Token Vive
Feature activation+0.280
Top resid features:
units
Token units
Feature activation+0.102
Top resid features:
via
Token via
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+0.013
Top resid features:
would
Token would
Feature activation+0.070
Top resid features:
be
Token be
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
first
Token first
Feature activation+3.927
Top resid features:
whole
Token whole
Feature activation+0.012
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
hearted
Tokenhearted
Feature activation+0.011
Top resid features:
venture
Token venture
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
convicted
Token convicted
Feature activation-0.034
Top resid features:
murderer
Token murderer
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.077
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
first
Token first
Feature activation+3.899
Top resid features:
person
Token person
Feature activation+0.115
Top resid features:
in
Token in
Feature activation+0.086
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
world
Token world
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.003
Top resid features:
ickey
Tokenickey
Feature activation+0.010
Top resid features:
became
Token became
Feature activation+0.031
Top resid features:
the
Token the
Feature activation-0.131
Top resid features:
first
Token first
Feature activation+4.070
Top resid features:
kn
Token kn
Feature activation+0.019
Top resid features:
uckle
Tokenuckle
Feature activation+0.028
Top resid features:
ball
Tokenball
Feature activation+0.023
Top resid features:
pitcher
Token pitcher
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.101
Top resid features:
As
TokenAs
Feature activation+0.020
Top resid features:
he
Tokenhe
Feature activation+0.002
Top resid features:
ville
Tokenville
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.035
Top resid features:
their
Token their
Feature activation-0.003
Top resid features:
first
Token first
Feature activation+4.023
Top resid features:
tournament
Token tournament
Feature activation+0.038
Top resid features:
game
Token game
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
Norwegian
Token Norwegian
Feature activation+0.056
Top resid features:
inmates
Token inmates
Feature activation+0.093
Top resid features:
made
Token made
Feature activation-0.013
Top resid features:
up
Token up
Feature activation-0.119
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
first
Token first
Feature activation+3.847
Top resid features:
prisoner
Token prisoner
Feature activation+0.228
Top resid features:
transfer
Token transfer
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
In
TokenIn
Feature activation-0.022
Top resid features:
the
Token the
Feature activation-0.095
Top resid features:
very
Token very
Feature activation-0.004
Top resid features:
first
Token first
Feature activation+3.912
Top resid features:
image
Token image
Feature activation+0.095
Top resid features:
of
Token of
Feature activation+0.226
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
release
Token release
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
design
Token design
Feature activation+0.037
Top resid features:
challenges
Token challenges
Feature activation+0.039
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.047
Top resid features:
first
Token first
Feature activation+3.743
Top resid features:
Tesla
Token Tesla
Feature activation+0.271
Top resid features:
car
Token car
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
von
Token von
Feature activation+0.000
Top resid features:
Hol
Token Hol
Feature activation+0.000
Top resid features:
probably
Token probably
Feature activation-0.009
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation-0.006
Top resid features:
as
Token as
Feature activation+0.078
Top resid features:
the
Token the
Feature activation-0.040
Top resid features:
first
Token first
Feature activation+3.734
Top resid features:
service
Token service
Feature activation+0.060
Top resid features:
user
Token user
Feature activation+0.223
Top resid features:
involvement
Token involvement
Feature activation+0.050
Top resid features:
movement
Token movement
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
convicted
Token convicted
Feature activation-0.034
Top resid features:
murderer
Token murderer
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
first
Token first
Feature activation+4.020
Top resid features:
person
Token person
Feature activation+0.080
Top resid features:
in
Token in
Feature activation+0.054
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
world
Token world
Feature activation+0.013
Top resid features:
to
Token to
Feature activation-0.091
Top resid features:
he
Token he
Feature activation+0.019
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.014
Top resid features:
SN
Token SN
Feature activation+0.023
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
first
Token first
Feature activation+4.063
Top resid features:
OP
Token OP
Feature activation+0.015
Top resid features:
OY
TokenOY
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
do
Token do
Feature activation-0.042
Top resid features:
it
Token it
Feature activation-0.087
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
will
Token will
Feature activation-0.005
Top resid features:
also
Token also
Feature activation-0.044
Top resid features:
feature
Token feature
Feature activation-0.029
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
first
Token first
Feature activation+3.816
Top resid features:
Retro
Token Retro
Feature activation+0.062
Top resid features:
Fitness
Token Fitness
Feature activation+0.058
Top resid features:
gym
Token gym
Feature activation-0.040
Top resid features:
in
Token in
Feature activation+0.128
Top resid features:
Chicago
Token Chicago
Feature activation+0.000
Top resid features:
bankruptcy
Token bankruptcy
Feature activation-0.001
Top resid features:
but
Token but
Feature activation+0.036
Top resid features:
Detroit
Token Detroit
Feature activation-0.035
Top resid features:
is
Token is
Feature activation-0.020
Top resid features:
the
Token the
Feature activation-0.101
Top resid features:
first
Token first
Feature activation+4.003
Top resid features:
major
Token major
Feature activation-0.023
Top resid features:
U
Token U
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+0.016
Top resid features:
laws
Token laws
Feature activation-0.005
Top resid features:
would
Token would
Feature activation+0.010
Top resid features:
represent
Token represent
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
first
Token first
Feature activation+3.944
Top resid features:
roll
Token roll
Feature activation+0.014
Top resid features:
back
Tokenback
Feature activation-0.012
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
NSA
Token NSA
Feature activation-0.005
Top resid features:
also
Token also
Feature activation-0.008
Top resid features:
credited
Token credited
Feature activation-0.019
Top resid features:
as
Token as
Feature activation+0.042
Top resid features:
being
Token being
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.044
Top resid features:
first
Token first
Feature activation+3.787
Top resid features:
drive
Token drive
Feature activation+0.034
Top resid features:
-
Token-
Feature activation+0.025
Top resid features:
through
Tokenthrough
Feature activation+0.055
Top resid features:
restaurant
Token restaurant
Feature activation-0.057
Top resid features:
in
Token in
Feature activation+0.154
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.05

Head 3: 0.03

Head 4: 0.02

Head 5: 0.05

Head 6: 0.06

Head 7: 0.06

Head 8: 0.04

Head 9: 0.05

Head 10: 0.07

Head 11: 0.51

Positive logits

ever1.53

EVER1.50

imaginable1.37

Ever1.36

foray1.35

ogy1.34

ascent1.33

istani1.32

ocumented1.27

afia1.26

idas1.25

Nasa1.24

colonization1.23

conceivable1.23

encounter1.21

Possible1.20

ever1.17

glimpse1.17

introdu1.17

recogn1.16

Negative logits

contin-1.40

umbers-1.34

tics-1.32

hun-1.31

pmwiki-1.29

bos-1.26

��-1.24

ngth-1.22

uyomi-1.20

utton-1.20

-1.20

,,,,,,,,-1.19

bara-1.18

laughs-1.16

cms-1.16

vor-1.14

verages-1.14

laugh-1.14

quickShipAvailable-1.14

dece-1.13

INTERVAL 3.721 - 4.134
CONTAINS 0.001%

made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
prisoner
Token prisoner
Feature activation+3.591
transfer
Token transfer
Feature activation+3.780
on
Token on
Feature activation+2.446
Tuesday
Token Tuesday
Feature activation+0.459
,
Token,
Feature activation+0.500
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.009
ever
Token ever
Feature activation+2.022
BMW
Token BMW
Feature activation+2.507
i
Token i
Feature activation+3.816
3
Token3
Feature activation+2.215
s
Tokens
Feature activation+2.916
features
Token features
Feature activation+1.848
an
Token an
Feature activation+0.407
output
Token output
Feature activation+0.000
offer
Token offer
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.202
commercial
Token commercial
Feature activation+2.651
Vive
Token Vive
Feature activation+2.408
units
Token units
Feature activation+3.761
via
Token via
Feature activation+1.610
a
Token a
Feature activation+0.799
limited
Token limited
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.421
oil
Token oil
Feature activation+0.000
and
Token and
Feature activation+0.000
gas
Token gas
Feature activation+0.000
producer
Token producer
Feature activation+0.000
since
Token since
Feature activation+4.090
prices
Token prices
Feature activation+0.000
started
Token started
Feature activation+0.000
falling
Token falling
Feature activation+0.000
last
Token last
Feature activation+0.000
summer
Token summer
Feature activation+0.000
first
Token first
Feature activation+0.000
African
Token African
Feature activation+2.265
-
Token-
Feature activation+1.304
American
TokenAmerican
Feature activation+2.289
Republican
Token Republican
Feature activation+2.766
to
Token to
Feature activation+3.953
serve
Token serve
Feature activation+0.679
in
Token in
Feature activation+0.619
the
Token the
Feature activation+0.525
Oregon
Token Oregon
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000

INTERVAL 3.307 - 3.721
CONTAINS 0.003%

first
Token first
Feature activation+0.113
person
Token person
Feature activation+1.570
in
Token in
Feature activation+2.716
the
Token the
Feature activation+2.887
world
Token world
Feature activation+1.084
to
Token to
Feature activation+3.617
be
Token be
Feature activation+3.508
legally
Token legally
Feature activation+0.681
executed
Token executed
Feature activation+0.000
using
Token using
Feature activation+0.220
an
Token an
Feature activation+0.000
sal
Token sal
Feature activation+0.858
oon
Tokenoon
Feature activation+2.496
in
Token in
Feature activation+2.924
the
Token the
Feature activation+2.862
city
Token city
Feature activation+0.420
to
Token to
Feature activation+3.424
employ
Token employ
Feature activation+2.112
an
Token an
Feature activation+0.000
armed
Token armed
Feature activation+0.000
boun
Token boun
Feature activation+0.000
cer
Tokencer
Feature activation+0.000
U
Token U
Feature activation+0.391
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
city
Token city
Feature activation+0.657
to
Token to
Feature activation+3.449
file
Token file
Feature activation+1.340
for
Token for
Feature activation+0.182
bankruptcy
Token bankruptcy
Feature activation+0.000
,
Token,
Feature activation+1.108
pressured
Token pressured
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.274
service
Token service
Feature activation+2.186
user
Token user
Feature activation+2.823
involvement
Token involvement
Feature activation+3.524
movement
Token movement
Feature activation+2.223
.
Token.
Feature activation+0.810
Founder
Token Founder
Feature activation+0.000
member
Token member
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Retro
Token Retro
Feature activation+0.000
Fitness
Token Fitness
Feature activation+0.000
gym
Token gym
Feature activation+2.821
in
Token in
Feature activation+3.469
Chicago
Token Chicago
Feature activation+0.230
,
Token,
Feature activation+1.177
C
Token C
Feature activation+0.000
ui
Tokenui
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 2.894 - 3.307
CONTAINS 0.007%

and
Token and
Feature activation+1.330
US
Token US
Feature activation+0.000
presidential
Token presidential
Feature activation+0.058
cabinet
Token cabinet
Feature activation+0.000
member
Token member
Feature activation+1.130
to
Token to
Feature activation+3.290
be
Token be
Feature activation+3.022
held
Token held
Feature activation+0.498
in
Token in
Feature activation+0.534
contempt
Token contempt
Feature activation+0.000
.
Token.
Feature activation+0.245
set
Token set
Feature activation+0.073
of
Token of
Feature activation+2.062
skysc
Token skysc
Feature activation+0.564
rap
Tokenrap
Feature activation+0.000
ers
Tokeners
Feature activation+1.059
to
Token to
Feature activation+3.208
be
Token be
Feature activation+3.326
built
Token built
Feature activation+2.168
with
Token with
Feature activation+0.285
integrated
Token integrated
Feature activation+0.000
wind
Token wind
Feature activation+0.000
then
Token then
Feature activation+0.000
came
Token came
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.173
factory
Token factory
Feature activation+2.012
occupations
Token occupations
Feature activation+3.101
against
Token against
Feature activation+1.528
closures
Token closures
Feature activation+0.000
and
Token and
Feature activation+0.000
layoffs
Token layoffs
Feature activation+0.000
.
Token.
Feature activation+0.226
-
Token-
Feature activation+0.085
ever
Tokenever
Feature activation+2.165
marketplace
Token marketplace
Feature activation+1.112
in
Token in
Feature activation+2.177
Malaysia
Token Malaysia
Feature activation+0.000
to
Token to
Feature activation+3.090
have
Token have
Feature activation+2.103
integrated
Token integrated
Feature activation+0.290
a
Token a
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
wallet
Token wallet
Feature activation+0.000
at
Token at
Feature activation+0.000
York
Token York
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.340
female
Token female
Feature activation+3.070
commander
Token commander
Feature activation+0.000
of
Token of
Feature activation+1.353
Rock
Token Rock
Feature activation+0.000
Hill
Token Hill
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.322

INTERVAL 2.480 - 2.894
CONTAINS 0.011%

team
Token team
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.345
competitive
Token competitive
Feature activation+2.114
game
Token game
Feature activation+2.772
in
Token in
Feature activation+2.618
charge
Token charge
Feature activation+0.306
shows
Token shows
Feature activation+0.000
seven
Token seven
Feature activation+0.000
personnel
Token personnel
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
of
Token of
Feature activation+1.657
my
Token my
Feature activation+2.857
11
Token 11
Feature activation+0.498
assignments
Token assignments
Feature activation+0.775
in
Token in
Feature activation+1.247
that
Token that
Feature activation+1.165
country
Token country
Feature activation+0.000
it
Token it
Feature activation+0.000
got
Token got
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.570
commercial
Token commercial
Feature activation+2.752
run
Token run
Feature activation+2.890
in
Token in
Feature activation+1.380
April
Token April
Feature activation+0.000
of
Token of
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.170
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
internationally
Token internationally
Feature activation+2.004
published
Token published
Feature activation+2.237
games
Token games
Feature activation+2.533
to
Token to
Feature activation+2.822
come
Token come
Feature activation+2.157
out
Token out
Feature activation+0.309
of
Token of
Feature activation+0.382
Finland
Token Finland
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.961
official
Token official
Feature activation+2.293
website
Token website
Feature activation+0.937
to
Token to
Feature activation+2.602
be
Token be
Feature activation+2.934
registered
Token registered
Feature activation+1.594
in
Token in
Feature activation+1.373
the
Token the
Feature activation+1.223
Armenian
Token Armenian
Feature activation+0.000

INTERVAL 2.067 - 2.480
CONTAINS 0.019%

The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
three
Token three
Feature activation+0.000
playoff
Token playoff
Feature activation+0.000
runs
Token runs
Feature activation+0.224
saw
Token saw
Feature activation+2.161
Pl
Token Pl
Feature activation+0.000
ante
Tokenante
Feature activation+0.000
lose
Token lose
Feature activation+0.000
just
Token just
Feature activation+0.000
two
Token two
Feature activation+0.000
squ
Token squ
Feature activation+0.000
ander
Tokenander
Feature activation+0.000
our
Token our
Feature activation+0.000
first
Token first
Feature activation+0.000
viewing
Token viewing
Feature activation+1.156
of
Token of
Feature activation+2.366
by
Tokenby
Feature activation+0.011
leaping
Token leaping
Feature activation+0.000
head
Token head
Feature activation+0.000
long
Tokenlong
Feature activation+0.000
into
Token into
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
issued
Token issued
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.751
-
Token-
Feature activation+0.253
ever
Tokenever
Feature activation+2.289
red
Token red
Feature activation+1.307
alert
Token alert
Feature activation+0.678
on
Token on
Feature activation+1.083
December
Token December
Feature activation+0.000
7
Token 7
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.466
I
Token I
Feature activation+2.454
opened
Token opened
Feature activation+0.970
I
Token I
Feature activation+2.321
was
Token was
Feature activation+2.299
pretty
Token pretty
Feature activation+0.000
sure
Token sure
Feature activation+0.000
I
Token I
Feature activation+0.161
recognized
Token recognized
Feature activation+0.000
the
Token the
Feature activation+0.000
accidental
Token accidental
Feature activation+0.000
star
Token star
Feature activation+0.000
gave
Token gave
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.372
true
Token true
Feature activation+2.086
interview
Token interview
Feature activation+1.556
.
Token.
Feature activation+0.124
V
Token V
Feature activation+0.000
ulture
Tokenulture
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000

INTERVAL 1.654 - 2.067
CONTAINS 0.027%

last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
official
Token official
Feature activation+1.874
meet
Token meet
Feature activation+2.013
up
Tokenup
Feature activation+1.098
for
Token for
Feature activation+0.878
the
Token the
Feature activation+0.689
notorious
Token notorious
Feature activation+0.051
cruising
Token cruising
Feature activation+0.000
through
Token through
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.000
round
Token round
Feature activation+0.000
of
Token of
Feature activation+1.936
2018
Token 2018
Feature activation+0.000
World
Token World
Feature activation+0.000
Cup
Token Cup
Feature activation+0.854
Qual
Token Qual
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
point
Token point
Feature activation+0.146
about
Token about
Feature activation+1.710
the
Token the
Feature activation+0.723
terror
Token terror
Feature activation+0.000
laws
Token laws
Feature activation+0.427
:
Token:
Feature activation+0.343
They
Token They
Feature activation+0.000
electing
Token electing
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.085
gay
Token gay
Feature activation+2.204
bishop
Token bishop
Feature activation+1.897
,
Token,
Feature activation+1.915
the
Token the
Feature activation+0.497
Episcopal
Token Episcopal
Feature activation+0.000
Church
Token Church
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
first
Token first
Feature activation+0.000
complex
Token complex
Feature activation+1.140
organisms
Token organisms
Feature activation+3.127
that
Token that
Feature activation+1.656
ever
Token ever
Feature activation+1.696
inhabited
Token inhabited
Feature activation+1.770
the
Token the
Feature activation+0.293
oceans
Token oceans
Feature activation+0.122
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.240 - 1.654
CONTAINS 0.039%

that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+1.305
that
Token that
Feature activation+0.329
he
Token he
Feature activation+1.033
had
Token had
Feature activation+0.605
ever
Token ever
Feature activation+2.470
used
Token used
Feature activation+0.168
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.123
ever
Tokenever
Feature activation+1.559
visually
Token visually
Feature activation+1.039
impaired
Token impaired
Feature activation+1.389
person
Token person
Feature activation+2.000
to
Token to
Feature activation+3.406
head
Token head
Feature activation+0.193
the
Token the
Feature activation+0.179
Senate
Token Senate
Feature activation+0.000
of
Token of
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.439
to
Token to
Feature activation+1.620
take
Token take
Feature activation+1.165
to
Token to
Feature activation+2.283
the
Token the
Feature activation+0.992
streets
Token streets
Feature activation+0.036
on
Token on
Feature activation+0.151
Rats
Token Rats
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Canadian
Token Canadian
Feature activation+1.384
to
Token to
Feature activation+2.171
be
Token be
Feature activation+2.733
taken
Token taken
Feature activation+0.854
in
Token in
Feature activation+1.462
the
Token the
Feature activation+1.084
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.147
depressive
Token depressive
Feature activation+1.226
episode
Token episode
Feature activation+2.245
in
Token in
Feature activation+1.670
their
Token their
Feature activation+1.407
life
Token life
Feature activation+0.617
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
METHOD
TokenMETHOD
Feature activation+0.000

INTERVAL 0.827 - 1.240
CONTAINS 0.053%

meet
Token meet
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.867
I
Token I
Feature activation+2.204
came
Token came
Feature activation+1.731
over
Token over
Feature activation+0.694
he
Token he
Feature activation+1.830
actually
Token actually
Feature activation+0.000
Mak
Token Mak
Feature activation+0.000
abe
Tokenabe
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
title
Token title
Feature activation+0.855
shot
Token shot
Feature activation+1.879
of
Token of
Feature activation+2.156
his
Token his
Feature activation+0.876
career
Token career
Feature activation+0.000
on
Token on
Feature activation+0.384
those
Token those
Feature activation+1.495
un
Token un
Feature activation+0.196
gr
Tokengr
Feature activation+0.000
ateful
Tokenateful
Feature activation+0.000
Spurs
Token Spurs
Feature activation+0.007
fans
Token fans
Feature activation+0.942
he
Token he
Feature activation+2.445
âĢ
TokenâĢ
Feature activation+0.286
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
told
Token told
Feature activation+0.000
a
Token a
Feature activation+1.803
family
Token family
Feature activation+0.000
of
Token of
Feature activation+0.224
precursor
Token precursor
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
for
Token for
Feature activation+1.018
preparing
Token preparing
Feature activation+0.000
semic
Token semic
Feature activation+0.000
onduct
Tokenonduct
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.383
2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
year
Token year
Feature activation+1.237
of
Token of
Feature activation+1.630
its
Token its
Feature activation+1.404
existence
Token existence
Feature activation+1.531
,
Token,
Feature activation+0.609
more
Token more
Feature activation+0.000

INTERVAL 0.413 - 0.827
CONTAINS 0.077%

Mark
Token Mark
Feature activation+0.000
Travis
Token Travis
Feature activation+0.000
purchased
Token purchased
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+0.816
certificate
Token certificate
Feature activation+2.679
from
Token from
Feature activation+1.908
the
Token the
Feature activation+2.014
Spart
Token Spart
Feature activation+0.000
a
Tokena
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
major
Token major
Feature activation+1.835
female
Token female
Feature activation+1.680
video
Token video
Feature activation+0.498
game
Token game
Feature activation+0.516
protagonist
Token protagonist
Feature activation+0.488
.
Token.
Feature activation+0.549
She
Token She
Feature activation+0.040
remains
Token remains
Feature activation+0.000
one
Token one
Feature activation+0.000
patents
Token patents
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.550
2017
Token 2017
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
160
Token 160
Feature activation+0.000
,
Token,
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+0.565
panels
Token panels
Feature activation+0.000
on
Token on
Feature activation+0.454
the
Token the
Feature activation+0.436
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
roof
Token roof
Feature activation+0.000
in
Token in
Feature activation+0.000
1979
Token 1979
Feature activation+0.000
be
Token be
Feature activation+0.000
provided
Token provided
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.026
day
Token day
Feature activation+0.554
of
Token of
Feature activation+1.644
pull
Token pull
Feature activation+0.530
out
Tokenout
Feature activation+1.127
,
Token,
Feature activation+1.821
using
Token using
Feature activation+0.000

INTERVAL 0.000 - 0.413
CONTAINS 99.764%

Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
By
Token By
Feature activation+0.000
The
Token The
Feature activation+0.000
Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
V
TokenV
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
ICAN
TokenICAN
Feature activation+0.000
digital
Token digital
Feature activation+0.000
copy
Token copy
Feature activation+0.000
of
Token of
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
down
Tokendown
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
every
Token every
Feature activation+0.000
detail
Token detail
Feature activation+0.000
before
Token before
Feature activation+0.000
posting
Token posting
Feature activation+0.000
their
Token their
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
predictions
Token predictions
Feature activation+0.000
.
Token.
Feature activation+0.000
which
Token which
Feature activation+0.000
launched
Token launched
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Switch
Token Switch
Feature activation+0.000
several
Token several
Feature activation+0.000
days
Token days
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CA
Token CA
Feature activation+0.000
,
Token,
Feature activation+0.000
USA
Token USA
Feature activation+0.000
;
Token;
Feature activation+0.000
USC
Token USC
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000
Noah
Token Noah
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H3.11: (feature 22804)

TOP ACTIVATIONS
MAX = 4.088

would
Token would
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.315
email
Token email
Feature activation+1.971
channel
Token channel
Feature activation+4.088
useless
Token useless
Feature activation+0.206
.
Token.
Feature activation+0.188
Email
Token Email
Feature activation+0.000
sp
Token sp
Feature activation+0.000
ams
Tokenams
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
kept
Token kept
Feature activation+0.000
her
Token her
Feature activation+0.000
entire
Token entire
Feature activation+1.166
Elaine
Token Elaine
Feature activation+0.914
wardrobe
Token wardrobe
Feature activation+3.662
from
Token from
Feature activation+3.655
Se
Token Se
Feature activation+0.000
infeld
Tokeninfeld
Feature activation+0.000
;
Token;
Feature activation+1.499
Jason
Token Jason
Feature activation+0.000
kept
Token kept
Feature activation+0.000
her
Token her
Feature activation+0.000
entire
Token entire
Feature activation+1.166
Elaine
Token Elaine
Feature activation+0.914
wardrobe
Token wardrobe
Feature activation+3.662
from
Token from
Feature activation+3.655
Se
Token Se
Feature activation+0.000
infeld
Tokeninfeld
Feature activation+0.000
;
Token;
Feature activation+1.499
Jason
Token Jason
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.046
military
Token military
Feature activation+2.821
force
Token force
Feature activation+3.642
of
Token of
Feature activation+1.926
the
Token the
Feature activation+1.962
Syndicate
Token Syndicate
Feature activation+0.000
Worlds
Token Worlds
Feature activation+0.000
continues
Token continues
Feature activation+0.607
about
Token about
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.714
Democratic
Token Democratic
Feature activation+1.663
Party
Token Party
Feature activation+3.632
,
Token,
Feature activation+3.131
the
Token the
Feature activation+2.165
GOP
Token GOP
Feature activation+0.587
Never
Token Never
Feature activation+1.051
Tr
TokenTr
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
whole
Token whole
Feature activation+0.258
arrangement
Token arrangement
Feature activation+2.183
is
Token is
Feature activation+3.583
unique
Token unique
Feature activation+0.021
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.047
publisher
Token publisher
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
had
Token had
Feature activation+0.000
asked
Token asked
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.056
class
Token class
Feature activation+3.540
to
Token to
Feature activation+1.005
write
Token write
Feature activation+0.000
an
Token an
Feature activation+0.623
essay
Token essay
Feature activation+0.287
about
Token about
Feature activation+0.000
situation
Token situation
Feature activation+0.000
throws
Token throws
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.608
incentive
Token incentive
Feature activation+2.482
system
Token system
Feature activation+3.534
on
Token on
Feature activation+1.406
its
Token its
Feature activation+0.000
head
Token head
Feature activation+0.000
Columbia
Token Columbia
Feature activation+0.000
Law
Token Law
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
whole
Token whole
Feature activation+0.494
system
Token system
Feature activation+3.189
was
Token was
Feature activation+3.503
broken
Token broken
Feature activation+1.456
.
Token.
Feature activation+0.148
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Australian
Token Australian
Feature activation+1.113
community
Token community
Feature activation+3.489
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Christ
TokenChrist
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.743
primary
Token primary
Feature activation+2.392
process
Token process
Feature activation+3.488
âĢĵ
Token âĢĵ
Feature activation+3.073
from
Token from
Feature activation+3.217
the
Token the
Feature activation+1.024
super
Token super
Feature activation+0.000
delegates
Token delegates
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.776
city
Token city
Feature activation+3.479
was
Token was
Feature activation+3.365
empty
Token empty
Feature activation+0.702
.
Token.
Feature activation+0.312
The
Token The
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.265
felt
Token felt
Feature activation+0.000
"
Token "
Feature activation+0.000
that
Tokenthat
Feature activation+0.000
their
Token their
Feature activation+0.000
whole
Token whole
Feature activation+0.536
city
Token city
Feature activation+3.442
has
Token has
Feature activation+2.382
been
Token been
Feature activation+3.199
put
Token put
Feature activation+2.548
under
Token under
Feature activation+0.483
curfew
Token curfew
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.776
city
Token city
Feature activation+3.479
was
Token was
Feature activation+3.365
empty
Token empty
Feature activation+0.702
.
Token.
Feature activation+0.312
The
Token The
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.265
gym
Token gym
Feature activation+1.018
gave
Token gave
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.010
country
Token country
Feature activation+3.128
the
Token the
Feature activation+2.102
day
Token day
Feature activation+3.360
off
Token off
Feature activation+0.000
.
Token.
Feature activation+0.337
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
1861
Token 1861
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.563
country
Token country
Feature activation+3.331
don
Token don
Feature activation+2.116
ned
Tokenned
Feature activation+0.000
their
Token their
Feature activation+0.149
mourning
Token mourning
Feature activation+0.511
attire
Token attire
Feature activation+0.989
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
entire
Token entire
Feature activation+0.542
region
Token region
Feature activation+3.322
has
Token has
Feature activation+2.391
promise
Token promise
Feature activation+0.749
.
Token.
Feature activation+0.108
But
Token But
Feature activation+0.000
capturing
Token capturing
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Color
Token Color
Feature activation+0.836
Rush
Token Rush
Feature activation+0.485
idea
Token idea
Feature activation+3.302
for
Token for
Feature activation+1.608
the
Token the
Feature activation+0.688
whole
Token whole
Feature activation+0.000
NFL
Token NFL
Feature activation+0.063
."
Token."
Feature activation+0.000
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.768
country
Token country
Feature activation+3.257
would
Token would
Feature activation+0.412
be
Token be
Feature activation+1.818
able
Token able
Feature activation+0.368
to
Token to
Feature activation+0.259
participate
Token participate
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Ragnarok
Token Ragnarok
Feature activation+1.223
thing
Token thing
Feature activation+2.788
in
Token in
Feature activation+2.929
Asgard
Token Asgard
Feature activation+0.000
is
Token is
Feature activation+3.225
all
Token all
Feature activation+0.000
kinds
Token kinds
Feature activation+0.000
nuts
Token nuts
Feature activation+0.000
.
Token.
Feature activation+0.000
Odin
Token Odin
Feature activation+0.000

Top DFA by src position
MAX = 5.055

.
Token.
Feature activation-0.028
Top resid features:
This
Token This
Feature activation-0.048
Top resid features:
would
Token would
Feature activation-0.020
Top resid features:
make
Token make
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.226
Top resid features:
whole
Token whole
Feature activation+4.928
Top resid features:
email
Token email
Feature activation+0.265
Top resid features:
channel
Token channel
Feature activation+0.021
Top resid features:
useless
Token useless
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Email
Token Email
Feature activation+0.000
Top resid features:
rey
Tokenrey
Feature activation-0.002
Top resid features:
f
Tokenf
Feature activation+0.001
Top resid features:
uss
Tokenuss
Feature activation+0.000
Top resid features:
kept
Token kept
Feature activation+0.037
Top resid features:
her
Token her
Feature activation-0.048
Top resid features:
entire
Token entire
Feature activation+4.596
Top resid features:
Elaine
Token Elaine
Feature activation+0.053
Top resid features:
wardrobe
Token wardrobe
Feature activation+0.023
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Se
Token Se
Feature activation+0.000
Top resid features:
infeld
Tokeninfeld
Feature activation+0.000
Top resid features:
rey
Tokenrey
Feature activation+0.001
Top resid features:
f
Tokenf
Feature activation+0.001
Top resid features:
uss
Tokenuss
Feature activation+0.000
Top resid features:
kept
Token kept
Feature activation+0.059
Top resid features:
her
Token her
Feature activation+0.008
Top resid features:
entire
Token entire
Feature activation+4.569
Top resid features:
Elaine
Token Elaine
Feature activation-0.004
Top resid features:
wardrobe
Token wardrobe
Feature activation+0.097
Top resid features:
from
Token from
Feature activation-0.018
Top resid features:
Se
Token Se
Feature activation+0.000
Top resid features:
infeld
Tokeninfeld
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.028
Top resid features:
As
TokenAs
Feature activation-0.045
Top resid features:
the
Token the
Feature activation-0.382
Top resid features:
entire
Token entire
Feature activation+4.503
Top resid features:
military
Token military
Feature activation+0.437
Top resid features:
force
Token force
Feature activation+0.154
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Syndicate
Token Syndicate
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.016
Top resid features:
think
Token think
Feature activation+0.012
Top resid features:
about
Token about
Feature activation+0.011
Top resid features:
:
Token:
Feature activation-0.055
Top resid features:
the
Token the
Feature activation-0.216
Top resid features:
whole
Token whole
Feature activation+4.408
Top resid features:
Democratic
Token Democratic
Feature activation+0.251
Top resid features:
Party
Token Party
Feature activation+0.208
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
GOP
Token GOP
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.002
Top resid features:
altru
Token altru
Feature activation-0.000
Top resid features:
ist
Tokenist
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
The
Token The
Feature activation-0.385
Top resid features:
whole
Token whole
Feature activation+4.738
Top resid features:
arrangement
Token arrangement
Feature activation+0.200
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
unique
Token unique
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
her
Token her
Feature activation-0.020
Top resid features:
teacher
Token teacher
Feature activation-0.008
Top resid features:
had
Token had
Feature activation+0.013
Top resid features:
asked
Token asked
Feature activation-0.264
Top resid features:
the
Token the
Feature activation-0.428
Top resid features:
whole
Token whole
Feature activation+5.055
Top resid features:
class
Token class
Feature activation+0.177
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
write
Token write
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
essay
Token essay
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.033
Top resid features:
Manafort
Token Manafort
Feature activation-0.010
Top resid features:
situation
Token situation
Feature activation-0.007
Top resid features:
throws
Token throws
Feature activation+0.033
Top resid features:
the
Token the
Feature activation-0.261
Top resid features:
whole
Token whole
Feature activation+4.399
Top resid features:
incentive
Token incentive
Feature activation+0.333
Top resid features:
system
Token system
Feature activation-0.030
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
head
Token head
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.031
Top resid features:
t
Tokent
Feature activation+0.010
Top resid features:
work
Token work
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
The
Token The
Feature activation-0.269
Top resid features:
whole
Token whole
Feature activation+4.258
Top resid features:
system
Token system
Feature activation+0.321
Top resid features:
was
Token was
Feature activation+0.064
Top resid features:
broken
Token broken
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
than
Token than
Feature activation-0.004
Top resid features:
it
Token it
Feature activation-0.032
Top resid features:
is
Token is
Feature activation-0.046
Top resid features:
to
Token to
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.253
Top resid features:
whole
Token whole
Feature activation+4.740
Top resid features:
Australian
Token Australian
Feature activation+0.022
Top resid features:
community
Token community
Feature activation+0.063
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.017
Top resid features:
1970
Token 1970
Feature activation-0.023
Top resid features:
s
Tokens
Feature activation-0.017
Top resid features:
,
Token,
Feature activation-0.071
Top resid features:
the
Token the
Feature activation-0.235
Top resid features:
entire
Token entire
Feature activation+4.657
Top resid features:
primary
Token primary
Feature activation+0.171
Top resid features:
process
Token process
Feature activation-0.003
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
In
Token In
Feature activation-0.019
Top resid features:
fact
Token fact
Feature activation-0.073
Top resid features:
,
Token,
Feature activation-0.048
Top resid features:
the
Token the
Feature activation-0.291
Top resid features:
whole
Token whole
Feature activation+4.543
Top resid features:
city
Token city
Feature activation+0.340
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
empty
Token empty
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
residents
Token residents
Feature activation-0.021
Top resid features:
felt
Token felt
Feature activation+0.038
Top resid features:
"
Token "
Feature activation-0.021
Top resid features:
that
Tokenthat
Feature activation-0.067
Top resid features:
their
Token their
Feature activation-0.173
Top resid features:
whole
Token whole
Feature activation+4.353
Top resid features:
city
Token city
Feature activation+0.206
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
In
Token In
Feature activation-0.001
Top resid features:
fact
Token fact
Feature activation+0.038
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
the
Token the
Feature activation-0.290
Top resid features:
whole
Token whole
Feature activation+4.158
Top resid features:
city
Token city
Feature activation+0.286
Top resid features:
was
Token was
Feature activation+0.079
Top resid features:
empty
Token empty
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
when
Token when
Feature activation-0.022
Top resid features:
he
Token he
Feature activation-0.015
Top resid features:
essentially
Token essentially
Feature activation+0.008
Top resid features:
gave
Token gave
Feature activation+0.038
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
whole
Token whole
Feature activation+4.443
Top resid features:
country
Token country
Feature activation+0.158
Top resid features:
the
Token the
Feature activation-0.411
Top resid features:
day
Token day
Feature activation+0.139
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
1861
Token 1861
Feature activation-0.086
Top resid features:
,
Token,
Feature activation-0.095
Top resid features:
the
Token the
Feature activation-0.173
Top resid features:
entire
Token entire
Feature activation+4.400
Top resid features:
country
Token country
Feature activation+0.249
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
ned
Tokenned
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
mourning
Token mourning
Feature activation+0.000
Top resid features:
grow
Token grow
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation-0.081
Top resid features:
The
TokenThe
Feature activation-0.360
Top resid features:
entire
Token entire
Feature activation+4.390
Top resid features:
region
Token region
Feature activation+0.227
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
promise
Token promise
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
kind
Token kind
Feature activation-0.015
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
talk
Token talk
Feature activation+0.019
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.168
Top resid features:
whole
Token whole
Feature activation+4.337
Top resid features:
Color
Token Color
Feature activation+0.141
Top resid features:
Rush
Token Rush
Feature activation+0.051
Top resid features:
idea
Token idea
Feature activation-0.121
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
encounter
Token encounter
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Also
Token Also
Feature activation-0.104
Top resid features:
,
Token,
Feature activation-0.087
Top resid features:
the
Token the
Feature activation-0.303
Top resid features:
whole
Token whole
Feature activation+4.379
Top resid features:
country
Token country
Feature activation+0.323
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
but
Token but
Feature activation-0.009
Top resid features:
not
Token not
Feature activation+0.026
Top resid features:
;
Token;
Feature activation-0.051
Top resid features:
the
Token the
Feature activation-0.038
Top resid features:
whole
Token whole
Feature activation+4.320
Top resid features:
Ragnarok
Token Ragnarok
Feature activation+0.049
Top resid features:
thing
Token thing
Feature activation+0.104
Top resid features:
in
Token in
Feature activation-0.116
Top resid features:
Asgard
Token Asgard
Feature activation-0.129
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.06

Head 3: 0.03

Head 4: 0.02

Head 5: 0.05

Head 6: 0.08

Head 7: 0.06

Head 8: 0.04

Head 9: 0.06

Head 10: 0.05

Head 11: 0.51

Positive logits

��1.53

yss1.51

except1.48

ossier1.46

except1.44

ruciating1.39

shenan1.39

roy1.31

reciation1.31

ワン1.27

Tes1.27

Including1.25

cram1.24

including1.24

mathemat1.18

revolves1.16

endeavour1.16

atche1.13

catalogue1.12

sites1.12

Negative logits

leaning-1.19

mM-1.19

occasional-1.15

neighbor-1.13

odan-1.12

asma-1.11

ally-1.09

imminent-1.06

assisted-1.05

intendent-1.04

colleague-1.04

partner-1.04

ensis-1.02

Partner-1.02

neutral-1.02

placed-1.01

cially-1.01

Samar-0.99

premature-0.99

forthcoming-0.99

INTERVAL 3.679 - 4.088
CONTAINS 0.000%

would
Token would
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.315
email
Token email
Feature activation+1.971
channel
Token channel
Feature activation+4.088
useless
Token useless
Feature activation+0.206
.
Token.
Feature activation+0.188
Email
Token Email
Feature activation+0.000
sp
Token sp
Feature activation+0.000
ams
Tokenams
Feature activation+0.000

INTERVAL 3.270 - 3.679
CONTAINS 0.002%

situation
Token situation
Feature activation+0.000
throws
Token throws
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.608
incentive
Token incentive
Feature activation+2.482
system
Token system
Feature activation+3.534
on
Token on
Feature activation+1.406
its
Token its
Feature activation+0.000
head
Token head
Feature activation+0.000
Columbia
Token Columbia
Feature activation+0.000
Law
Token Law
Feature activation+0.000
felt
Token felt
Feature activation+0.000
"
Token "
Feature activation+0.000
that
Tokenthat
Feature activation+0.000
their
Token their
Feature activation+0.000
whole
Token whole
Feature activation+0.536
city
Token city
Feature activation+3.442
has
Token has
Feature activation+2.382
been
Token been
Feature activation+3.199
put
Token put
Feature activation+2.548
under
Token under
Feature activation+0.483
curfew
Token curfew
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Color
Token Color
Feature activation+0.836
Rush
Token Rush
Feature activation+0.485
idea
Token idea
Feature activation+3.302
for
Token for
Feature activation+1.608
the
Token the
Feature activation+0.688
whole
Token whole
Feature activation+0.000
NFL
Token NFL
Feature activation+0.063
."
Token."
Feature activation+0.000
about
Token about
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.714
Democratic
Token Democratic
Feature activation+1.663
Party
Token Party
Feature activation+3.632
,
Token,
Feature activation+3.131
the
Token the
Feature activation+2.165
GOP
Token GOP
Feature activation+0.587
Never
Token Never
Feature activation+1.051
Tr
TokenTr
Feature activation+0.000
kept
Token kept
Feature activation+0.000
her
Token her
Feature activation+0.000
entire
Token entire
Feature activation+1.166
Elaine
Token Elaine
Feature activation+0.914
wardrobe
Token wardrobe
Feature activation+3.662
from
Token from
Feature activation+3.655
Se
Token Se
Feature activation+0.000
infeld
Tokeninfeld
Feature activation+0.000
;
Token;
Feature activation+1.499
Jason
Token Jason
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000

INTERVAL 2.861 - 3.270
CONTAINS 0.004%

and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.825
episode
Token episode
Feature activation+1.950
was
Token was
Feature activation+3.106
Trump
Token Trump
Feature activation+0.350
's
Token's
Feature activation+0.560
sense
Token sense
Feature activation+1.321
of
Token of
Feature activation+0.000
humor
Token humor
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
their
Token their
Feature activation+0.000
whole
Token whole
Feature activation+0.473
case
Token case
Feature activation+3.028
forward
Token forward
Feature activation+0.830
in
Token in
Feature activation+0.461
one
Token one
Feature activation+1.202
hour
Token hour
Feature activation+0.000
?
Token?
Feature activation+0.000
this
Token this
Feature activation+0.000
whole
Token whole
Feature activation+0.673
Dakota
Token Dakota
Feature activation+0.354
Access
Token Access
Feature activation+0.000
Pipeline
Token Pipeline
Feature activation+0.000
thing
Token thing
Feature activation+2.890
âĢĶ
TokenâĢĶ
Feature activation+1.141
no
Tokenno
Feature activation+0.000
more
Token more
Feature activation+0.000
delays
Token delays
Feature activation+0.000
due
Token due
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.714
Democratic
Token Democratic
Feature activation+1.663
Party
Token Party
Feature activation+3.632
,
Token,
Feature activation+3.131
the
Token the
Feature activation+2.165
GOP
Token GOP
Feature activation+0.587
Never
Token Never
Feature activation+1.051
Tr
TokenTr
Feature activation+0.000
umps
Tokenumps
Feature activation+0.000
included
Token included
Feature activation+0.000
,
Token,
Feature activation+0.000
skewed
Token skewed
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
set
Token set
Feature activation+2.904
.
Token.
Feature activation+0.455
Perhaps
Token Perhaps
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
some
Token some
Feature activation+0.000

INTERVAL 2.453 - 2.861
CONTAINS 0.006%

and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.747
dog
Token dog
Feature activation+2.337
meat
Token meat
Feature activation+1.619
trade
Token trade
Feature activation+2.500
so
Token so
Feature activation+0.450
grotesque
Token grotesque
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
not
Token not
Feature activation+0.000
;
Token;
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Ragnarok
Token Ragnarok
Feature activation+1.223
thing
Token thing
Feature activation+2.788
in
Token in
Feature activation+2.929
Asgard
Token Asgard
Feature activation+0.000
is
Token is
Feature activation+3.225
all
Token all
Feature activation+0.000
kinds
Token kinds
Feature activation+0.000
Manafort
Token Manafort
Feature activation+0.000
situation
Token situation
Feature activation+0.000
throws
Token throws
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.608
incentive
Token incentive
Feature activation+2.482
system
Token system
Feature activation+3.534
on
Token on
Feature activation+1.406
its
Token its
Feature activation+0.000
head
Token head
Feature activation+0.000
Columbia
Token Columbia
Feature activation+0.000
pins
Tokenpins
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.421
Obamacare
Token Obamacare
Feature activation+0.427
system
Token system
Feature activation+3.199
âĢĵ
Token âĢĵ
Feature activation+2.768
making
Token making
Feature activation+0.242
another
Token another
Feature activation+0.000
measure
Token measure
Feature activation+0.000
,
Token,
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
U
Token U
Feature activation+1.745
.
Token.
Feature activation+0.158
S
TokenS
Feature activation+0.862
.
Token.
Feature activation+1.133
healthcare
Token healthcare
Feature activation+0.635
system
Token system
Feature activation+2.808
has
Token has
Feature activation+0.855
generated
Token generated
Feature activation+0.619
an
Token an
Feature activation+0.159
enormous
Token enormous
Feature activation+0.000
amount
Token amount
Feature activation+0.000

INTERVAL 2.044 - 2.453
CONTAINS 0.006%

get
Token get
Feature activation+0.000
cynical
Token cynical
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
process
Token process
Feature activation+2.329
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.579
world
Token world
Feature activation+2.082
,
Token,
Feature activation+2.170
and
Token and
Feature activation+0.335
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
site
Token site
Feature activation+0.000
or
Token or
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
internet
Token internet
Feature activation+2.127
.
Token.
Feature activation+0.347
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
building
Token building
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.260
thing
Token thing
Feature activation+2.370
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.334
escalated
Token escalated
Feature activation+0.000
into
Token into
Feature activation+0.000
sectarian
Token sectarian
Feature activation+0.000
map
Tokenmap
Feature activation+0.000
utra
Tokenutra
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
entire
Token entire
Feature activation+0.341
stretch
Token stretch
Feature activation+2.402
in
Token in
Feature activation+1.983
the
Token the
Feature activation+1.215
State
Token State
Feature activation+0.510
from
Token from
Feature activation+1.578
S
Token S
Feature activation+0.000

INTERVAL 1.635 - 2.044
CONTAINS 0.008%

to
Token to
Feature activation+0.000
surrender
Token surrender
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.831
area
Token area
Feature activation+2.834
including
Token including
Feature activation+1.750
Haj
Token Haj
Feature activation+0.000
in
Tokenin
Feature activation+0.000
village
Token village
Feature activation+0.300
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.638
poem
Token poem
Feature activation+1.684
below
Token below
Feature activation+2.039
.
Token.
Feature activation+0.247
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
i
Tokeni
Feature activation+0.000
saw
Token saw
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Wh
TokenWh
Feature activation+0.000
ole
Tokenole
Feature activation+0.000
bunch
Token bunch
Feature activation+1.450
of
Token of
Feature activation+1.941
shirt
Token shirt
Feature activation+0.670
orders
Token orders
Feature activation+0.615
went
Token went
Feature activation+1.275
out
Token out
Feature activation+0.121
today
Token today
Feature activation+0.000
I
Token I
Feature activation+0.000
blame
Token blame
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
whole
Token whole
Feature activation+0.138
thing
Token thing
Feature activation+2.012
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.091
person
Token person
Feature activation+0.000
selling
Token selling
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.000
,
Token,
Feature activation+0.758
from
Token from
Feature activation+1.956
its
Token its
Feature activation+0.000
start
Token start
Feature activation+0.827
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.226 - 1.635
CONTAINS 0.009%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
own
Token own
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
route
Token route
Feature activation+1.483
,
Token,
Feature activation+1.784
despite
Token despite
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
programs
Token programs
Feature activation+0.000
apple
Token apple
Feature activation+0.000
farm
Token farm
Feature activation+0.000
their
Token their
Feature activation+0.000
whole
Token whole
Feature activation+0.011
life
Token life
Feature activation+1.879
and
Token and
Feature activation+1.507
the
Token the
Feature activation+0.040
second
Token second
Feature activation+0.000
person
Token person
Feature activation+0.000
has
Token has
Feature activation+0.000
lived
Token lived
Feature activation+0.000
write
Token write
Feature activation+0.000
an
Token an
Feature activation+0.000
entire
Token entire
Feature activation+0.298
article
Token article
Feature activation+3.104
on
Token on
Feature activation+2.910
the
Token the
Feature activation+1.552
promise
Token promise
Feature activation+0.000
and
Token and
Feature activation+0.758
peril
Token peril
Feature activation+0.000
of
Token of
Feature activation+0.000
OK
Token OK
Feature activation+0.000
TS
TokenTS
Feature activation+0.000
150
Token 150
Feature activation+0.000
66
Token66
Feature activation+0.000
eBook
Token eBook
Feature activation+1.111
,
Token,
Feature activation+2.736
which
Token which
Feature activation+1.382
treats
Token treats
Feature activation+0.000
of
Token of
Feature activation+0.000
collaborative
Token collaborative
Feature activation+0.000
robot
Token robot
Feature activation+0.000
safety
Token safety
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
her
Token her
Feature activation+0.000
whole
Token whole
Feature activation+1.251
family
Token family
Feature activation+2.992
to
Token to
Feature activation+1.543
space
Token space
Feature activation+0.224
.
Token.
Feature activation+0.004
The
Token The
Feature activation+0.000

INTERVAL 0.818 - 1.226
CONTAINS 0.012%

since
Token since
Feature activation+0.000
its
Token its
Feature activation+0.000
entire
Token entire
Feature activation+0.907
purpose
Token purpose
Feature activation+2.890
is
Token is
Feature activation+1.957
to
Token to
Feature activation+0.966
catalog
Token catalog
Feature activation+0.265
the
Token the
Feature activation+0.000
instances
Token instances
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
their
Token their
Feature activation+0.000
whole
Token whole
Feature activation+0.473
case
Token case
Feature activation+3.028
forward
Token forward
Feature activation+0.830
in
Token in
Feature activation+0.461
one
Token one
Feature activation+1.202
hour
Token hour
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
entire
Token entire
Feature activation+0.000
year
Token year
Feature activation+1.193
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.351
budget
Token budget
Feature activation+0.841
of
Token of
Feature activation+1.659
the
Token the
Feature activation+0.652
Mind
Token Mind
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Wars
Token Wars
Feature activation+0.000
franchise
Token franchise
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.000
.
Token.
Feature activation+1.118
A
Token A
Feature activation+0.000
new
Token new
Feature activation+0.000
Battle
Token Battle
Feature activation+0.172
front
Tokenfront
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
whole
Token whole
Feature activation+0.065
idea
Token idea
Feature activation+2.697
is
Token is
Feature activation+2.855
that
Token that
Feature activation+1.058
you
Token you
Feature activation+0.130
work
Token work
Feature activation+0.000
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.409 - 0.818
CONTAINS 0.021%

to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ordeal
Token ordeal
Feature activation+0.000
crossing
Token crossing
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.741
city
Token city
Feature activation+3.148
to
Token to
Feature activation+1.085
go
Token go
Feature activation+0.050
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+0.000
whole
Token whole
Feature activation+0.652
community
Token community
Feature activation+2.949
thing
Token thing
Feature activation+1.913
,
Token,
Feature activation+1.330
and
Token and
Feature activation+0.518
we
Token we
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
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.776
city
Token city
Feature activation+3.479
was
Token was
Feature activation+3.365
empty
Token empty
Feature activation+0.702
.
Token.
Feature activation+0.312
The
Token The
Feature activation+0.000
giving
Token giving
Feature activation+0.000
over
Token over
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.106
life
Token life
Feature activation+0.567
of
Token of
Feature activation+1.522
the
Token the
Feature activation+1.604
couple
Token couple
Feature activation+0.000
to
Token to
Feature activation+0.173
God
Token God
Feature activation+0.000
exchange
Token exchange
Feature activation+2.086
was
Token was
Feature activation+2.789
shut
Token shut
Feature activation+1.074
down
Token down
Feature activation+0.580
by
Token by
Feature activation+0.082
the
Token the
Feature activation+0.648
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.169
Either
Token Either
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.409
CONTAINS 99.932%

to
Token to
Feature activation+0.000
sit
Token sit
Feature activation+0.000
down
Token down
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+0.000
and
Token and
Feature activation+0.000
explain
Token explain
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
taking
Token taking
Feature activation+0.000
bites
Token bites
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
molecules
Token molecules
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
essential
Token essential
Feature activation+0.000
titles
Token titles
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
1994
Token 1994
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
96
Token96
Feature activation+0.000
,
Token,
Feature activation+0.000
reached
Token reached
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
ISO
Token ISO
Feature activation+0.000
8
Token 8
Feature activation+0.000
583
Token583
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ISO
Token ISO
Feature activation+0.000
/
Token/
Feature activation+0.000
I
TokenI
Feature activation+0.000
EC
TokenEC
Feature activation+0.000
49
Token 49
Feature activation+0.000
342
Token342
Feature activation+0.000
,
Token,
Feature activation+0.000
6
Token6
Feature activation+0.000
34
Token34
Feature activation+0.000
in
Token in
Feature activation+0.000
taxpayer
Token taxpayer
Feature activation+0.000
hand
Token hand
Feature activation+0.000
outs
Tokenouts
Feature activation+0.000
from
Token from
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
through
Token through
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H3.11: (feature 4269)

TOP ACTIVATIONS
MAX = 2.691

like
Token like
Feature activation+0.850
today
Token today
Feature activation+0.000
for
Token for
Feature activation+0.919
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.700
say
Token say
Feature activation+2.691
this
Token this
Feature activation+0.265
,
Token,
Feature activation+0.202
but
Token but
Feature activation+2.232
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
make
Token make
Feature activation+1.123
it
Token it
Feature activation+1.973
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
channel
Token channel
Feature activation+0.000
but
Token but
Feature activation+2.643
when
Token when
Feature activation+0.761
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
and
Token and
Feature activation+0.000
look
Token look
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.101
to
Token to
Feature activation+0.450
tell
Token tell
Feature activation+0.842
if
Token if
Feature activation+2.633
this
Token this
Feature activation+0.615
idea
Token idea
Feature activation+0.000
has
Token has
Feature activation+0.143
been
Token been
Feature activation+0.111
put
Token put
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.231
think
Token think
Feature activation+0.863
of
Token of
Feature activation+0.791
a
Token a
Feature activation+0.274
more
Token more
Feature activation+2.485
misguided
Token misguided
Feature activation+0.000
application
Token application
Feature activation+0.000
than
Token than
Feature activation+2.159
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
tough
Token tough
Feature activation+0.265
cover
Token cover
Feature activation+0.000
for
Token for
Feature activation+2.431
MJ
Token MJ
Feature activation+0.000
,
Token,
Feature activation+0.183
but
Token but
Feature activation+1.297
LeBron
Token LeBron
Feature activation+0.000
is
Token is
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.390
to
Token to
Feature activation+0.684
study
Token study
Feature activation+1.549
because
Token because
Feature activation+2.390
,
Token,
Feature activation+0.582
between
Token between
Feature activation+0.000
episodes
Token episodes
Feature activation+0.000
,
Token,
Feature activation+0.000
people
Token people
Feature activation+0.000
was
Token was
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.363
find
Token find
Feature activation+1.013
so
Token so
Feature activation+2.344
maybe
Token maybe
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
did
Token did
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.500
levy
Token levy
Feature activation+0.750
any
Token any
Feature activation+2.341
charges
Token charges
Feature activation+0.000
,
Token,
Feature activation+0.000
Ste
Token Ste
Feature activation+0.000
iding
Tokeniding
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
tough
Token tough
Feature activation+0.293
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
,
Token,
Feature activation+0.447
but
Token but
Feature activation+2.341
slowly
Token slowly
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+0.000
came
Token came
Feature activation+0.000
.
Token.
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.808
to
Token to
Feature activation+1.166
explain
Token explain
Feature activation+1.736
what
Token what
Feature activation+2.309
this
Token this
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
is
Token is
Feature activation+0.423
like
Token like
Feature activation+0.211
because
Token because
Feature activation+1.496
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.317
to
Token to
Feature activation+0.318
see
Token see
Feature activation+0.758
how
Token how
Feature activation+2.309
many
Token many
Feature activation+0.041
parts
Token parts
Feature activation+0.000
make
Token make
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
tough
Token tough
Feature activation+0.383
,
Token,
Feature activation+0.476
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.470
to
Token to
Feature activation+0.780
predict
Token predict
Feature activation+2.270
exactly
Token exactly
Feature activation+0.790
what
Token what
Feature activation+0.000
will
Token will
Feature activation+0.000
tick
Token tick
Feature activation+0.000
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
tough
Token tough
Feature activation+1.871
line
Token line
Feature activation+0.367
to
Token to
Feature activation+2.239
tread
Token tread
Feature activation+1.464
because
Token because
Feature activation+2.255
the
Token the
Feature activation+0.000
blame
Token blame
Feature activation+0.000
should
Token should
Feature activation+0.000
still
Token still
Feature activation+0.000
be
Token be
Feature activation+0.232
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
these
Token these
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.284
but
Token but
Feature activation+2.247
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
overall
Token overall
Feature activation+0.000
gest
Token gest
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.506
tell
Token tell
Feature activation+0.583
what
Token what
Feature activation+2.244
kind
Token kind
Feature activation+0.090
of
Token of
Feature activation+0.000
shark
Token shark
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
tough
Token tough
Feature activation+1.871
line
Token line
Feature activation+0.367
to
Token to
Feature activation+2.239
tread
Token tread
Feature activation+1.464
because
Token because
Feature activation+2.255
the
Token the
Feature activation+0.000
blame
Token blame
Feature activation+0.000
should
Token should
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.700
say
Token say
Feature activation+2.691
this
Token this
Feature activation+0.265
,
Token,
Feature activation+0.202
but
Token but
Feature activation+2.232
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Welcome
TokenWelcome
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.791
a
Token a
Feature activation+0.274
more
Token more
Feature activation+2.485
misguided
Token misguided
Feature activation+0.000
application
Token application
Feature activation+0.000
than
Token than
Feature activation+2.159
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
maintenance
Token maintenance
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.364
to
Token to
Feature activation+0.412
describe
Token describe
Feature activation+1.221
what
Token what
Feature activation+2.098
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+0.448
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
difficult
Token difficult
Feature activation+0.527
to
Token to
Feature activation+0.618
predict
Token predict
Feature activation+1.680
how
Token how
Feature activation+2.088
Goodell
Token Goodell
Feature activation+0.000
will
Token will
Feature activation+0.000
wield
Token wield
Feature activation+0.000
his
Token his
Feature activation+0.000
discretionary
Token discretionary
Feature activation+0.000

Top DFA by src position
MAX = 4.197

Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
"
Token"
Feature activation-0.023
Top resid features:
It
TokenIt
Feature activation-0.025
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
hard
Token hard
Feature activation+4.013
Top resid features:
given
Token given
Feature activation+0.052
Top resid features:
stories
Token stories
Feature activation-0.051
Top resid features:
like
Token like
Feature activation+0.102
Top resid features:
today
Token today
Feature activation-0.013
Top resid features:
for
Token for
Feature activation+0.081
Top resid features:
sea
Token sea
Feature activation-0.002
Top resid features:
level
Token level
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
It
Token It
Feature activation-0.023
Top resid features:
's
Token's
Feature activation-0.009
Top resid features:
hard
Token hard
Feature activation+4.033
Top resid features:
to
Token to
Feature activation+0.070
Top resid features:
make
Token make
Feature activation+0.050
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
out
Token out
Feature activation+0.097
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
it
Token it
Feature activation-0.084
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
hard
Token hard
Feature activation+4.197
Top resid features:
to
Token to
Feature activation-0.117
Top resid features:
tell
Token tell
Feature activation+0.120
Top resid features:
if
Token if
Feature activation+0.110
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
but
Token but
Feature activation-0.010
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
hard
Token hard
Feature activation+3.812
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
think
Token think
Feature activation-0.065
Top resid features:
of
Token of
Feature activation+0.248
Top resid features:
a
Token a
Feature activation+0.125
Top resid features:
more
Token more
Feature activation-0.051
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Kobe
Token Kobe
Feature activation-0.041
Top resid features:
might
Token might
Feature activation+0.053
Top resid features:
be
Token be
Feature activation+0.038
Top resid features:
a
Token a
Feature activation-0.059
Top resid features:
tough
Token tough
Feature activation+3.497
Top resid features:
cover
Token cover
Feature activation+0.258
Top resid features:
for
Token for
Feature activation+0.303
Top resid features:
MJ
Token MJ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
It
TokenIt
Feature activation-0.078
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
difficult
Token difficult
Feature activation+3.804
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
study
Token study
Feature activation+0.132
Top resid features:
because
Token because
Feature activation+0.084
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
"
Token "
Feature activation-0.045
Top resid features:
It
TokenIt
Feature activation-0.029
Top resid features:
was
Token was
Feature activation+0.023
Top resid features:
pretty
Token pretty
Feature activation+0.050
Top resid features:
hard
Token hard
Feature activation+3.602
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
find
Token find
Feature activation+0.312
Top resid features:
so
Token so
Feature activation+0.082
Top resid features:
maybe
Token maybe
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
protected
Token protected
Feature activation-0.012
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.016
Top resid features:
it
Token it
Feature activation-0.025
Top resid features:
could
Token could
Feature activation-0.034
Top resid features:
be
Token be
Feature activation+0.031
Top resid features:
difficult
Token difficult
Feature activation+3.853
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
levy
Token levy
Feature activation+0.118
Top resid features:
any
Token any
Feature activation+0.077
Top resid features:
charges
Token charges
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
They
Token They
Feature activation-0.040
Top resid features:
found
Token found
Feature activation+0.004
Top resid features:
it
Token it
Feature activation-0.062
Top resid features:
tough
Token tough
Feature activation+3.696
Top resid features:
at
Token at
Feature activation+0.111
Top resid features:
first
Token first
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.131
Top resid features:
but
Token but
Feature activation+0.017
Top resid features:
slowly
Token slowly
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
"
Token"
Feature activation-0.021
Top resid features:
It
TokenIt
Feature activation-0.039
Top resid features:
's
Token's
Feature activation+0.027
Top resid features:
hard
Token hard
Feature activation+3.493
Top resid features:
to
Token to
Feature activation-0.065
Top resid features:
explain
Token explain
Feature activation+0.351
Top resid features:
what
Token what
Feature activation+0.120
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
feeling
Token feeling
Feature activation+0.000
Top resid features:
mentioned
Token mentioned
Feature activation-0.011
Top resid features:
before
Token before
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
it
Token it
Feature activation-0.045
Top resid features:
is
Token is
Feature activation+0.040
Top resid features:
difficult
Token difficult
Feature activation+4.072
Top resid features:
to
Token to
Feature activation-0.106
Top resid features:
see
Token see
Feature activation+0.042
Top resid features:
how
Token how
Feature activation-0.007
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
parts
Token parts
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
It
TokenIt
Feature activation-0.100
Top resid features:
has
Token has
Feature activation+0.034
Top resid features:
been
Token been
Feature activation-0.008
Top resid features:
tough
Token tough
Feature activation+3.655
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
however
Token however
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.254
Top resid features:
predict
Token predict
Feature activation+0.119
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
ľ
Tokenľ
Feature activation+0.007
Top resid features:
It
TokenIt
Feature activation-0.007
Top resid features:
's
Token's
Feature activation+0.025
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
tough
Token tough
Feature activation+3.792
Top resid features:
line
Token line
Feature activation+0.089
Top resid features:
to
Token to
Feature activation+0.052
Top resid features:
tread
Token tread
Feature activation-0.029
Top resid features:
because
Token because
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
neoliberal
Token neoliberal
Feature activation+0.000
Top resid features:
ism
Tokenism
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
It
Token It
Feature activation-0.042
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
tough
Token tough
Feature activation+3.459
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
say
Token say
Feature activation+0.172
Top resid features:
where
Token where
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
party
Token party
Feature activation-0.001
Top resid features:
because
Token because
Feature activation+0.047
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
hard
Token hard
Feature activation+3.574
Top resid features:
to
Token to
Feature activation-0.027
Top resid features:
tell
Token tell
Feature activation+0.094
Top resid features:
what
Token what
Feature activation+0.090
Top resid features:
kind
Token kind
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
It
TokenIt
Feature activation-0.034
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
a
Token a
Feature activation-0.111
Top resid features:
tough
Token tough
Feature activation+3.851
Top resid features:
line
Token line
Feature activation+0.097
Top resid features:
to
Token to
Feature activation+0.105
Top resid features:
tread
Token tread
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
"
Token"
Feature activation-0.016
Top resid features:
It
TokenIt
Feature activation+0.002
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
hard
Token hard
Feature activation+3.459
Top resid features:
given
Token given
Feature activation+0.086
Top resid features:
stories
Token stories
Feature activation-0.015
Top resid features:
like
Token like
Feature activation+0.079
Top resid features:
today
Token today
Feature activation-0.013
Top resid features:
for
Token for
Feature activation+0.023
Top resid features:
but
Token but
Feature activation-0.023
Top resid features:
it
Token it
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.028
Top resid features:
hard
Token hard
Feature activation+3.326
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
think
Token think
Feature activation-0.058
Top resid features:
of
Token of
Feature activation+0.075
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
more
Token more
Feature activation-0.018
Top resid features:
ptoms
Tokenptoms
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
It
TokenIt
Feature activation-0.058
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
difficult
Token difficult
Feature activation+3.394
Top resid features:
to
Token to
Feature activation-0.042
Top resid features:
describe
Token describe
Feature activation+0.263
Top resid features:
what
Token what
Feature activation+0.091
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
While
TokenWhile
Feature activation+0.017
Top resid features:
it
Token it
Feature activation-0.034
Top resid features:
's
Token's
Feature activation+0.038
Top resid features:
difficult
Token difficult
Feature activation+3.541
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
predict
Token predict
Feature activation+0.101
Top resid features:
how
Token how
Feature activation+0.108
Top resid features:
Goodell
Token Goodell
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.05

Head 3: 0.02

Head 4: 0.02

Head 5: 0.07

Head 6: 0.05

Head 7: 0.05

Head 8: 0.04

Head 9: 0.06

Head 10: 0.07

Head 11: 0.50

Positive logits

nor1.77

anymore1.56

too1.50

due1.46

Reviewer1.40

til1.30

cemic1.27

1.24

comings1.23

Flavoring1.23

ennis1.22

overly1.21

ffen1.19

waning1.18

Younger1.18

underestimated1.18

particularly1.18

sclerosis1.18

esides1.17

Raw1.16

Negative logits

ailability-1.36

srfAttach-1.28

��-1.24

��-1.21

ertodd-1.16

gdala-1.16

SetTextColor-1.15

AG-1.14

RON-1.14

imus-1.14

teasp-1.14

inery-1.13

��-1.13

ioxide-1.13

proceeds-1.13

agent-1.12

��-1.12

instead-1.11

DragonMagazine-1.11

pier-1.11

INTERVAL 2.421 - 2.691
CONTAINS 0.001%

make
Token make
Feature activation+1.123
it
Token it
Feature activation+1.973
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
channel
Token channel
Feature activation+0.000
but
Token but
Feature activation+2.643
when
Token when
Feature activation+0.761
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
and
Token and
Feature activation+0.000
look
Token look
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
tough
Token tough
Feature activation+0.265
cover
Token cover
Feature activation+0.000
for
Token for
Feature activation+2.431
MJ
Token MJ
Feature activation+0.000
,
Token,
Feature activation+0.183
but
Token but
Feature activation+1.297
LeBron
Token LeBron
Feature activation+0.000
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.850
today
Token today
Feature activation+0.000
for
Token for
Feature activation+0.919
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.700
say
Token say
Feature activation+2.691
this
Token this
Feature activation+0.265
,
Token,
Feature activation+0.202
but
Token but
Feature activation+2.232
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.101
to
Token to
Feature activation+0.450
tell
Token tell
Feature activation+0.842
if
Token if
Feature activation+2.633
this
Token this
Feature activation+0.615
idea
Token idea
Feature activation+0.000
has
Token has
Feature activation+0.143
been
Token been
Feature activation+0.111
put
Token put
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.231
think
Token think
Feature activation+0.863
of
Token of
Feature activation+0.791
a
Token a
Feature activation+0.274
more
Token more
Feature activation+2.485
misguided
Token misguided
Feature activation+0.000
application
Token application
Feature activation+0.000
than
Token than
Feature activation+2.159
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.152 - 2.421
CONTAINS 0.001%

me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.700
say
Token say
Feature activation+2.691
this
Token this
Feature activation+0.265
,
Token,
Feature activation+0.202
but
Token but
Feature activation+2.232
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Welcome
TokenWelcome
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
these
Token these
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.284
but
Token but
Feature activation+2.247
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
overall
Token overall
Feature activation+0.000
gest
Token gest
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.506
tell
Token tell
Feature activation+0.583
what
Token what
Feature activation+2.244
kind
Token kind
Feature activation+0.090
of
Token of
Feature activation+0.000
shark
Token shark
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
it
Token it
Feature activation+0.000
tough
Token tough
Feature activation+0.293
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
,
Token,
Feature activation+0.447
but
Token but
Feature activation+2.341
slowly
Token slowly
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+0.000
came
Token came
Feature activation+0.000
.
Token.
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.808
to
Token to
Feature activation+1.166
explain
Token explain
Feature activation+1.736
what
Token what
Feature activation+2.309
this
Token this
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
is
Token is
Feature activation+0.423
like
Token like
Feature activation+0.211
because
Token because
Feature activation+1.496

INTERVAL 1.883 - 2.152
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.458
say
Token say
Feature activation+1.222
whether
Token whether
Feature activation+2.020
Elephant
Token Elephant
Feature activation+0.000
777
Token777
Feature activation+0.000
has
Token has
Feature activation+0.000
something
Token something
Feature activation+0.000
personal
Token personal
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.364
to
Token to
Feature activation+0.412
describe
Token describe
Feature activation+1.221
what
Token what
Feature activation+2.098
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+0.448
's
Token's
Feature activation+0.000
very
Token very
Feature activation+0.000
difficult
Token difficult
Feature activation+0.233
to
Token to
Feature activation+0.332
discern
Token discern
Feature activation+0.971
how
Token how
Feature activation+2.020
they
Token they
Feature activation+0.505
determined
Token determined
Feature activation+0.067
this
Token this
Feature activation+0.109
compensation
Token compensation
Feature activation+0.000
package
Token package
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.859
to
Token to
Feature activation+1.421
make
Token make
Feature activation+1.123
it
Token it
Feature activation+1.973
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
channel
Token channel
Feature activation+0.000
but
Token but
Feature activation+2.643
when
Token when
Feature activation+0.761
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
tough
Token tough
Feature activation+0.305
to
Token to
Feature activation+0.863
say
Token say
Feature activation+1.535
where
Token where
Feature activation+1.943
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
's
Token's
Feature activation+0.000
head
Token head
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 1.614 - 1.883
CONTAINS 0.002%

to
Token to
Feature activation+0.028
pick
Token pick
Feature activation+0.293
a
Token a
Feature activation+0.533
winner
Token winner
Feature activation+0.039
,
Token,
Feature activation+0.485
but
Token but
Feature activation+1.769
told
Token told
Feature activation+0.000
fans
Token fans
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
tough
Token tough
Feature activation+0.621
situation
Token situation
Feature activation+0.631
for
Token for
Feature activation+1.714
everyone
Token everyone
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.827
go
Token go
Feature activation+0.000
.
Token.
Feature activation+0.502
is
Token is
Feature activation+0.000
often
Token often
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.137
understand
Token understand
Feature activation+1.190
why
Token why
Feature activation+1.644
government
Token government
Feature activation+0.000
bureaucr
Token bureaucr
Feature activation+0.000
acies
Tokenacies
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.026
to
Token to
Feature activation+0.954
imagine
Token imagine
Feature activation+1.675
Car
Token Car
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ever
Token ever
Feature activation+1.341
being
Token being
Feature activation+0.000
that
Token that
Feature activation+1.576
incredibly
Token incredibly
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
in
Token in
Feature activation+0.008
those
Token those
Feature activation+0.631
instances
Token instances
Feature activation+0.000
when
Token when
Feature activation+1.757
you
Token you
Feature activation+0.020
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
trying
Token trying
Feature activation+0.000

INTERVAL 1.345 - 1.614
CONTAINS 0.003%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.326
entirely
Token entirely
Feature activation+1.040
prevent
Token prevent
Feature activation+1.466
a
Token a
Feature activation+0.000
Content
Token Content
Feature activation+0.000
ID
TokenID
Feature activation+0.000
claim
Token claim
Feature activation+0.000
.
Token.
Feature activation+0.644
that
Token that
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
difficult
Token difficult
Feature activation+0.197
for
Token for
Feature activation+0.000
anyone
Token anyone
Feature activation+1.394
but
Token but
Feature activation+1.110
a
Token a
Feature activation+0.000
human
Token human
Feature activation+0.000
to
Token to
Feature activation+0.000
decipher
Token decipher
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
tough
Token tough
Feature activation+0.305
to
Token to
Feature activation+0.863
say
Token say
Feature activation+1.535
where
Token where
Feature activation+1.943
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
's
Token's
Feature activation+0.000
head
Token head
Feature activation+0.000
hardest
Token hardest
Feature activation+0.108
feats
Token feats
Feature activation+0.000
to
Token to
Feature activation+0.464
achieve
Token achieve
Feature activation+0.000
in
Token in
Feature activation+0.135
any
Token any
Feature activation+1.398
game
Token game
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
board
Token board
Feature activation+0.000
each
Token each
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+1.445
Look
Token Look
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000

INTERVAL 1.076 - 1.345
CONTAINS 0.005%

it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.337
to
Token to
Feature activation+0.779
be
Token be
Feature activation+0.000
too
Token too
Feature activation+1.191
positive
Token positive
Feature activation+0.000
when
Token when
Feature activation+1.382
the
Token the
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
goalkeeper
Token goalkeeper
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.343
for
Token for
Feature activation+0.426
this
Token this
Feature activation+0.919
community
Token community
Feature activation+0.000
.
Token.
Feature activation+1.107
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+1.281
misinterpret
Token misinterpret
Feature activation+0.502
an
Token an
Feature activation+0.665
airliner
Token airliner
Feature activation+0.000
at
Token at
Feature activation+0.130
such
Token such
Feature activation+1.192
height
Token height
Feature activation+0.000
as
Token as
Feature activation+0.944
a
Token a
Feature activation+0.000
threat
Token threat
Feature activation+0.000
,
Token,
Feature activation+0.000
imagine
Token imagine
Feature activation+1.168
Congress
Token Congress
Feature activation+0.000
approving
Token approving
Feature activation+0.000
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+1.114
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
these
Token these
Feature activation+0.000
caveats
Token caveats
Feature activation+0.000
harder
Token harder
Feature activation+0.133
to
Token to
Feature activation+0.100
convey
Token convey
Feature activation+1.222
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.638
but
Token but
Feature activation+1.313
film
Token film
Feature activation+0.000
no
Token no
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
coded
Token coded
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.807 - 1.076
CONTAINS 0.010%

.
Token.
Feature activation+0.440
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.343
for
Token for
Feature activation+0.426
this
Token this
Feature activation+0.919
community
Token community
Feature activation+0.000
.
Token.
Feature activation+1.107
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
a
Token a
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
presence
Token presence
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
if
Token if
Feature activation+0.977
they
Token they
Feature activation+0.000
use
Token use
Feature activation+0.000
intermedi
Token intermedi
Feature activation+0.000
aries
Tokenaries
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
challenging
Token challenging
Feature activation+0.621
collision
Token collision
Feature activation+0.918
in
Token in
Feature activation+0.815
that
Token that
Feature activation+0.682
there
Token there
Feature activation+0.646
is
Token is
Feature activation+0.033
a
Token a
Feature activation+0.220
considerable
Token considerable
Feature activation+0.000
it
Token it
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
for
Token for
Feature activation+0.061
the
Token the
Feature activation+0.088
president
Token president
Feature activation+0.000
to
Token to
Feature activation+0.953
now
Token now
Feature activation+0.855
claim
Token claim
Feature activation+0.455
that
Token that
Feature activation+0.595
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
man
Tokenman
Feature activation+0.000
family
Token family
Feature activation+0.000
during
Token during
Feature activation+0.000
this
Token this
Feature activation+0.000
difficult
Token difficult
Feature activation+0.898
time
Token time
Feature activation+0.270
.
Token.
Feature activation+0.020
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000

INTERVAL 0.538 - 0.807
CONTAINS 0.017%

Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
difficult
Token difficult
Feature activation+0.527
to
Token to
Feature activation+0.618
predict
Token predict
Feature activation+1.680
how
Token how
Feature activation+2.088
Goodell
Token Goodell
Feature activation+0.000
will
Token will
Feature activation+0.000
wield
Token wield
Feature activation+0.000
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.549
employees
Token employees
Feature activation+0.000
to
Token to
Feature activation+0.519
be
Token be
Feature activation+0.972
told
Token told
Feature activation+0.693
that
Token that
Feature activation+1.521
even
Token even
Feature activation+0.322
though
Token though
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
into
Token into
Feature activation+0.000
than
Token than
Feature activation+0.207
it
Token it
Feature activation+0.000
actually
Token actually
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.547
Really
Token Really
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
a
Token a
Feature activation+0.000
f
Token f
Feature activation+0.000
udge
Tokenudge
Feature activation+0.000
pack
Token pack
Feature activation+0.000
er
Tokener
Feature activation+0.000
as
Token as
Feature activation+0.787
well
Token well
Feature activation+0.000
since
Token since
Feature activation+0.595
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
literally
Token literally
Feature activation+0.000
the
Token the
Feature activation+0.778
NBA
Token NBA
Feature activation+0.000
than
Token than
Feature activation+1.159
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
?
Token?
Feature activation+0.740
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.000

INTERVAL 0.269 - 0.538
CONTAINS 0.031%

wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
a
Token a
Feature activation+0.000
difficult
Token difficult
Feature activation+0.461
one
Token one
Feature activation+0.125
,
Token,
Feature activation+1.042
as
Token as
Feature activation+1.471
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
Others
Token Others
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
utterly
Token utterly
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.308
believe
Token believe
Feature activation+0.000
how
Token how
Feature activation+0.903
someone
Token someone
Feature activation+0.000
like
Token like
Feature activation+0.000
him
Token him
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.549
employees
Token employees
Feature activation+0.000
to
Token to
Feature activation+0.519
be
Token be
Feature activation+0.972
told
Token told
Feature activation+0.693
that
Token that
Feature activation+1.521
even
Token even
Feature activation+0.322
though
Token though
Feature activation+0.000
to
Token to
Feature activation+0.000
act
Token act
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
.
Token.
Feature activation+0.525
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
'
Token'
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.188
the
Token the
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
.
Token.
Feature activation+0.434
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 0.000 - 0.269
CONTAINS 99.930%

polls
Token polls
Feature activation+0.000
held
Token held
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
a
Tokena
Feature activation+0.000
fell
Token fell
Feature activation+0.000
short
Token short
Feature activation+0.000
of
Token of
Feature activation+0.000
analog
Token analog
Feature activation+0.000
for
Token for
Feature activation+0.000
Haskell
Token Haskell
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
time
Token time
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
begins
Token begins
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
in
Token in
Feature activation+0.000
J
Token J
Feature activation+0.000
aff
Tokenaff
Feature activation+0.000
a
Tokena
Feature activation+0.000
ANT
TokenANT
Feature activation+0.000
E
TokenE
Feature activation+0.000
ES
TokenES
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
neither
Token neither
Feature activation+0.000
can
Token can
Feature activation+0.000
Fresh
Token Fresh
Feature activation+0.000
marine
Tokenmarine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
grip
Token grip
Feature activation+0.000
on
Token on
Feature activation+0.066
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H3.11: (feature 21877)

TOP ACTIVATIONS
MAX = 3.138

Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+1.215
the
Token the
Feature activation+1.936
point
Token point
Feature activation+3.138
,
Token,
Feature activation+2.470
Graham
Token Graham
Feature activation+0.000
was
Token was
Feature activation+1.042
also
Token also
Feature activation+0.000
relying
Token relying
Feature activation+0.000
audience
Token audience
Feature activation+0.000
had
Token had
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.964
do
Token do
Feature activation+1.712
with
Token with
Feature activation+2.982
rock
Token rock
Feature activation+0.000
and
Token and
Feature activation+0.000
roll
Token roll
Feature activation+0.000
than
Token than
Feature activation+0.000
with
Token with
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
interesting
Token interesting
Feature activation+2.979
to
Token to
Feature activation+0.713
me
Token me
Feature activation+0.731
is
Token is
Feature activation+0.842
that
Token that
Feature activation+0.299
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
lab
Token lab
Feature activation+0.167
material
Token material
Feature activation+1.201
can
Token can
Feature activation+2.129
be
Token be
Feature activation+1.739
found
Token found
Feature activation+2.976
on
Token on
Feature activation+1.017
the
Token the
Feature activation+0.722
wiki
Token wiki
Feature activation+0.000
,
Token,
Feature activation+0.399
and
Token and
Feature activation+0.489
"
Token"
Feature activation+0.000
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
more
Token more
Feature activation+0.000
oxidation
Token oxidation
Feature activation+1.189
involved
Token involved
Feature activation+2.931
in
Token in
Feature activation+1.538
the
Token the
Feature activation+0.785
new
Token new
Feature activation+0.000
sample
Token sample
Feature activation+0.000
,"
Token,"
Feature activation+1.282
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
fires
Token fires
Feature activation+0.546
to
Token to
Feature activation+2.483
come
Token come
Feature activation+2.923
in
Token in
Feature activation+1.427
the
Token the
Feature activation+1.198
days
Token days
Feature activation+0.000
and
Token and
Feature activation+0.285
weeks
Token weeks
Feature activation+0.000
Waters
Token Waters
Feature activation+0.000
captured
Token captured
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
color
Token color
Feature activation+0.000
fully
Tokenfully
Feature activation+2.915
than
Token than
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
to
Token to
Feature activation+0.756
the
Token the
Feature activation+1.842
point
Token point
Feature activation+2.796
,
Token,
Feature activation+1.210
the
Token the
Feature activation+0.314
stealth
Token stealth
Feature activation+0.000
recruitment
Token recruitment
Feature activation+0.000
and
Token and
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
environmental
Token environmental
Feature activation+0.181
implications
Token implications
Feature activation+2.732
.
Token.
Feature activation+0.811
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Basically
TokenBasically
Feature activation+0.000
to
Token to
Feature activation+0.000
Other
Token Other
Feature activation+0.000
observers
Token observers
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
scept
Token scept
Feature activation+1.313
ical
Tokenical
Feature activation+2.716
.
Token.
Feature activation+0.414
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Rah
TokenRah
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+2.697
to
Token to
Feature activation+1.089
me
Token me
Feature activation+0.202
and
Token and
Feature activation+0.312
to
Token to
Feature activation+0.095
Canada
Token Canada
Feature activation+0.000
If
TokenIf
Feature activation+0.000
this
Token this
Feature activation+0.000
gets
Token gets
Feature activation+0.000
more
Token more
Feature activation+0.000
parents
Token parents
Feature activation+0.292
involved
Token involved
Feature activation+2.688
in
Token in
Feature activation+1.784
what
Token what
Feature activation+0.591
their
Token their
Feature activation+0.000
children
Token children
Feature activation+0.000
do
Token do
Feature activation+0.161
something
Token something
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
sinister
Token sinister
Feature activation+2.337
occurring
Token occurring
Feature activation+1.987
in
Token in
Feature activation+2.677
the
Token the
Feature activation+1.634
streets
Token streets
Feature activation+0.000
of
Token of
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
It
TokenIt
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
more
Token more
Feature activation+0.000
probable
Token probable
Feature activation+2.672
that
Token that
Feature activation+2.009
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
building
Token building
Feature activation+0.000
's
Token's
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Time
TokenTime
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.003
important
Token important
Feature activation+2.648
than
Token than
Feature activation+0.000
money
Token money
Feature activation+0.000
!
Token!
Feature activation+0.000
There
Token There
Feature activation+0.000
I
Token I
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
victory
Token victory
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+2.569
as
Token as
Feature activation+1.178
it
Token it
Feature activation+0.000
maintains
Token maintains
Feature activation+0.000
our
Token our
Feature activation+0.000
lead
Token lead
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
ballots
Token ballots
Feature activation+1.678
were
Token were
Feature activation+1.716
drawn
Token drawn
Feature activation+1.766
in
Token in
Feature activation+1.297
every
Token every
Feature activation+2.569
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
more
Token more
Feature activation+0.000
years
Token years
Feature activation+2.559
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
get
Token get
Feature activation+0.000
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.807
in
Token in
Feature activation+2.012
jail
Token jail
Feature activation+0.899
then
Token then
Feature activation+2.544
if
Token if
Feature activation+0.692
you
Token you
Feature activation+0.000
kill
Token kill
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
expected
Token expected
Feature activation+0.000
more
Token more
Feature activation+0.000
l
Token l
Feature activation+0.327
arc
Tokenarc
Feature activation+0.000
eny
Tokeneny
Feature activation+2.023
charges
Token charges
Feature activation+2.538
pred
Token pred
Feature activation+0.604
icated
Tokenicated
Feature activation+0.964
upon
Token upon
Feature activation+1.546
a
Token a
Feature activation+0.246
pet
Token pet
Feature activation+0.000

Top DFA by src position
MAX = 3.714

himself
Token himself
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
But
TokenBut
Feature activation+0.086
Top resid features:
more
Token more
Feature activation+3.530
Top resid features:
to
Token to
Feature activation+0.071
Top resid features:
the
Token the
Feature activation-0.142
Top resid features:
point
Token point
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Graham
Token Graham
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
his
Token his
Feature activation-0.023
Top resid features:
young
Token young
Feature activation-0.024
Top resid features:
audience
Token audience
Feature activation+0.021
Top resid features:
had
Token had
Feature activation+0.042
Top resid features:
more
Token more
Feature activation+3.262
Top resid features:
to
Token to
Feature activation+0.075
Top resid features:
do
Token do
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.090
Top resid features:
rock
Token rock
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
What
Token What
Feature activation-0.025
Top resid features:
is
Token is
Feature activation-0.200
Top resid features:
more
Token more
Feature activation+3.714
Top resid features:
interesting
Token interesting
Feature activation-0.109
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
used
Token used
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
class
Token class
Feature activation+0.002
Top resid features:
;
Token;
Feature activation+0.032
Top resid features:
more
Token more
Feature activation+3.409
Top resid features:
lab
Token lab
Feature activation+0.025
Top resid features:
material
Token material
Feature activation-0.003
Top resid features:
can
Token can
Feature activation-0.046
Top resid features:
be
Token be
Feature activation-0.055
Top resid features:
found
Token found
Feature activation+0.034
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
"
Token"
Feature activation-0.014
Top resid features:
There
TokenThere
Feature activation+0.074
Top resid features:
's
Token's
Feature activation+0.081
Top resid features:
more
Token more
Feature activation+3.284
Top resid features:
oxidation
Token oxidation
Feature activation-0.028
Top resid features:
involved
Token involved
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
undoubtedly
Token undoubtedly
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
there
Token there
Feature activation+0.030
Top resid features:
will
Token will
Feature activation+0.032
Top resid features:
be
Token be
Feature activation+0.028
Top resid features:
more
Token more
Feature activation+3.202
Top resid features:
fires
Token fires
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.153
Top resid features:
come
Token come
Feature activation-0.071
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.061
Top resid features:
Waters
Token Waters
Feature activation-0.016
Top resid features:
captured
Token captured
Feature activation-0.009
Top resid features:
it
Token it
Feature activation-0.114
Top resid features:
more
Token more
Feature activation+3.492
Top resid features:
color
Token color
Feature activation+0.018
Top resid features:
fully
Tokenfully
Feature activation-0.042
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
anyone
Token anyone
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
not
Token not
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
game
Token game
Feature activation-0.017
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
More
Token More
Feature activation+3.356
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.145
Top resid features:
point
Token point
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.071
Top resid features:
are
Token are
Feature activation+0.015
Top resid features:
going
Token going
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
be
Token be
Feature activation+0.103
Top resid features:
more
Token more
Feature activation+2.834
Top resid features:
environmental
Token environmental
Feature activation+0.005
Top resid features:
implications
Token implications
Feature activation+0.074
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
back
Token back
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
Other
Token Other
Feature activation-0.078
Top resid features:
observers
Token observers
Feature activation+0.035
Top resid features:
are
Token are
Feature activation-0.137
Top resid features:
more
Token more
Feature activation+3.288
Top resid features:
scept
Token scept
Feature activation+0.021
Top resid features:
ical
Tokenical
Feature activation-0.024
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
ľ
Tokenľ
Feature activation+0.016
Top resid features:
No
TokenNo
Feature activation-0.031
Top resid features:
relationship
Token relationship
Feature activation+0.044
Top resid features:
is
Token is
Feature activation-0.156
Top resid features:
more
Token more
Feature activation+3.377
Top resid features:
important
Token important
Feature activation-0.146
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
"
Token"
Feature activation-0.005
Top resid features:
If
TokenIf
Feature activation+0.007
Top resid features:
this
Token this
Feature activation-0.018
Top resid features:
gets
Token gets
Feature activation+0.031
Top resid features:
more
Token more
Feature activation+3.040
Top resid features:
parents
Token parents
Feature activation-0.030
Top resid features:
involved
Token involved
Feature activation+0.048
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.001
Top resid features:
there
Token there
Feature activation+0.027
Top resid features:
is
Token is
Feature activation+0.029
Top resid features:
something
Token something
Feature activation+0.042
Top resid features:
far
Token far
Feature activation-0.121
Top resid features:
more
Token more
Feature activation+2.953
Top resid features:
sinister
Token sinister
Feature activation-0.055
Top resid features:
occurring
Token occurring
Feature activation+0.156
Top resid features:
in
Token in
Feature activation+0.095
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
streets
Token streets
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
It
TokenIt
Feature activation+0.040
Top resid features:
seems
Token seems
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
me
Token me
Feature activation+0.061
Top resid features:
more
Token more
Feature activation+3.053
Top resid features:
probable
Token probable
Feature activation-0.082
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
building
Token building
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.060
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Time
TokenTime
Feature activation-0.105
Top resid features:
is
Token is
Feature activation-0.200
Top resid features:
more
Token more
Feature activation+3.408
Top resid features:
important
Token important
Feature activation-0.095
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
money
Token money
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
means
Token means
Feature activation-0.004
Top resid features:
but
Token but
Feature activation+0.117
Top resid features:
the
Token the
Feature activation-0.093
Top resid features:
victory
Token victory
Feature activation-0.063
Top resid features:
is
Token is
Feature activation-0.170
Top resid features:
more
Token more
Feature activation+3.316
Top resid features:
important
Token important
Feature activation-0.106
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
maintains
Token maintains
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
ana
Tokenana
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.028
Top resid features:
More
Token More
Feature activation+3.306
Top resid features:
Democratic
Token Democratic
Feature activation-0.020
Top resid features:
ballots
Token ballots
Feature activation-0.029
Top resid features:
were
Token were
Feature activation+0.036
Top resid features:
drawn
Token drawn
Feature activation-0.117
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
his
Token his
Feature activation-0.060
Top resid features:
rights
Token rights
Feature activation-0.032
Top resid features:
for
Token for
Feature activation-0.021
Top resid features:
a
Token a
Feature activation-0.090
Top resid features:
few
Token few
Feature activation-0.021
Top resid features:
more
Token more
Feature activation+2.823
Top resid features:
years
Token years
Feature activation+0.210
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.038
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
get
Token get
Feature activation+0.011
Top resid features:
more
Token more
Feature activation+2.857
Top resid features:
time
Token time
Feature activation+0.077
Top resid features:
in
Token in
Feature activation+0.048
Top resid features:
jail
Token jail
Feature activation+0.035
Top resid features:
then
Token then
Feature activation-0.043
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
We
Token We
Feature activation+0.018
Top resid features:
would
Token would
Feature activation-0.007
Top resid features:
have
Token have
Feature activation+0.020
Top resid features:
expected
Token expected
Feature activation+0.067
Top resid features:
more
Token more
Feature activation+2.875
Top resid features:
l
Token l
Feature activation-0.078
Top resid features:
arc
Tokenarc
Feature activation+0.011
Top resid features:
eny
Tokeneny
Feature activation+0.036
Top resid features:
charges
Token charges
Feature activation+0.017
Top resid features:
pred
Token pred
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.08

Head 3: 0.03

Head 4: 0.02

Head 5: 0.05

Head 6: 0.06

Head 7: 0.06

Head 8: 0.04

Head 9: 0.04

Head 10: 0.06

Head 11: 0.50

Positive logits

than3.59

than3.51

Than2.61

erous1.69

besides1.24

Reviewer1.22

harsher1.21

oriented1.16

efficient1.14

NOW1.13

oldemort1.13

nearer1.12

manageable1.12

wiser1.10

Teg1.10

orer1.10

ubi1.09

>>>1.08

rab1.07

"}],"1.07

Negative logits

Disapp-1.26

ILCS-1.21

xtap-1.19

;;;;;;;;;;;;-1.18

サーティワン-1.16

Carnival-1.12

Jamaica-1.12

escription-1.09

Assass-1.09

mouth-1.07

Consolid-1.05

avin-1.05

cffffcc-1.05

Slip-1.04

verning-1.04

STON-1.04

velop-1.03

Happ-1.03

estead-1.02

Jinn-1.02

INTERVAL 2.825 - 3.138
CONTAINS 0.001%

"
Token"
Feature activation+0.000
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
more
Token more
Feature activation+0.000
oxidation
Token oxidation
Feature activation+1.189
involved
Token involved
Feature activation+2.931
in
Token in
Feature activation+1.538
the
Token the
Feature activation+0.785
new
Token new
Feature activation+0.000
sample
Token sample
Feature activation+0.000
,"
Token,"
Feature activation+1.282
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+1.215
the
Token the
Feature activation+1.936
point
Token point
Feature activation+3.138
,
Token,
Feature activation+2.470
Graham
Token Graham
Feature activation+0.000
was
Token was
Feature activation+1.042
also
Token also
Feature activation+0.000
relying
Token relying
Feature activation+0.000
more
Token more
Feature activation+0.000
lab
Token lab
Feature activation+0.167
material
Token material
Feature activation+1.201
can
Token can
Feature activation+2.129
be
Token be
Feature activation+1.739
found
Token found
Feature activation+2.976
on
Token on
Feature activation+1.017
the
Token the
Feature activation+0.722
wiki
Token wiki
Feature activation+0.000
,
Token,
Feature activation+0.399
and
Token and
Feature activation+0.489
Waters
Token Waters
Feature activation+0.000
captured
Token captured
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
color
Token color
Feature activation+0.000
fully
Tokenfully
Feature activation+2.915
than
Token than
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
fires
Token fires
Feature activation+0.546
to
Token to
Feature activation+2.483
come
Token come
Feature activation+2.923
in
Token in
Feature activation+1.427
the
Token the
Feature activation+1.198
days
Token days
Feature activation+0.000
and
Token and
Feature activation+0.285
weeks
Token weeks
Feature activation+0.000

INTERVAL 2.511 - 2.825
CONTAINS 0.002%

on
Token on
Feature activation+0.000
more
Token more
Feature activation+0.000
Des
Token Des
Feature activation+0.000
kt
Tokenkt
Feature activation+0.000
ops
Tokenops
Feature activation+0.000
like
Token like
Feature activation+2.531
Mate
Token Mate
Feature activation+0.000
and
Token and
Feature activation+0.000
X
Token X
Feature activation+0.000
FC
TokenFC
Feature activation+0.000
E
TokenE
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
ballots
Token ballots
Feature activation+1.678
were
Token were
Feature activation+1.716
drawn
Token drawn
Feature activation+1.766
in
Token in
Feature activation+1.297
every
Token every
Feature activation+2.569
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
something
Token something
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
sinister
Token sinister
Feature activation+2.337
occurring
Token occurring
Feature activation+1.987
in
Token in
Feature activation+2.677
the
Token the
Feature activation+1.634
streets
Token streets
Feature activation+0.000
of
Token of
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
If
TokenIf
Feature activation+0.000
this
Token this
Feature activation+0.000
gets
Token gets
Feature activation+0.000
more
Token more
Feature activation+0.000
parents
Token parents
Feature activation+0.292
involved
Token involved
Feature activation+2.688
in
Token in
Feature activation+1.784
what
Token what
Feature activation+0.591
their
Token their
Feature activation+0.000
children
Token children
Feature activation+0.000
do
Token do
Feature activation+0.161
1996
Token 1996
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
important
Token important
Feature activation+2.513
,
Token,
Feature activation+0.331
the
Token the
Feature activation+0.295
Politico
Token Politico
Feature activation+0.000
story
Token story
Feature activation+0.408
reports
Token reports
Feature activation+0.510

INTERVAL 2.197 - 2.511
CONTAINS 0.006%

of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.290
mockery
Token mockery
Feature activation+2.311
âĢ¦
TokenâĢ¦
Feature activation+1.238
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
aed
Tokenaed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bloomberg
TokenBloomberg
Feature activation+0.000
has
Token has
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
more
Token more
Feature activation+0.068
engaged
Token engaged
Feature activation+2.510
in
Token in
Feature activation+2.407
electoral
Token electoral
Feature activation+0.111
politics
Token politics
Feature activation+0.674
in
Token in
Feature activation+1.890
the
Token the
Feature activation+0.922
's
Token's
Feature activation+0.000
programme
Token programme
Feature activation+0.000
has
Token has
Feature activation+0.000
more
Token more
Feature activation+0.000
in
Token in
Feature activation+1.620
common
Token common
Feature activation+2.246
with
Token with
Feature activation+2.229
US
Token US
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
trust
Tokentrust
Feature activation+0.000
bound
Token bound
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
in
Token in
Feature activation+1.882
the
Token the
Feature activation+2.391
coming
Token coming
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
and
Token and
Feature activation+1.083
months
Token months
Feature activation+0.000
.
Token.
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
have
Token have
Feature activation+0.000
always
Token always
Feature activation+0.000
felt
Token felt
Feature activation+0.000
more
Token more
Feature activation+0.000
strongly
Token strongly
Feature activation+2.438
than
Token than
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000

INTERVAL 1.883 - 2.197
CONTAINS 0.017%

squeeze
Token squeeze
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
more
Token more
Feature activation+0.273
beach
Token beach
Feature activation+0.516
season
Token season
Feature activation+2.185
before
Token before
Feature activation+0.840
temporarily
Token temporarily
Feature activation+0.000
shutting
Token shutting
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
users
Token users
Feature activation+0.000
are
Token are
Feature activation+0.000
"
Token "
Feature activation+0.000
more
Tokenmore
Feature activation+0.000
comfortable
Token comfortable
Feature activation+2.179
when
Token when
Feature activation+0.977
something
Token something
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
pharmaceutical
Token pharmaceutical
Feature activation+0.000
-
Token-
Feature activation+0.000
income
Tokenincome
Feature activation+0.000
families
Token families
Feature activation+0.000
spend
Token spend
Feature activation+0.000
more
Token more
Feature activation+0.100
time
Token time
Feature activation+1.995
watching
Token watching
Feature activation+1.029
TV
Token TV
Feature activation+0.000
and
Token and
Feature activation+0.187
using
Token using
Feature activation+0.000
electronic
Token electronic
Feature activation+0.000
issues
Token issues
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
more
Token more
Feature activation+0.000
contentious
Token contentious
Feature activation+2.029
since
Token since
Feature activation+0.416
Trump
Token Trump
Feature activation+0.000
entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
done
Token done
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+2.130
than
Token than
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
,
Token,
Feature activation+0.000
yet
Token yet
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 1.569 - 1.883
CONTAINS 0.029%

More
Token More
Feature activation+0.000
research
Token research
Feature activation+1.324
is
Token is
Feature activation+2.094
needed
Token needed
Feature activation+1.934
to
Token to
Feature activation+1.552
find
Token find
Feature activation+1.573
out
Token out
Feature activation+0.103
how
Token how
Feature activation+0.000
drastically
Token drastically
Feature activation+0.000
the
Token the
Feature activation+0.000
whales
Token whales
Feature activation+0.000
the
Token the
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
and
Token and
Feature activation+0.000
promised
Token promised
Feature activation+0.000
more
Token more
Feature activation+0.000
acts
Token acts
Feature activation+1.698
of
Token of
Feature activation+0.235
violence
Token violence
Feature activation+1.713
to
Token to
Feature activation+1.007
come
Token come
Feature activation+0.944
:
Token:
Feature activation+0.224
a
Token a
Feature activation+0.000
slower
Token slower
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
more
Token more
Feature activation+0.174
satisfying
Token satisfying
Feature activation+1.676
burn
Token burn
Feature activation+0.000
like
Token like
Feature activation+2.057
few
Token few
Feature activation+0.000
other
Token other
Feature activation+0.000
medium
Token medium
Feature activation+0.000
that
Token that
Feature activation+0.000
bother
Token bother
Feature activation+0.000
me
Token me
Feature activation+0.000
more
Token more
Feature activation+0.000
every
Token every
Feature activation+1.992
time
Token time
Feature activation+1.796
I
Token I
Feature activation+0.000
hear
Token hear
Feature activation+0.000
them
Token them
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
coming
Token coming
Feature activation+0.431
from
Token from
Feature activation+1.161
within
Token within
Feature activation+0.552
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
as
Token as
Feature activation+1.674
he
Token he
Feature activation+0.000
ran
Token ran
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.255 - 1.569
CONTAINS 0.038%

read
Token read
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
fascinating
Token fascinating
Feature activation+1.523
when
Token when
Feature activation+1.815
you
Token you
Feature activation+0.598
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
moving
Token moving
Feature activation+0.000
towards
Token towards
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
green
Token green
Feature activation+0.388
,
Token,
Feature activation+1.266
stable
Token stable
Feature activation+1.018
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
information
Token information
Feature activation+0.000
collected
Token collected
Feature activation+1.365
by
Token by
Feature activation+1.089
military
Token military
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
and
Token and
Feature activation+0.000
by
Token by
Feature activation+0.690
-
Token-
Feature activation+0.075
oriented
Tokenoriented
Feature activation+0.709
,
Token,
Feature activation+1.219
we
Token we
Feature activation+0.386
're
Token're
Feature activation+0.000
concerned
Token concerned
Feature activation+1.302
that
Token that
Feature activation+0.155
the
Token the
Feature activation+0.000
variability
Token variability
Feature activation+0.000
of
Token of
Feature activation+0.000
tips
Token tips
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
coverage
Token coverage
Feature activation+1.401
:
Token:
Feature activation+0.589
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Y
TokenY
Feature activation+0.000
ERE
TokenERE
Feature activation+0.000
V
TokenV
Feature activation+0.000

INTERVAL 0.942 - 1.255
CONTAINS 0.049%

complaint
Token complaint
Feature activation+0.000
called
Token called
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.089
caution
Token caution
Feature activation+1.455
when
Token when
Feature activation+1.171
airing
Token airing
Feature activation+0.000
commercials
Token commercials
Feature activation+0.000
during
Token during
Feature activation+0.174
times
Token times
Feature activation+0.000
when
Token when
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
presidential
Token presidential
Feature activation+0.821
:
Token:
Feature activation+0.959
better
Token better
Feature activation+0.000
informed
Token informed
Feature activation+0.376
on
Token on
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.188
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
greater
Token greater
Feature activation+0.000
role
Token role
Feature activation+1.116
for
Token for
Feature activation+0.700
the
Token the
Feature activation+0.546
IMF
Token IMF
Feature activation+0.000
's
Token's
Feature activation+0.000
Special
Token Special
Feature activation+0.000
to
Token to
Feature activation+0.000
zero
Token zero
Feature activation+0.000
;
Token;
Feature activation+0.000
what
Token what
Feature activation+0.000
more
Token more
Feature activation+0.000
can
Token can
Feature activation+1.213
we
Token we
Feature activation+0.525
do
Token do
Feature activation+0.504
?"
Token?"
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
surreal
Token surreal
Feature activation+1.133
:
Token:
Feature activation+0.386
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Asked
TokenAsked
Feature activation+0.000
whether
Token whether
Feature activation+0.000

INTERVAL 0.628 - 0.942
CONTAINS 0.069%

Whit
Token Whit
Feature activation+0.000
ewater
Tokenewater
Feature activation+0.000
,
Token,
Feature activation+0.465
WI
Token WI
Feature activation+0.000
PD
Token PD
Feature activation+0.000
here
Token here
Feature activation+0.775
.)
Token.)
Feature activation+0.071
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
now
Token now
Feature activation+0.000
documents
Token documents
Feature activation+0.000
and
Token and
Feature activation+0.000
find
Token find
Feature activation+0.000
more
Token more
Feature activation+0.000
interesting
Token interesting
Feature activation+2.182
stories
Token stories
Feature activation+0.794
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
it
Token it
Feature activation+0.000
!
Token!
Feature activation+0.000
But
Token But
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.781
he
Token he
Feature activation+0.094
was
Token was
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
Y
TokenY
Feature activation+0.000
with
Token with
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.034
offer
Token offer
Feature activation+0.915
the
Token the
Feature activation+0.712
Peter
Token Peter
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
and
Token and
Feature activation+0.000
J
Token J
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
specific
Token specific
Feature activation+1.220
sense
Token sense
Feature activation+0.699
,
Token,
Feature activation+0.256
karma
Token karma
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
component
Token component
Feature activation+0.000

INTERVAL 0.314 - 0.628
CONTAINS 0.117%

for
Token for
Feature activation+0.000
about
Token about
Feature activation+0.000
30
Token 30
Feature activation+0.000
more
Token more
Feature activation+0.000
seconds
Token seconds
Feature activation+2.345
(
Token (
Feature activation+0.326
this
Tokenthis
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
entirety
Token entirety
Feature activation+0.000
of
Token of
Feature activation+0.000
-
Token-
Feature activation+0.000
agent
Tokenagent
Feature activation+0.000
tracker
Token tracker
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
...
Token...
Feature activation+0.500
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
console
Token console
Feature activation+0.000
side
Token side
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.579
a
Token a
Feature activation+0.983
pillar
Token pillar
Feature activation+0.000
approach
Token approach
Feature activation+0.033
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
ro
Token ro
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.314
voters
Token voters
Feature activation+0.000
in
Token in
Feature activation+0.000
provinces
Token provinces
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
market
Token market
Feature activation+0.000
cap
Token cap
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
could
Token could
Feature activation+0.351
reach
Token reach
Feature activation+0.108
as
Token as
Feature activation+0.405
oppose
Token oppose
Feature activation+0.000
to
Token to
Feature activation+0.000
following
Token following
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000

INTERVAL 0.000 - 0.314
CONTAINS 99.672%

that
Token that
Feature activation+0.000
on
Token on
Feature activation+0.000
April
Token April
Feature activation+0.000
20
Token 20
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
safety
Token safety
Feature activation+0.000
parameters
Token parameters
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
enforced
Token enforced
Feature activation+0.000
potentially
Token potentially
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
team
Token team
Feature activation+0.000
ever
Token ever
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
argument
Token argument
Feature activation+0.000
that
Token that
Feature activation+0.000
gained
Token gained
Feature activation+0.000
steam
Token steam
Feature activation+0.000
hand
Token hand
Feature activation+0.000
-
Token-
Feature activation+0.000
tun
Tokentun
Feature activation+0.000
ing
Tokening
Feature activation+0.000
CONFIG
Token CONFIG
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
YS
TokenYS
Feature activation+0.000
and
Token and
Feature activation+0.000
AUT
Token AUT
Feature activation+0.000
O
TokenO
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.000
tax
Token tax
Feature activation+0.000
credits
Token credits
Feature activation+0.000
for
Token for
Feature activation+0.000
qualifying
Token qualifying
Feature activation+0.000
homeowners
Token homeowners
Feature activation+0.000
and
Token and
Feature activation+0.000
doctrine
Token doctrine
Feature activation+0.000
:
Token:
Feature activation+0.000
any
Token any
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
universal
Tokenuniversal
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
religious
Token religious
Feature activation+0.000
belief
Token belief
Feature activation+0.000
that
Token that
Feature activation+0.000
requires
Token requires
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 H3.11: (feature 5633)

TOP ACTIVATIONS
MAX = 4.686

its
Token its
Feature activation+0.148
January
Token January
Feature activation+0.927
8
Token 8
Feature activation+0.000
front
Token front
Feature activation+0.000
page
Token page
Feature activation+0.000
:
Token:
Feature activation+4.686
Ċ
TokenĊ
Feature activation+0.319
Ċ
TokenĊ
Feature activation+0.140
Right
TokenRight
Feature activation+0.000
on
Token on
Feature activation+0.000
!
Token!
Feature activation+0.000
URL
Token URL
Feature activation+0.159
into
Token into
Feature activation+0.000
your
Token your
Feature activation+0.000
web
Token web
Feature activation+0.000
browser
Token browser
Feature activation+0.000
:
Token:
Feature activation+4.558
Ċ
TokenĊ
Feature activation+0.847
Ċ
TokenĊ
Feature activation+0.501
https
Tokenhttps
Feature activation+0.000
://
Token://
Feature activation+0.000
www
Tokenwww
Feature activation+0.000
bl
Token bl
Feature activation+0.000
urb
Tokenurb
Feature activation+0.000
(
Token (
Feature activation+1.185
emphasis
Tokenemphasis
Feature activation+0.000
mine
Token mine
Feature activation+0.000
):
Token):
Feature activation+4.556
Ċ
TokenĊ
Feature activation+0.633
Ċ
TokenĊ
Feature activation+0.219
Virginia
TokenVirginia
Feature activation+0.000
Panel
Token Panel
Feature activation+0.000
Releases
Token Releases
Feature activation+0.000
and
Token and
Feature activation+0.000
run
Token run
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
command
Token command
Feature activation+2.231
:
Token:
Feature activation+4.435
Ċ
TokenĊ
Feature activation+1.428
Ċ
TokenĊ
Feature activation+0.989
./
Token./
Feature activation+0.000
man
Tokenman
Feature activation+0.000
age
Tokenage
Feature activation+0.000
the
Token the
Feature activation+2.735
result
Token result
Feature activation+3.327
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+0.176
:
Token:
Feature activation+4.432
Total
Token Total
Feature activation+0.000
Number
Token Number
Feature activation+0.000
Voting
Token Voting
Feature activation+0.000
................
Token................
Feature activation+0.039
.......
Token.......
Feature activation+0.000
pending
Token pending
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
states
Token states
Feature activation+3.198
:
Token:
Feature activation+4.368
Ċ
TokenĊ
Feature activation+0.443
Ċ
TokenĊ
Feature activation+0.357
Alabama
TokenAlabama
Feature activation+0.000
:
Token:
Feature activation+0.000
25
Token 25
Feature activation+0.000
you
Token you
Feature activation+0.000
define
Token define
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
configuration
Token configuration
Feature activation+0.000
:
Token:
Feature activation+4.338
1
Token 1
Feature activation+0.000
2
Token 2
Feature activation+0.000
3
Token 3
Feature activation+0.000
4
Token 4
Feature activation+0.000
5
Token 5
Feature activation+0.000
delegation
Token delegation
Feature activation+0.000
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+0.000
WC
Token WC
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
:
Token:
Feature activation+4.304
Okay
TokenOkay
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
to
Token to
Feature activation+0.000
translate
Token translate
Feature activation+0.000
is
Token is
Feature activation+0.583
the
Token the
Feature activation+2.323
roll
Token roll
Feature activation+0.833
call
Token call
Feature activation+0.000
vote
Token vote
Feature activation+0.894
:
Token:
Feature activation+4.117
Y
Token Y
Feature activation+0.193
AB
Token AB
Feature activation+0.000
RAM
TokenRAM
Feature activation+0.000
S
TokenS
Feature activation+0.000
Y
Token Y
Feature activation+0.000
to
Token to
Feature activation+0.000
qualify
Token qualify
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
endorsement
Token endorsement
Feature activation+0.499
:
Token:
Feature activation+4.018
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
afford
Token afford
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
series
Token series
Feature activation+2.753
of
Token of
Feature activation+0.567
perspectives
Token perspectives
Feature activation+0.519
:
Token:
Feature activation+3.998
American
Token American
Feature activation+0.000
military
Token military
Feature activation+0.000
members
Token members
Feature activation+0.000
,
Token,
Feature activation+0.000
people
Token people
Feature activation+0.000
states
Token states
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
important
Token important
Feature activation+1.867
details
Token details
Feature activation+0.206
:
Token:
Feature activation+3.975
Ċ
TokenĊ
Feature activation+0.639
Ċ
TokenĊ
Feature activation+0.417
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
HA
TokenHA
Feature activation+0.000
s
Tokens
Feature activation+0.000
features
Token features
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.202
:
Token:
Feature activation+3.962
âĢ
Token âĢ
Feature activation+0.149
ľ
Tokenľ
Feature activation+0.000
Xbox
TokenXbox
Feature activation+0.527
Live
Token Live
Feature activation+0.083
Gold
Token Gold
Feature activation+0.000
following
Token following
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.470
and
Token and
Feature activation+0.000
registration
Token registration
Feature activation+0.101
instructions
Token instructions
Feature activation+0.000
:
Token:
Feature activation+3.932
Ċ
TokenĊ
Feature activation+0.203
Ċ
TokenĊ
Feature activation+0.156
Works
TokenWorks
Feature activation+0.000
hops
Tokenhops
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
activities
Token activities
Feature activation+3.006
for
Token for
Feature activation+1.080
your
Token your
Feature activation+0.061
pet
Token pet
Feature activation+0.000
!
Token!
Feature activation+3.060
Ċ
TokenĊ
Feature activation+3.859
Ċ
TokenĊ
Feature activation+2.986
Many
TokenMany
Feature activation+0.000
loving
Token loving
Feature activation+0.000
pet
Token pet
Feature activation+0.000
owners
Token owners
Feature activation+0.000
following
Token following
Feature activation+0.054
e
Token e
Feature activation+0.986
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+1.964
message
Token message
Feature activation+2.210
:
Token:
Feature activation+3.856
Ċ
TokenĊ
Feature activation+0.135
Ċ
TokenĊ
Feature activation+0.017
Notice
TokenNotice
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
or
Token or
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+3.848
Ċ
TokenĊ
Feature activation+0.794
Ċ
TokenĊ
Feature activation+0.475
--
Token--
Feature activation+0.000
Run
TokenRun
Feature activation+0.000
stories
Token stories
Feature activation+0.000
then
Token then
Feature activation+0.000
execute
Token execute
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
code
Token code
Feature activation+1.655
.
Token.
Feature activation+3.758
This
Token This
Feature activation+0.136
will
Token will
Feature activation+0.000
affect
Token affect
Feature activation+0.000
instances
Token instances
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.170
every
Token every
Feature activation+1.213
ministerial
Token ministerial
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
letter
Token letter
Feature activation+0.000
:
Token:
Feature activation+3.721
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
following
Token following
Feature activation+0.000
statements
Token statements
Feature activation+2.069
remain
Token remain
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
accurate
Token accurate
Feature activation+2.516
:
Token:
Feature activation+3.688
Ċ
TokenĊ
Feature activation+0.079
Ċ
TokenĊ
Feature activation+0.029
"
Token"
Feature activation+0.000
Pat
TokenPat
Feature activation+0.000
ients
Tokenients
Feature activation+0.000

Top DFA by src position
MAX = 5.290

,
Token,
Feature activation+0.037
Top resid features:
USA
Token USA
Feature activation+0.001
Top resid features:
Today
Token Today
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
following
Token following
Feature activation+5.270
Top resid features:
information
Token information
Feature activation+0.064
Top resid features:
on
Token on
Feature activation+0.010
Top resid features:
its
Token its
Feature activation+0.039
Top resid features:
January
Token January
Feature activation+0.045
Top resid features:
8
Token 8
Feature activation-0.000
Top resid features:
com
Tokencom
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
just
Token just
Feature activation+0.014
Top resid features:
type
Token type
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
following
Token following
Feature activation+5.290
Top resid features:
URL
Token URL
Feature activation+0.057
Top resid features:
into
Token into
Feature activation+0.093
Top resid features:
your
Token your
Feature activation+0.042
Top resid features:
web
Token web
Feature activation-0.056
Top resid features:
browser
Token browser
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
find
Token find
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
following
Token following
Feature activation+5.145
Top resid features:
bl
Token bl
Feature activation+0.030
Top resid features:
urb
Tokenurb
Feature activation+0.043
Top resid features:
(
Token (
Feature activation+0.053
Top resid features:
emphasis
Tokenemphasis
Feature activation-0.060
Top resid features:
mine
Token mine
Feature activation+0.073
Top resid features:
tr
Tokentr
Feature activation+0.003
Top resid features:
acker
Tokenacker
Feature activation-0.008
Top resid features:
and
Token and
Feature activation-0.021
Top resid features:
run
Token run
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
following
Token following
Feature activation+5.070
Top resid features:
command
Token command
Feature activation+0.104
Top resid features:
:
Token:
Feature activation+0.169
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
./
Token./
Feature activation+0.000
Top resid features:
p
Token p
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
m
Tokenm
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
The
Token The
Feature activation+0.040
Top resid features:
following
Token following
Feature activation+4.969
Top resid features:
is
Token is
Feature activation+0.100
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
result
Token result
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.093
Top resid features:
bills
Token bills
Feature activation-0.034
Top resid features:
still
Token still
Feature activation+0.012
Top resid features:
pending
Token pending
Feature activation-0.020
Top resid features:
include
Token include
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.069
Top resid features:
following
Token following
Feature activation+4.984
Top resid features:
states
Token states
Feature activation+0.115
Top resid features:
:
Token:
Feature activation+0.126
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Alabama
TokenAlabama
Feature activation+0.000
Top resid features:
>
Token>
Feature activation+0.002
Top resid features:
if
Token if
Feature activation-0.011
Top resid features:
you
Token you
Feature activation-0.002
Top resid features:
define
Token define
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
following
Token following
Feature activation+4.806
Top resid features:
configuration
Token configuration
Feature activation+0.069
Top resid features:
:
Token:
Feature activation+0.214
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
State
Token State
Feature activation+0.001
Top resid features:
Department
Token Department
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
The
Token The
Feature activation-0.000
Top resid features:
following
Token following
Feature activation+5.012
Top resid features:
is
Token is
Feature activation+0.037
Top resid features:
an
Token an
Feature activation+0.031
Top resid features:
email
Token email
Feature activation+0.025
Top resid features:
from
Token from
Feature activation+0.014
Top resid features:
Terry
Token Terry
Feature activation+0.019
Top resid features:
voting
Token voting
Feature activation-0.004
Top resid features:
........
Token........
Feature activation-0.008
Top resid features:
......
Token......
Feature activation-0.009
Top resid features:
9
Token 9
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.087
Top resid features:
following
Token following
Feature activation+4.791
Top resid features:
is
Token is
Feature activation+0.107
Top resid features:
the
Token the
Feature activation+0.186
Top resid features:
roll
Token roll
Feature activation+0.043
Top resid features:
call
Token call
Feature activation-0.011
Top resid features:
vote
Token vote
Feature activation-0.095
Top resid features:
even
Token even
Feature activation-0.023
Top resid features:
going
Token going
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
qualify
Token qualify
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.068
Top resid features:
following
Token following
Feature activation+4.680
Top resid features:
endorsement
Token endorsement
Feature activation+0.082
Top resid features:
:
Token:
Feature activation+0.188
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
Nov
Token Nov
Feature activation+0.025
Top resid features:
ick
Tokenick
Feature activation-0.003
Top resid features:
are
Token are
Feature activation+0.050
Top resid features:
balancing
Token balancing
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
following
Token following
Feature activation+4.616
Top resid features:
series
Token series
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+0.051
Top resid features:
perspectives
Token perspectives
Feature activation-0.048
Top resid features:
:
Token:
Feature activation+0.196
Top resid features:
American
Token American
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
It
Token It
Feature activation+0.058
Top resid features:
also
Token also
Feature activation+0.027
Top resid features:
states
Token states
Feature activation+0.084
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
following
Token following
Feature activation+4.632
Top resid features:
important
Token important
Feature activation-0.002
Top resid features:
details
Token details
Feature activation-0.105
Top resid features:
:
Token:
Feature activation+0.155
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
features
Token features
Feature activation+0.037
Top resid features:
with
Token with
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
following
Token following
Feature activation+4.585
Top resid features:
:
Token:
Feature activation+0.082
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Xbox
TokenXbox
Feature activation+0.000
Top resid features:
Live
Token Live
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
please
Token please
Feature activation+0.038
Top resid features:
review
Token review
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
following
Token following
Feature activation+4.426
Top resid features:
guidelines
Token guidelines
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.091
Top resid features:
registration
Token registration
Feature activation-0.008
Top resid features:
instructions
Token instructions
Feature activation+0.013
Top resid features:
:
Token:
Feature activation+0.182
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
up
Token up
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
following
Token following
Feature activation+4.578
Top resid features:
activities
Token activities
Feature activation+0.049
Top resid features:
for
Token for
Feature activation+0.030
Top resid features:
your
Token your
Feature activation+0.008
Top resid features:
pet
Token pet
Feature activation+0.002
Top resid features:
!
Token!
Feature activation+0.088
Top resid features:
Last
TokenLast
Feature activation-0.038
Top resid features:
week
Token week
Feature activation+0.054
Top resid features:
we
Token we
Feature activation+0.045
Top resid features:
received
Token received
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
following
Token following
Feature activation+4.476
Top resid features:
e
Token e
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
mail
Tokenmail
Feature activation+0.022
Top resid features:
message
Token message
Feature activation+0.096
Top resid features:
:
Token:
Feature activation+0.084
Top resid features:
one
Token one
Feature activation+0.021
Top resid features:
or
Token or
Feature activation+0.031
Top resid features:
more
Token more
Feature activation-0.016
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
following
Token following
Feature activation+4.430
Top resid features:
:
Token:
Feature activation+0.104
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
--
Token--
Feature activation+0.000
Top resid features:
Run
TokenRun
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
then
Token then
Feature activation+0.024
Top resid features:
execute
Token execute
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.143
Top resid features:
following
Token following
Feature activation+4.181
Top resid features:
code
Token code
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.156
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
affect
Token affect
Feature activation+0.000
Top resid features:
October
Token October
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
He
Token He
Feature activation+0.045
Top resid features:
included
Token included
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
following
Token following
Feature activation+4.355
Top resid features:
paragraph
Token paragraph
Feature activation-0.019
Top resid features:
in
Token in
Feature activation+0.049
Top resid features:
every
Token every
Feature activation-0.038
Top resid features:
ministerial
Token ministerial
Feature activation+0.063
Top resid features:
mandate
Token mandate
Feature activation+0.026
Top resid features:
last
Token last
Feature activation+0.006
Top resid features:
year
Token year
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
so
Token so
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
following
Token following
Feature activation+4.397
Top resid features:
statements
Token statements
Feature activation-0.038
Top resid features:
remain
Token remain
Feature activation+0.072
Top resid features:
entirely
Token entirely
Feature activation-0.001
Top resid features:
accurate
Token accurate
Feature activation+0.074
Top resid features:
:
Token:
Feature activation+0.133
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.05

Head 2: 0.04

Head 3: 0.02

Head 4: 0.04

Head 5: 0.07

Head 6: 0.05

Head 7: 0.05

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.50

Positive logits

:(1.73

:-1.73

:"1.47

":[1.45

*:1.43

FIG1.34

apply1.32

applies1.31

viz1.28

":[{"1.28

icipated1.27

:\1.26

RGB1.24

namely1.24

names1.22

ACTIONS1.22

Statement1.21

,—1.21

embodiments1.21

^^^^1.19

Negative logits

Trafford-1.44

Downloadha-1.32

Kinder-1.32

database-1.29

aith-1.28

jong-1.25

waukee-1.24

utenberg-1.24

eter-1.22

inosaur-1.22

erver-1.22

trak-1.18

atown-1.17

nexus-1.17

ndra-1.17

ionage-1.16

imeter-1.15

ayette-1.15

research-1.13

iddles-1.13

INTERVAL 4.217 - 4.686
CONTAINS 0.001%

pending
Token pending
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
states
Token states
Feature activation+3.198
:
Token:
Feature activation+4.368
Ċ
TokenĊ
Feature activation+0.443
Ċ
TokenĊ
Feature activation+0.357
Alabama
TokenAlabama
Feature activation+0.000
:
Token:
Feature activation+0.000
25
Token 25
Feature activation+0.000
you
Token you
Feature activation+0.000
define
Token define
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
configuration
Token configuration
Feature activation+0.000
:
Token:
Feature activation+4.338
1
Token 1
Feature activation+0.000
2
Token 2
Feature activation+0.000
3
Token 3
Feature activation+0.000
4
Token 4
Feature activation+0.000
5
Token 5
Feature activation+0.000
and
Token and
Feature activation+0.000
run
Token run
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
command
Token command
Feature activation+2.231
:
Token:
Feature activation+4.435
Ċ
TokenĊ
Feature activation+1.428
Ċ
TokenĊ
Feature activation+0.989
./
Token./
Feature activation+0.000
man
Tokenman
Feature activation+0.000
age
Tokenage
Feature activation+0.000
its
Token its
Feature activation+0.148
January
Token January
Feature activation+0.927
8
Token 8
Feature activation+0.000
front
Token front
Feature activation+0.000
page
Token page
Feature activation+0.000
:
Token:
Feature activation+4.686
Ċ
TokenĊ
Feature activation+0.319
Ċ
TokenĊ
Feature activation+0.140
Right
TokenRight
Feature activation+0.000
on
Token on
Feature activation+0.000
!
Token!
Feature activation+0.000
delegation
Token delegation
Feature activation+0.000
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+0.000
WC
Token WC
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
:
Token:
Feature activation+4.304
Okay
TokenOkay
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
to
Token to
Feature activation+0.000
translate
Token translate
Feature activation+0.000

INTERVAL 3.748 - 4.217
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
features
Token features
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.202
:
Token:
Feature activation+3.962
âĢ
Token âĢ
Feature activation+0.149
ľ
Tokenľ
Feature activation+0.000
Xbox
TokenXbox
Feature activation+0.527
Live
Token Live
Feature activation+0.083
Gold
Token Gold
Feature activation+0.000
following
Token following
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.470
and
Token and
Feature activation+0.000
registration
Token registration
Feature activation+0.101
instructions
Token instructions
Feature activation+0.000
:
Token:
Feature activation+3.932
Ċ
TokenĊ
Feature activation+0.203
Ċ
TokenĊ
Feature activation+0.156
Works
TokenWorks
Feature activation+0.000
hops
Tokenhops
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
following
Token following
Feature activation+0.054
e
Token e
Feature activation+0.986
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+1.964
message
Token message
Feature activation+2.210
:
Token:
Feature activation+3.856
Ċ
TokenĊ
Feature activation+0.135
Ċ
TokenĊ
Feature activation+0.017
Notice
TokenNotice
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
or
Token or
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+3.848
Ċ
TokenĊ
Feature activation+0.794
Ċ
TokenĊ
Feature activation+0.475
--
Token--
Feature activation+0.000
Run
TokenRun
Feature activation+0.000
stories
Token stories
Feature activation+0.000
is
Token is
Feature activation+0.583
the
Token the
Feature activation+2.323
roll
Token roll
Feature activation+0.833
call
Token call
Feature activation+0.000
vote
Token vote
Feature activation+0.894
:
Token:
Feature activation+4.117
Y
Token Y
Feature activation+0.193
AB
Token AB
Feature activation+0.000
RAM
TokenRAM
Feature activation+0.000
S
TokenS
Feature activation+0.000
Y
Token Y
Feature activation+0.000

INTERVAL 3.280 - 3.748
CONTAINS 0.002%

following
Token following
Feature activation+0.000
statements
Token statements
Feature activation+2.069
remain
Token remain
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
accurate
Token accurate
Feature activation+2.516
:
Token:
Feature activation+3.688
Ċ
TokenĊ
Feature activation+0.079
Ċ
TokenĊ
Feature activation+0.029
"
Token"
Feature activation+0.000
Pat
TokenPat
Feature activation+0.000
ients
Tokenients
Feature activation+0.000
Tenth
Token Tenth
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
states
Token states
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.010
:
Token:
Feature activation+3.384
Ċ
TokenĊ
Feature activation+0.216
Ċ
TokenĊ
Feature activation+0.073
The
TokenThe
Feature activation+0.111
powers
Token powers
Feature activation+0.000
not
Token not
Feature activation+0.000
look
Token look
Feature activation+0.000
something
Token something
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+3.322
Ċ
TokenĊ
Feature activation+2.021
Ċ
TokenĊ
Feature activation+1.439
use
Tokenuse
Feature activation+0.000
std
Token std
Feature activation+0.000
::
Token::
Feature activation+0.000
in
Token in
Feature activation+0.170
every
Token every
Feature activation+1.213
ministerial
Token ministerial
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
letter
Token letter
Feature activation+0.000
:
Token:
Feature activation+3.721
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
or
Token or
Feature activation+0.000
your
Token your
Feature activation+0.000
provider
Token provider
Feature activation+0.000
asked
Token asked
Feature activation+0.000
for
Token for
Feature activation+0.000
:
Token:
Feature activation+3.490
In
Token In
Feature activation+0.000
patient
Tokenpatient
Feature activation+0.000
Hospital
Token Hospital
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.811 - 3.280
CONTAINS 0.001%

law
Token law
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
process
Token process
Feature activation+0.576
.
Token.
Feature activation+3.012
First
Token First
Feature activation+1.261
we
Token we
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
activities
Token activities
Feature activation+3.006
for
Token for
Feature activation+1.080
your
Token your
Feature activation+0.061
pet
Token pet
Feature activation+0.000
!
Token!
Feature activation+3.060
Ċ
TokenĊ
Feature activation+3.859
we
Token we
Feature activation+0.000
executed
Token executed
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
alter
Token alter
Feature activation+2.376
.
Token.
Feature activation+2.922
Ċ
TokenĊ
Feature activation+3.524
Ċ
TokenĊ
Feature activation+2.681
AL
TokenAL
Feature activation+0.000
TER
TokenTER
Feature activation+0.000
TABLE
Token TABLE
Feature activation+0.000
perpetrator
Token perpetrator
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+2.901
Following
TokenFollowing
Feature activation+0.000
Bond
Token Bond
Feature activation+0.268
's
Token's
Feature activation+0.057
arrest
Token arrest
Feature activation+0.000
,
Token,
Feature activation+0.386
for
Token for
Feature activation+1.080
your
Token your
Feature activation+0.061
pet
Token pet
Feature activation+0.000
!
Token!
Feature activation+3.060
Ċ
TokenĊ
Feature activation+3.859
Ċ
TokenĊ
Feature activation+2.986
Many
TokenMany
Feature activation+0.000
loving
Token loving
Feature activation+0.000
pet
Token pet
Feature activation+0.000
owners
Token owners
Feature activation+0.000
like
Token like
Feature activation+0.000

INTERVAL 2.343 - 2.811
CONTAINS 0.002%

them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Consider
Token Consider
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+2.668
Ċ
TokenĊ
Feature activation+1.591
Ċ
TokenĊ
Feature activation+1.101
@
Token@
Feature activation+0.000
rec
Tokenrec
Feature activation+0.000
ieved
Tokenieved
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.149
ľ
Tokenľ
Feature activation+0.000
Xbox
TokenXbox
Feature activation+0.527
Live
Token Live
Feature activation+0.083
Gold
Token Gold
Feature activation+0.000
members
Token members
Feature activation+2.425
with
Token with
Feature activation+0.000
Xbox
Token Xbox
Feature activation+0.000
One
Token One
Feature activation+0.000
can
Token can
Feature activation+0.000
experience
Token experience
Feature activation+0.000
then
Token then
Feature activation+0.000
we
Token we
Feature activation+0.000
executed
Token executed
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
alter
Token alter
Feature activation+2.376
.
Token.
Feature activation+2.922
Ċ
TokenĊ
Feature activation+3.524
Ċ
TokenĊ
Feature activation+2.681
AL
TokenAL
Feature activation+0.000
TER
TokenTER
Feature activation+0.000
released
Token released
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.997
statement
Token statement
Feature activation+2.588
Thursday
Token Thursday
Feature activation+1.642
:
Token:
Feature activation+2.772
"
Token "
Feature activation+0.000
My
TokenMy
Feature activation+0.000
thoughts
Token thoughts
Feature activation+0.000
and
Token and
Feature activation+0.000
prayers
Token prayers
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+2.567
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.532

INTERVAL 1.874 - 2.343
CONTAINS 0.002%

have
Token have
Feature activation+0.000
identified
Token identified
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
domain
Token domain
Feature activation+1.513
objects
Token objects
Feature activation+2.090
Ċ
TokenĊ
Feature activation+3.096
Ċ
TokenĊ
Feature activation+2.178
Organ
TokenOrgan
Feature activation+0.000
izer
Tokenizer
Feature activation+0.043
Att
Token Att
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
domain
Token domain
Feature activation+1.513
objects
Token objects
Feature activation+2.090
Ċ
TokenĊ
Feature activation+3.096
Ċ
TokenĊ
Feature activation+2.178
Organ
TokenOrgan
Feature activation+0.000
izer
Tokenizer
Feature activation+0.043
Att
Token Att
Feature activation+0.000
endants
Tokenendants
Feature activation+0.000
Events
Token Events
Feature activation+0.000
April
Token April
Feature activation+0.000
20
Token 20
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.255
safety
Token safety
Feature activation+0.907
parameters
Token parameters
Feature activation+1.928
will
Token will
Feature activation+1.310
be
Token be
Feature activation+0.595
enforced
Token enforced
Feature activation+0.590
:
Token:
Feature activation+3.670
-
Token -
Feature activation+0.000
people
Token people
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
.
Token.
Feature activation+1.660
Ċ
TokenĊ
Feature activation+2.605
Ċ
TokenĊ
Feature activation+1.969
141
Token141
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
British
Token British
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
statements
Token statements
Feature activation+2.069
remain
Token remain
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
accurate
Token accurate
Feature activation+2.516
:
Token:
Feature activation+3.688
Ċ
TokenĊ
Feature activation+0.079

INTERVAL 1.406 - 1.874
CONTAINS 0.004%

.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
one
Token one
Feature activation+0.083
.
Token.
Feature activation+1.678
Ċ
TokenĊ
Feature activation+1.593
Ċ
TokenĊ
Feature activation+0.775
To
TokenTo
Feature activation+0.000
get
Token get
Feature activation+0.000
their
Token their
Feature activation+0.000
your
Token your
Feature activation+0.000
game
Token game
Feature activation+0.000
console
Token console
Feature activation+0.000
as
Token as
Feature activation+0.000
follows
Token follows
Feature activation+0.000
:
Token:
Feature activation+1.542
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
default
Tokendefault
Feature activation+0.000
_
Token_
Feature activation+0.000
f
Tokenf
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
in
Token in
Feature activation+0.000
common
Token common
Feature activation+0.000
:
Token:
Feature activation+1.469
They
Token They
Feature activation+0.000
will
Token will
Feature activation+0.000
or
Token or
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.159
3
Token 3
Feature activation+1.734
phases
Token phases
Feature activation+0.058
:
Token:
Feature activation+3.414
Ċ
TokenĊ
Feature activation+0.039
Ċ
TokenĊ
Feature activation+0.000
Phase
TokenPhase
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
execute
Token execute
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
code
Token code
Feature activation+1.655
.
Token.
Feature activation+3.758
This
Token This
Feature activation+0.136
will
Token will
Feature activation+0.000
affect
Token affect
Feature activation+0.000
instances
Token instances
Feature activation+0.000

INTERVAL 0.937 - 1.406
CONTAINS 0.006%

article
Token article
Feature activation+0.000
included
Token included
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
quote
Token quote
Feature activation+1.341
,
Token,
Feature activation+1.395
which
Token which
Feature activation+0.113
IM
Token IM
Feature activation+0.000
O
TokenO
Feature activation+0.000
sums
Token sums
Feature activation+0.000
up
Token up
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
following
Token following
Feature activation+0.000
their
Token their
Feature activation+0.546
tradition
Token tradition
Feature activation+1.129
of
Token of
Feature activation+0.000
tink
Token tink
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
,
Token,
Feature activation+0.000
driving
Token driving
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
following
Token following
Feature activation+0.000
is
Token is
Feature activation+1.184
the
Token the
Feature activation+2.735
result
Token result
Feature activation+3.327
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+0.176
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.253
Ċ
TokenĊ
Feature activation+1.199
Ċ
TokenĊ
Feature activation+0.623
"
Token"
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
e
Tokene
Feature activation+0.000
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.122
day
Token day
Feature activation+1.322
,
Token,
Feature activation+1.545
saying
Token saying
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
workers
Token workers
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 0.469 - 0.937
CONTAINS 0.012%

used
Token used
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
tournament
Token tournament
Feature activation+0.000
.
Token.
Feature activation+1.556
We
Token We
Feature activation+0.656
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.000
not
Token not
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
has
Token has
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
following
Token following
Feature activation+0.000
the
Token the
Feature activation+0.000
practice
Token practice
Feature activation+0.000
.
Token.
Feature activation+0.649
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
USA
Token USA
Feature activation+0.000
Today
Token Today
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.784
information
Token information
Feature activation+3.004
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.148
January
Token January
Feature activation+0.927
8
Token 8
Feature activation+0.000
support
Token support
Feature activation+0.000
following
Token following
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.781
Ļ
TokenĻ
Feature activation+0.826
s
Tokens
Feature activation+0.381
congressional
Token congressional
Feature activation+0.000
address
Token address
Feature activation+0.024
Ċ
TokenĊ
Feature activation+0.081
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+2.005
Ċ
TokenĊ
Feature activation+1.827
Ċ
TokenĊ
Feature activation+1.038
In
TokenIn
Feature activation+0.502
the
Token the
Feature activation+0.000
early
Token early
Feature activation+0.000
nin
Token nin
Feature activation+0.000
eties
Tokeneties
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.469
CONTAINS 99.970%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Loud
Token Loud
Feature activation+0.000
oun
Tokenoun
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.000
Office
Token Office
Feature activation+0.000
is
Token is
Feature activation+0.000
alert
Token alert
Feature activation+0.000
ing
Tokening
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Carter
TokenCarter
Feature activation+0.000
:
Token:
Feature activation+0.000
"...
Token "...
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
,
Token,
Feature activation+0.000
<
Token <
Feature activation+0.000
h
Token h
Feature activation+0.000
1
Token1
Feature activation+0.000
>
Token >
Feature activation+0.000
Flask
Token Flask
Feature activation+0.000
Chart
Token Chart
Feature activation+0.000
.
Token.
Feature activation+0.000
js
Token js
Feature activation+0.000
<
Token <
Feature activation+0.000
/
Token /
Feature activation+0.000
h
Tokenh
Feature activation+0.000
meanwhile
Token meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
received
Token received
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
enough
Token enough
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
to
Token to
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
stock
Token stock
Feature activation+0.000
Sony
Token Sony
Feature activation+0.000
firmware
Token firmware
Feature activation+0.000
be
Token be
Feature activation+0.000
flashing
Token flashing
Feature activation+0.000
an
Token an
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H3.11: (feature 1687)

TOP ACTIVATIONS
MAX = 4.023

mother
Tokenmother
Feature activation+0.000
has
Token has
Feature activation+0.000
even
Token even
Feature activation+0.000
caught
Token caught
Feature activation+2.918
the
Token the
Feature activation+2.323
attention
Token attention
Feature activation+3.864
of
Token of
Feature activation+0.922
O
Token O
Feature activation+0.000
zzy
Tokenzzy
Feature activation+0.000
Os
Token Os
Feature activation+0.000
bourne
Tokenbourne
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
even
Token even
Feature activation+0.463
some
Token some
Feature activation+3.663
on
Token on
Feature activation+0.073
the
Token the
Feature activation+1.826
Tory
Token Tory
Feature activation+0.000
right
Token right
Feature activation+0.303
who
Token who
Feature activation+1.661
just
Token just
Feature activation+0.000
should
Token should
Feature activation+0.000
play
Token play
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.363
just
Token just
Feature activation+3.610
once
Token once
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
levels
Token levels
Feature activation+0.000
Even
Token Even
Feature activation+0.000
James
Token James
Feature activation+0.032
Earl
Token Earl
Feature activation+0.000
Jones
Token Jones
Feature activation+0.065
,
Token,
Feature activation+2.676
who
Token who
Feature activation+3.497
voiced
Token voiced
Feature activation+0.000
Darth
Token Darth
Feature activation+0.000
Vader
Token Vader
Feature activation+0.000
,
Token,
Feature activation+0.000
remembers
Token remembers
Feature activation+0.711
movement
Token movement
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
can
Token can
Feature activation+0.000
even
Token even
Feature activation+0.774
help
Token help
Feature activation+3.472
scientists
Token scientists
Feature activation+0.121
differentiate
Token differentiate
Feature activation+0.262
between
Token between
Feature activation+0.000
different
Token different
Feature activation+0.000
kinds
Token kinds
Feature activation+0.000
my
Token my
Feature activation+0.000
readers
Token readers
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
from
Token from
Feature activation+0.981
some
Token some
Feature activation+3.460
of
Token of
Feature activation+0.525
my
Token my
Feature activation+0.308
colleagues
Token colleagues
Feature activation+0.033
,
Token,
Feature activation+0.045
I
Token I
Feature activation+0.000
Dom
Token Dom
Feature activation+0.000
P
Token P
Feature activation+0.754
agn
Tokenagn
Feature activation+1.177
otti
Tokenotti
Feature activation+2.071
was
Token was
Feature activation+2.989
afraid
Token afraid
Feature activation+3.404
!
Token!
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
show
Token show
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
with
Token with
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+1.011
best
Token best
Feature activation+3.366
guns
Token guns
Feature activation+0.000
in
Token in
Feature activation+0.000
paint
Token paint
Feature activation+0.000
ball
Tokenball
Feature activation+0.000
.
Token.
Feature activation+0.164
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
at
Token at
Feature activation+1.490
every
Token every
Feature activation+3.302
open
Token open
Feature activation+0.000
24
Token 24
Feature activation+0.000
hours
Token hours
Feature activation+0.000
,
Token,
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.338
talk
Token talk
Feature activation+3.297
about
Token about
Feature activation+2.054
what
Token what
Feature activation+0.687
percentage
Token percentage
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
acknowledge
Token acknowledge
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
consider
Token consider
Feature activation+3.268
,
Token,
Feature activation+1.268
the
Token the
Feature activation+0.498
importance
Token importance
Feature activation+0.258
of
Token of
Feature activation+0.000
leading
Token leading
Feature activation+0.000
confused
Token confused
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.072
sure
Token sure
Feature activation+3.210
such
Token such
Feature activation+0.089
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.000
existed
Token existed
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
even
Token even
Feature activation+0.000
some
Token some
Feature activation+2.475
of
Token of
Feature activation+1.413
the
Token the
Feature activation+1.724
most
Token most
Feature activation+3.135
specific
Token specific
Feature activation+0.000
questions
Token questions
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.000
questions
Token questions
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.298
alluded
Token alluded
Feature activation+3.132
to
Token to
Feature activation+1.481
in
Token in
Feature activation+0.700
Batman
Token Batman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.266
Ļ
TokenĻ
Feature activation+0.064
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.047
going
Token going
Feature activation+3.084
to
Token to
Feature activation+1.901
qualify
Token qualify
Feature activation+1.743
the
Token the
Feature activation+0.036
following
Token following
Feature activation+0.311
endorsement
Token endorsement
Feature activation+0.000
of
Token of
Feature activation+0.000
software
Token software
Feature activation+0.000
are
Token are
Feature activation+0.000
even
Token even
Feature activation+0.082
able
Token able
Feature activation+2.769
to
Token to
Feature activation+3.044
automatically
Token automatically
Feature activation+0.953
spot
Token spot
Feature activation+0.098
and
Token and
Feature activation+0.000
highlight
Token highlight
Feature activation+0.590
these
Token these
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
noticing
Token noticing
Feature activation+3.043
what
Token what
Feature activation+0.443
these
Token these
Feature activation+0.000
rooms
Token rooms
Feature activation+0.000
look
Token look
Feature activation+0.000
like
Token like
Feature activation+0.000
his
Token his
Feature activation+0.000
YouTube
Token YouTube
Feature activation+0.000
videos
Token videos
Feature activation+0.000
can
Token can
Feature activation+0.000
even
Token even
Feature activation+0.467
be
Token be
Feature activation+3.042
critical
Token critical
Feature activation+0.640
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.055
own
Token own
Feature activation+0.448
theories
Token theories
Feature activation+0.000
my
Token my
Feature activation+0.000
whole
Token whole
Feature activation+0.000
life
Token life
Feature activation+0.000
to
Token to
Feature activation+0.000
even
Token even
Feature activation+0.000
be
Token be
Feature activation+3.033
in
Token in
Feature activation+1.788
this
Token this
Feature activation+2.003
predicament
Token predicament
Feature activation+0.000
.
Token.
Feature activation+0.107
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
even
Token even
Feature activation+0.461
be
Token be
Feature activation+3.028
given
Token given
Feature activation+1.743
a
Token a
Feature activation+1.912
wall
Token wall
Feature activation+0.000
of
Token of
Feature activation+0.000
links
Token links
Feature activation+0.000

Top DFA by src position
MAX = 5.067

Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
TokenThe
Feature activation-0.014
Top resid features:
Grind
Token Grind
Feature activation-0.027
Top resid features:
mother
Tokenmother
Feature activation+0.004
Top resid features:
has
Token has
Feature activation-0.024
Top resid features:
even
Token even
Feature activation+4.712
Top resid features:
caught
Token caught
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
attention
Token attention
Feature activation-0.012
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
O
Token O
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
parliament
Token parliament
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.068
Top resid features:
There
Token There
Feature activation-0.151
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
even
Token even
Feature activation+4.783
Top resid features:
some
Token some
Feature activation+0.035
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Tory
Token Tory
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
you
Token you
Feature activation+0.017
Top resid features:
just
Token just
Feature activation+0.022
Top resid features:
should
Token should
Feature activation+0.018
Top resid features:
play
Token play
Feature activation+0.002
Top resid features:
even
Token even
Feature activation+5.067
Top resid features:
if
Token if
Feature activation-0.618
Top resid features:
just
Token just
Feature activation-0.037
Top resid features:
once
Token once
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.016
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
former
Token former
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Even
Token Even
Feature activation+4.252
Top resid features:
James
Token James
Feature activation-0.019
Top resid features:
Earl
Token Earl
Feature activation-0.054
Top resid features:
Jones
Token Jones
Feature activation-0.093
Top resid features:
,
Token,
Feature activation+0.208
Top resid features:
who
Token who
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
movement
Token movement
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
They
Token They
Feature activation-0.156
Top resid features:
can
Token can
Feature activation+0.032
Top resid features:
even
Token even
Feature activation+4.352
Top resid features:
help
Token help
Feature activation+0.126
Top resid features:
scientists
Token scientists
Feature activation+0.000
Top resid features:
differentiate
Token differentiate
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
skepticism
Token skepticism
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
my
Token my
Feature activation+0.001
Top resid features:
readers
Token readers
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
even
Token even
Feature activation+4.042
Top resid features:
from
Token from
Feature activation+0.248
Top resid features:
some
Token some
Feature activation+0.041
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
colleagues
Token colleagues
Feature activation+0.000
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
head
Token head
Feature activation+0.006
Top resid features:
!
Token!
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Even
TokenEven
Feature activation+4.059
Top resid features:
Dom
Token Dom
Feature activation-0.019
Top resid features:
P
Token P
Feature activation-0.010
Top resid features:
agn
Tokenagn
Feature activation-0.017
Top resid features:
otti
Tokenotti
Feature activation-0.025
Top resid features:
was
Token was
Feature activation+0.164
Top resid features:
will
Token will
Feature activation-0.008
Top resid features:
hold
Token hold
Feature activation-0.004
Top resid features:
its
Token its
Feature activation-0.007
Top resid features:
own
Token own
Feature activation-0.054
Top resid features:
with
Token with
Feature activation-0.038
Top resid features:
even
Token even
Feature activation+4.234
Top resid features:
the
Token the
Feature activation+0.132
Top resid features:
best
Token best
Feature activation+0.002
Top resid features:
guns
Token guns
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
paint
Token paint
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
easy
Token easy
Feature activation+0.015
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
find
Token find
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
even
Token even
Feature activation+3.763
Top resid features:
at
Token at
Feature activation+0.290
Top resid features:
every
Token every
Feature activation+0.032
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
24
Token 24
Feature activation+0.000
Top resid features:
hours
Token hours
Feature activation+0.000
Top resid features:
let
Token let
Feature activation-0.157
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation-0.046
Top resid features:
not
Token not
Feature activation+0.071
Top resid features:
even
Token even
Feature activation+4.236
Top resid features:
talk
Token talk
Feature activation+0.053
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
percentage
Token percentage
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
wise
Token wise
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
acknowledge
Token acknowledge
Feature activation+0.043
Top resid features:
,
Token,
Feature activation-0.058
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
even
Token even
Feature activation+4.142
Top resid features:
consider
Token consider
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
importance
Token importance
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
being
Token being
Feature activation-0.041
Top resid features:
confused
Token confused
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.029
Top resid features:
not
Token not
Feature activation-0.052
Top resid features:
even
Token even
Feature activation+4.088
Top resid features:
sure
Token sure
Feature activation+0.056
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
document
Token document
Feature activation+0.000
Top resid features:
existed
Token existed
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.222
Top resid features:
-
Token-
Feature activation+0.042
Top resid features:
to
Tokento
Feature activation-0.003
Top resid features:
place
Token place
Feature activation-0.015
Top resid features:
for
Token for
Feature activation+0.029
Top resid features:
even
Token even
Feature activation+3.751
Top resid features:
some
Token some
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.173
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
most
Token most
Feature activation-0.022
Top resid features:
specific
Token specific
Feature activation+0.000
Top resid features:
or
Tokenor
Feature activation-0.001
Top resid features:
ro
Tokenro
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.028
Top resid features:
which
Tokenwhich
Feature activation-0.059
Top resid features:
was
Token was
Feature activation-0.020
Top resid features:
even
Token even
Feature activation+4.037
Top resid features:
alluded
Token alluded
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Batman
Token Batman
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
We
TokenWe
Feature activation-0.148
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
re
Tokenre
Feature activation+0.151
Top resid features:
not
Token not
Feature activation-0.063
Top resid features:
even
Token even
Feature activation+4.018
Top resid features:
going
Token going
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
qualify
Token qualify
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:
Recent
TokenRecent
Feature activation-0.019
Top resid features:
versions
Token versions
Feature activation-0.026
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
software
Token software
Feature activation-0.030
Top resid features:
are
Token are
Feature activation+0.077
Top resid features:
even
Token even
Feature activation+3.671
Top resid features:
able
Token able
Feature activation+0.085
Top resid features:
to
Token to
Feature activation+0.100
Top resid features:
automatically
Token automatically
Feature activation+0.000
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
We
Token We
Feature activation-0.103
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
re
Tokenre
Feature activation+0.181
Top resid features:
not
Token not
Feature activation-0.036
Top resid features:
even
Token even
Feature activation+3.940
Top resid features:
noticing
Token noticing
Feature activation-0.005
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
rooms
Token rooms
Feature activation+0.000
Top resid features:
look
Token look
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
YouTube
Token YouTube
Feature activation+0.003
Top resid features:
videos
Token videos
Feature activation-0.007
Top resid features:
can
Token can
Feature activation-0.090
Top resid features:
even
Token even
Feature activation+3.941
Top resid features:
be
Token be
Feature activation+0.069
Top resid features:
critical
Token critical
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
my
Token my
Feature activation-0.087
Top resid features:
whole
Token whole
Feature activation-0.008
Top resid features:
life
Token life
Feature activation-0.073
Top resid features:
to
Token to
Feature activation-0.041
Top resid features:
even
Token even
Feature activation+4.026
Top resid features:
be
Token be
Feature activation+0.099
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
predicament
Token predicament
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
sources
Token sources
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
you
Token you
Feature activation-0.171
Top resid features:
might
Token might
Feature activation+0.019
Top resid features:
even
Token even
Feature activation+3.942
Top resid features:
be
Token be
Feature activation+0.054
Top resid features:
given
Token given
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
wall
Token wall
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.05

Head 2: 0.07

Head 3: 0.03

Head 4: 0.02

Head 5: 0.05

Head 6: 0.10

Head 7: 0.03

Head 8: 0.04

Head 9: 0.05

Head 10: 0.05

Head 11: 0.50

Positive logits

perty1.52

aminer1.48

tein1.47

��1.46

yip1.45

imates1.44

avorite1.38

agi1.35

eter1.35

etimes1.32

ppers1.32

nodd1.26

nered1.25

slightest1.24

ulent1.24

hire1.23

earcher1.22

bered1.22

mite1.21

anuts1.20

Negative logits

along-1.36

imperative-1.28

essa-1.17

Commerce-1.17

Dw-1.13

Kub-1.12

Kong-1.09

emphasis-1.05

folio-1.04

illustration-1.02

concent-1.02

Redmond-1.00

Recommend-1.00

awaits-0.99

Connector-0.99

:\-0.99

south-0.99

tackle-0.98

Responsibility-0.98

sweeps-0.98

INTERVAL 3.621 - 4.023
CONTAINS 0.000%

mother
Tokenmother
Feature activation+0.000
has
Token has
Feature activation+0.000
even
Token even
Feature activation+0.000
caught
Token caught
Feature activation+2.918
the
Token the
Feature activation+2.323
attention
Token attention
Feature activation+3.864
of
Token of
Feature activation+0.922
O
Token O
Feature activation+0.000
zzy
Tokenzzy
Feature activation+0.000
Os
Token Os
Feature activation+0.000
bourne
Tokenbourne
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
even
Token even
Feature activation+0.463
some
Token some
Feature activation+3.663
on
Token on
Feature activation+0.073
the
Token the
Feature activation+1.826
Tory
Token Tory
Feature activation+0.000
right
Token right
Feature activation+0.303
who
Token who
Feature activation+1.661

INTERVAL 3.218 - 3.621
CONTAINS 0.001%

Dom
Token Dom
Feature activation+0.000
P
Token P
Feature activation+0.754
agn
Tokenagn
Feature activation+1.177
otti
Tokenotti
Feature activation+2.071
was
Token was
Feature activation+2.989
afraid
Token afraid
Feature activation+3.404
!
Token!
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
show
Token show
Feature activation+0.000
movement
Token movement
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
can
Token can
Feature activation+0.000
even
Token even
Feature activation+0.774
help
Token help
Feature activation+3.472
scientists
Token scientists
Feature activation+0.121
differentiate
Token differentiate
Feature activation+0.262
between
Token between
Feature activation+0.000
different
Token different
Feature activation+0.000
kinds
Token kinds
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.338
talk
Token talk
Feature activation+3.297
about
Token about
Feature activation+2.054
what
Token what
Feature activation+0.687
percentage
Token percentage
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
with
Token with
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+1.011
best
Token best
Feature activation+3.366
guns
Token guns
Feature activation+0.000
in
Token in
Feature activation+0.000
paint
Token paint
Feature activation+0.000
ball
Tokenball
Feature activation+0.000
.
Token.
Feature activation+0.164
just
Token just
Feature activation+0.000
should
Token should
Feature activation+0.000
play
Token play
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.363
just
Token just
Feature activation+3.610
once
Token once
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
levels
Token levels
Feature activation+0.000

INTERVAL 2.816 - 3.218
CONTAINS 0.004%

then
Token then
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.276
Ļ
TokenĻ
Feature activation+0.136
s
Tokens
Feature activation+0.000
just
Token just
Feature activation+3.020
a
Token a
Feature activation+0.000
box
Token box
Feature activation+0.000
to
Token to
Feature activation+0.000
haul
Token haul
Feature activation+0.000
them
Token them
Feature activation+0.000
for
Token for
Feature activation+0.000
even
Token even
Feature activation+0.000
some
Token some
Feature activation+2.475
of
Token of
Feature activation+1.413
the
Token the
Feature activation+1.724
most
Token most
Feature activation+3.135
specific
Token specific
Feature activation+0.000
questions
Token questions
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.000
questions
Token questions
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
Philip
Token Philip
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.206
has
Token has
Feature activation+1.162
a
Token a
Feature activation+2.899
shrine
Token shrine
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.930
in
Token in
Feature activation+0.145
his
Token his
Feature activation+0.000
honor
Token honor
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
described
Token described
Feature activation+0.000
even
Token even
Feature activation+0.000
by
Token by
Feature activation+3.007
her
Token her
Feature activation+0.633
supporters
Token supporters
Feature activation+1.560
in
Token in
Feature activation+0.367
male
Token male
Feature activation+0.687
and
Token and
Feature activation+0.000
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.893
pick
Token pick
Feature activation+0.801
iest
Tokeniest
Feature activation+2.974
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.455
,
Token,
Feature activation+0.097
to
Token to
Feature activation+0.000
foods
Token foods
Feature activation+0.000

INTERVAL 2.414 - 2.816
CONTAINS 0.005%

,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
even
Token even
Feature activation+0.592
be
Token be
Feature activation+2.685
dead
Token dead
Feature activation+0.880
.
Token.
Feature activation+0.028
6
Token6
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
even
Token even
Feature activation+0.000
got
Token got
Feature activation+2.679
lucky
Token lucky
Feature activation+2.784
enough
Token enough
Feature activation+1.452
to
Token to
Feature activation+0.289
catch
Token catch
Feature activation+0.556
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
even
Token even
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+2.748
with
Token with
Feature activation+0.832
all
Token all
Feature activation+0.283
its
Token its
Feature activation+0.000
problems
Token problems
Feature activation+0.000
,
Token,
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
on
Token on
Feature activation+1.275
a
Token a
Feature activation+2.663
Sea
Token Sea
Feature activation+0.000
-
Token-
Feature activation+0.000
D
TokenD
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
,
Token,
Feature activation+0.785
The
Token The
Feature activation+0.720
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.570
is
Token is
Feature activation+2.828
exploring
Token exploring
Feature activation+2.703
challenging
Token challenging
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.012 - 2.414
CONTAINS 0.009%

Key
Token Key
Feature activation+0.000
West
Token West
Feature activation+0.000
even
Token even
Feature activation+0.000
claims
Token claims
Feature activation+1.665
to
Token to
Feature activation+1.149
maintain
Token maintain
Feature activation+2.391
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.115
army
Token army
Feature activation+0.000
and
Token and
Feature activation+0.000
navy
Token navy
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.115
knocking
Token knocking
Feature activation+2.050
out
Token out
Feature activation+0.207
an
Token an
Feature activation+0.914
enemy
Token enemy
Feature activation+0.026
RPG
Token RPG
Feature activation+0.000
position
Token position
Feature activation+0.000
these
Token these
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+2.064
doesn
Token doesn
Feature activation+1.308
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.036
t
Tokent
Feature activation+0.000
make
Token make
Feature activation+0.421
here
Token here
Feature activation+0.000
?
Token?
Feature activation+0.000
Even
Token Even
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+2.107
have
Token have
Feature activation+2.030
a
Token a
Feature activation+1.112
dozen
Token dozen
Feature activation+0.316
more
Token more
Feature activation+0.000
rules
Token rules
Feature activation+0.000
logging
Token logging
Feature activation+0.000
popular
Token popular
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
his
Token his
Feature activation+0.598
doctor
Token doctor
Feature activation+0.000
wants
Token wants
Feature activation+2.239
a
Token a
Feature activation+0.998
selfie
Token selfie
Feature activation+0.000
with
Token with
Feature activation+0.000
him
Token him
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.034

INTERVAL 1.609 - 2.012
CONTAINS 0.013%

scene
Token scene
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
going
Token going
Feature activation+2.877
so
Token so
Feature activation+0.539
far
Token far
Feature activation+1.991
as
Token as
Feature activation+0.937
to
Token to
Feature activation+0.000
stand
Token stand
Feature activation+0.000
right
Token right
Feature activation+0.000
next
Token next
Feature activation+0.000
most
Token most
Feature activation+2.652
thorough
Token thorough
Feature activation+0.000
amongst
Token amongst
Feature activation+0.000
us
Token us
Feature activation+0.000
will
Token will
Feature activation+0.000
occasionally
Token occasionally
Feature activation+1.847
let
Token let
Feature activation+0.385
the
Token the
Feature activation+0.053
answers
Token answers
Feature activation+0.000
to
Token to
Feature activation+0.000
these
Token these
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
even
Token even
Feature activation+0.000
tell
Token tell
Feature activation+2.603
someone
Token someone
Feature activation+1.779
off
Token off
Feature activation+0.351
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.228
own
Token own
Feature activation+1.027
godd
Token godd
Feature activation+0.000
were
Token were
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+1.892
big
Token big
Feature activation+2.201
deal
Token deal
Feature activation+0.856
,
Token,
Feature activation+0.123
2
Token 2
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
Sometimes
Token Sometimes
Feature activation+0.000
she
Token she
Feature activation+0.000
even
Token even
Feature activation+0.214
leaves
Token leaves
Feature activation+1.782
the
Token the
Feature activation+0.451
radio
Token radio
Feature activation+0.000
on
Token on
Feature activation+0.000
at
Token at
Feature activation+0.879
night
Token night
Feature activation+0.000

INTERVAL 1.207 - 1.609
CONTAINS 0.018%

Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
if
Token if
Feature activation+0.076
it
Token it
Feature activation+1.569
's
Token's
Feature activation+1.517
an
Token an
Feature activation+0.326
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
seems
Token seems
Feature activation+0.000
especially
Token especially
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
in
Token in
Feature activation+1.313
massively
Token massively
Feature activation+0.625
over
Token over
Feature activation+0.000
built
Tokenbuilt
Feature activation+0.000
China
Token China
Feature activation+0.000
.
Token.
Feature activation+0.061
any
Token any
Feature activation+0.000
project
Token project
Feature activation+0.000
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
even
Token even
Feature activation+0.000
for
Token for
Feature activation+1.211
editorial
Token editorial
Feature activation+0.037
illustration
Token illustration
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.566
just
Tokenjust
Feature activation+0.635
one
Token one
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
Vanity
Token Vanity
Feature activation+0.000
Fair
Token Fair
Feature activation+0.030
calls
Token calls
Feature activation+2.009
it
Token it
Feature activation+1.465
what
Token what
Feature activation+0.104
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
detail
Token detail
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
even
Token even
Feature activation+0.000
used
Token used
Feature activation+1.290
an
Token an
Feature activation+0.911
authentic
Token authentic
Feature activation+0.000
Cra
Token Cra
Feature activation+0.000
ppy
Tokenppy
Feature activation+0.000
Old
Token Old
Feature activation+0.000

INTERVAL 0.805 - 1.207
CONTAINS 0.028%

Raiders
Token Raiders
Feature activation+0.000
places
Token places
Feature activation+0.000
even
Token even
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+1.803
hot
Token hot
Feature activation+1.089
team
Token team
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.450
Chargers
Token Chargers
Feature activation+0.000
two
Token two
Feature activation+0.179
surprise
Token surprise
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
economists
Token economists
Feature activation+2.061
who
Token who
Feature activation+1.550
once
Token once
Feature activation+1.106
backed
Token backed
Feature activation+0.172
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.000
are
Token are
Feature activation+0.245
now
Token now
Feature activation+0.608
counted
Token counted
Feature activation+0.000
as
Token as
Feature activation+0.000
truly
Token truly
Feature activation+0.000
successful
Token successful
Feature activation+0.000
even
Token even
Feature activation+0.000
in
Token in
Feature activation+1.029
Italian
Token Italian
Feature activation+0.233
theaters
Token theaters
Feature activation+0.176
without
Token without
Feature activation+0.000
first
Token first
Feature activation+0.000
having
Token having
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.822
official
Token official
Feature activation+1.183
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
military
Token military
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
natural
Token natural
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
necessary
Token necessary
Feature activation+0.865
effect
Token effect
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
market
Token market
Feature activation+0.000

INTERVAL 0.402 - 0.805
CONTAINS 0.047%

.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
even
Token even
Feature activation+0.431
has
Token has
Feature activation+1.571
an
Token an
Feature activation+2.160
old
Token old
Feature activation+0.506
-
Token-
Feature activation+0.000
school
Tokenschool
Feature activation+0.000
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.458
the
Token the
Feature activation+0.458
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
top
Token top
Feature activation+0.000
-
Token-
Feature activation+0.000
ranked
Tokenranked
Feature activation+0.000
suspension
Token suspension
Feature activation+0.000
or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.487
fine
Token fine
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.664
something
Token something
Feature activation+0.597
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
even
Token even
Feature activation+0.057
of
Token of
Feature activation+2.281
our
Token our
Feature activation+1.691
sleep
Token sleep
Feature activation+0.038
,
Token,
Feature activation+1.412
and
Token and
Feature activation+0.600
the
Token the
Feature activation+0.665
only
Token only
Feature activation+2.296
thing
Token thing
Feature activation+0.000
the
Token the
Feature activation+0.000
powers
Token powers
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
even
Token even
Feature activation+0.000
voted
Token voted
Feature activation+0.756
yet
Token yet
Feature activation+0.600
?
Token?
Feature activation+0.595
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
answer
Token answer
Feature activation+0.000

INTERVAL 0.000 - 0.402
CONTAINS 99.873%

""
Token ""
Feature activation+0.000
that
Token that
Feature activation+0.000
prevents
Token prevents
Feature activation+0.000
you
Token you
Feature activation+0.000
from
Token from
Feature activation+0.000
completing
Token completing
Feature activation+0.000
any
Token any
Feature activation+0.000
b
Token b
Feature activation+0.000
raw
Tokenraw
Feature activation+0.000
ls
Tokenls
Feature activation+0.000
.
Token.
Feature activation+0.000
events
Token events
Feature activation+0.000
that
Token that
Feature activation+0.000
happen
Token happen
Feature activation+0.000
to
Token to
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
decide
Token decide
Feature activation+0.000
not
Token not
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
am
Token am
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
of
Token of
Feature activation+0.000
rights
Token rights
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+0.000
any
Token any
Feature activation+0.000
-
Token-
Feature activation+0.000
gallery
Tokengallery
Feature activation+0.000
.
Token.
Feature activation+0.000
org
Tokenorg
Feature activation+0.000
/
Token/
Feature activation+0.000
event
Tokenevent
Feature activation+0.000
/
Token/
Feature activation+0.000
book
Tokenbook
Feature activation+0.000
-
Token-
Feature activation+0.000
club
Tokenclub
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Token in
Feature activation+0.000
1992
Token 1992
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H3.11: (feature 3122)

TOP ACTIVATIONS
MAX = 4.189

of
Token of
Feature activation+2.422
this
Token this
Feature activation+1.821
cosmic
Token cosmic
Feature activation+0.000
human
Token human
Feature activation+0.773
drama
Token drama
Feature activation+0.956
before
Token before
Feature activation+4.189
the
Token the
Feature activation+0.000
curtain
Token curtain
Feature activation+0.000
falls
Token falls
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
community
Token community
Feature activation+2.390
synagogue
Token synagogue
Feature activation+2.655
in
Token in
Feature activation+4.127
G
Token G
Feature activation+0.000
ond
Tokenond
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
,
Token,
Feature activation+0.811
in
Token in
Feature activation+0.899
,
Token,
Feature activation+0.000
writing
Token writing
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+1.159
book
Token book
Feature activation+4.060
,
Token,
Feature activation+1.837
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
Are
Token Are
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.836
we
Token we
Feature activation+3.144
need
Token need
Feature activation+3.978
-
Token -
Feature activation+1.180
another
Token another
Feature activation+0.000
news
Token news
Feature activation+0.000
outlet
Token outlet
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
V
Token V
Feature activation+1.789
-
Token-
Feature activation+1.080
1
Token1
Feature activation+0.973
site
Token site
Feature activation+3.917
in
Token in
Feature activation+3.855
range
Token range
Feature activation+0.000
of
Token of
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
was
Token was
Feature activation+3.294
last
Token last
Feature activation+0.000
V
Token V
Feature activation+1.789
-
Token-
Feature activation+1.080
1
Token1
Feature activation+0.973
site
Token site
Feature activation+3.917
in
Token in
Feature activation+3.855
range
Token range
Feature activation+0.000
of
Token of
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
was
Token was
Feature activation+3.294
overrun
Token overrun
Feature activation+0.030
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.886
we
Token we
Feature activation+3.191
want
Token want
Feature activation+3.854
is
Token is
Feature activation+3.638
to
Token to
Feature activation+2.304
lose
Token lose
Feature activation+0.447
a
Token a
Feature activation+0.000
player
Token player
Feature activation+0.000
last
Token last
Feature activation+0.000
time
Token time
Feature activation+1.393
it
Token it
Feature activation+0.892
was
Token was
Feature activation+3.329
restored
Token restored
Feature activation+1.029
was
Token was
Feature activation+3.832
in
Token in
Feature activation+0.755
the
Token the
Feature activation+0.281
1890
Token 1890
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
state
Token state
Feature activation+2.260
to
Token to
Feature activation+3.825
pass
Token pass
Feature activation+0.657
such
Token such
Feature activation+0.451
a
Token a
Feature activation+0.000
bill
Token bill
Feature activation+0.000
in
Token in
Feature activation+0.386
last
Token last
Feature activation+0.000
-
Token-
Feature activation+0.965
communication
Tokencommunication
Feature activation+1.286
date
Token date
Feature activation+0.442
in
Token in
Feature activation+2.624
any
Token any
Feature activation+3.755
Chinese
Token Chinese
Feature activation+0.000
-
Token-
Feature activation+0.000
language
Tokenlanguage
Feature activation+0.000
websites
Token websites
Feature activation+0.000
.
Token.
Feature activation+0.000
IV
Token IV
Feature activation+0.000
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.300
monarch
Token monarch
Feature activation+3.269
to
Token to
Feature activation+3.735
dismiss
Token dismiss
Feature activation+0.103
a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
lockout
Token lockout
Feature activation+1.781
was
Token was
Feature activation+3.680
in
Token in
Feature activation+1.353
1986
Token 1986
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
center
Token center
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.886
we
Token we
Feature activation+3.191
want
Token want
Feature activation+3.854
is
Token is
Feature activation+3.638
to
Token to
Feature activation+2.304
lose
Token lose
Feature activation+0.447
a
Token a
Feature activation+0.000
player
Token player
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+0.000
Budget
Token Budget
Feature activation+0.000
before
Token before
Feature activation+3.602
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.000
would
Token would
Feature activation+0.436
be
Token be
Feature activation+0.507
one
Token one
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
bit
Token bit
Feature activation+0.093
of
Token of
Feature activation+3.080
oxygen
Token oxygen
Feature activation+0.000
was
Token was
Feature activation+3.500
gone
Token gone
Feature activation+0.269
."
Token."
Feature activation+0.000
And
Token And
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
of
Token of
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
approved
Token approved
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
round
Token round
Feature activation+1.396
of
Token of
Feature activation+3.495
base
Token base
Feature activation+0.614
closures
Token closures
Feature activation+1.437
in
Token in
Feature activation+1.890
2005
Token 2005
Feature activation+0.000
.
Token.
Feature activation+0.000
World
Token World
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+0.000
tournament
Token tournament
Feature activation+3.485
as
Token as
Feature activation+2.055
an
Token an
Feature activation+0.283
ITV
Token ITV
Feature activation+0.000
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.000
constraint
Token constraint
Feature activation+0.000
DSL
Token DSL
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
last
Token last
Feature activation+0.000
article
Token article
Feature activation+3.467
included
Token included
Feature activation+1.842
the
Token the
Feature activation+0.344
following
Token following
Feature activation+0.000
quote
Token quote
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
ripped
Token ripped
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
last
Token last
Feature activation+0.136
remaining
Token remaining
Feature activation+3.460
shred
Token shred
Feature activation+2.270
of
Token of
Feature activation+1.609
legitimacy
Token legitimacy
Feature activation+0.000
in
Token in
Feature activation+0.293
what
Token what
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.096
monarch
Token monarch
Feature activation+2.370
to
Token to
Feature activation+3.433
veto
Token veto
Feature activation+0.133
an
Token an
Feature activation+0.000
Act
Token Act
Feature activation+0.000
of
Token of
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.000

Top DFA by src position
MAX = 4.964

part
Token part
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
parcel
Token parcel
Feature activation-0.015
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
last
Token last
Feature activation+4.964
Top resid features:
act
Token act
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
this
Token this
Feature activation-0.020
Top resid features:
cosmic
Token cosmic
Feature activation+0.034
Top resid features:
human
Token human
Feature activation+0.040
Top resid features:
Sunday
Token Sunday
Feature activation-0.000
Top resid features:
night
Token night
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.023
Top resid features:
The
TokenThe
Feature activation+0.008
Top resid features:
last
Token last
Feature activation+4.722
Top resid features:
community
Token community
Feature activation-0.021
Top resid features:
synagogue
Token synagogue
Feature activation+0.201
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
G
Token G
Feature activation+0.000
Top resid features:
ond
Tokenond
Feature activation+0.000
Top resid features:
Huntington
Token Huntington
Feature activation-0.033
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
writing
Token writing
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.039
Top resid features:
his
Token his
Feature activation-0.056
Top resid features:
last
Token last
Feature activation+4.800
Top resid features:
book
Token book
Feature activation+0.176
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Who
TokenWho
Feature activation+0.000
Top resid features:
ance
Tokenance
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
That
Token That
Feature activation-0.008
Top resid features:
's
Token's
Feature activation+0.046
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
last
Token last
Feature activation+4.502
Top resid features:
thing
Token thing
Feature activation+0.147
Top resid features:
we
Token we
Feature activation+0.177
Top resid features:
need
Token need
Feature activation-0.136
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
October
Token October
Feature activation+0.009
Top resid features:
1944
Token 1944
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
when
Token when
Feature activation-0.070
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
last
Token last
Feature activation+4.345
Top resid features:
V
Token V
Feature activation+0.035
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
1
Token1
Feature activation+0.107
Top resid features:
site
Token site
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
October
Token October
Feature activation-0.010
Top resid features:
1944
Token 1944
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
when
Token when
Feature activation-0.103
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
last
Token last
Feature activation+4.344
Top resid features:
V
Token V
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
1
Token1
Feature activation+0.014
Top resid features:
site
Token site
Feature activation+0.199
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
âĢ
TokenâĢ
Feature activation-0.035
Top resid features:
ľ
Tokenľ
Feature activation-0.015
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
last
Token last
Feature activation+4.422
Top resid features:
thing
Token thing
Feature activation+0.145
Top resid features:
we
Token we
Feature activation+0.253
Top resid features:
want
Token want
Feature activation-0.070
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
Re
TokenRe
Feature activation+0.002
Top resid features:
formation
Tokenformation
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
The
Token The
Feature activation+0.052
Top resid features:
last
Token last
Feature activation+4.682
Top resid features:
time
Token time
Feature activation+0.287
Top resid features:
it
Token it
Feature activation+0.108
Top resid features:
was
Token was
Feature activation-0.016
Top resid features:
restored
Token restored
Feature activation-0.291
Top resid features:
was
Token was
Feature activation-0.222
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.036
Top resid features:
in
Token in
Feature activation+0.041
Top resid features:
Illinois
Token Illinois
Feature activation-0.030
Top resid features:
becoming
Token becoming
Feature activation-0.036
Top resid features:
the
Token the
Feature activation-0.153
Top resid features:
last
Token last
Feature activation+4.499
Top resid features:
state
Token state
Feature activation+0.220
Top resid features:
to
Token to
Feature activation+0.125
Top resid features:
pass
Token pass
Feature activation+0.000
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
last
Token last
Feature activation+4.368
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
communication
Tokencommunication
Feature activation+0.057
Top resid features:
date
Token date
Feature activation+0.082
Top resid features:
in
Token in
Feature activation+0.096
Top resid features:
any
Token any
Feature activation-0.067
Top resid features:
King
Token King
Feature activation-0.020
Top resid features:
William
Token William
Feature activation-0.005
Top resid features:
IV
Token IV
Feature activation-0.007
Top resid features:
being
Token being
Feature activation-0.056
Top resid features:
the
Token the
Feature activation-0.127
Top resid features:
last
Token last
Feature activation+4.329
Top resid features:
monarch
Token monarch
Feature activation+0.186
Top resid features:
to
Token to
Feature activation+0.111
Top resid features:
dismiss
Token dismiss
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
prime
Token prime
Feature activation+0.000
Top resid features:
statement
Token statement
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
The
TokenThe
Feature activation-0.020
Top resid features:
last
Token last
Feature activation+4.348
Top resid features:
lockout
Token lockout
Feature activation+0.158
Top resid features:
was
Token was
Feature activation+0.083
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1986
Token 1986
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.027
Top resid features:
ľ
Tokenľ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.054
Top resid features:
last
Token last
Feature activation+4.540
Top resid features:
thing
Token thing
Feature activation+0.209
Top resid features:
we
Token we
Feature activation+0.068
Top resid features:
want
Token want
Feature activation-0.390
Top resid features:
is
Token is
Feature activation+0.071
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Osborne
Token Osborne
Feature activation-0.010
Top resid features:
told
Token told
Feature activation+0.083
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
BBC
Token BBC
Feature activation-0.042
Top resid features:
his
Token his
Feature activation-0.072
Top resid features:
last
Token last
Feature activation+4.588
Top resid features:
Budget
Token Budget
Feature activation-0.098
Top resid features:
before
Token before
Feature activation-0.072
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
election
Token election
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.081
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
last
Token last
Feature activation+4.314
Top resid features:
bit
Token bit
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.063
Top resid features:
oxygen
Token oxygen
Feature activation-0.114
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
gone
Token gone
Feature activation+0.000
Top resid features:
nationwide
Token nationwide
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Congress
Token Congress
Feature activation+0.012
Top resid features:
approved
Token approved
Feature activation-0.090
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
last
Token last
Feature activation+3.914
Top resid features:
round
Token round
Feature activation+0.382
Top resid features:
of
Token of
Feature activation+0.090
Top resid features:
base
Token base
Feature activation+0.000
Top resid features:
closures
Token closures
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2002
Token 2002
Feature activation+0.013
Top resid features:
World
Token World
Feature activation-0.022
Top resid features:
Cup
Token Cup
Feature activation+0.005
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.011
Top resid features:
his
Token his
Feature activation-0.091
Top resid features:
last
Token last
Feature activation+4.071
Top resid features:
tournament
Token tournament
Feature activation+0.163
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ITV
Token ITV
Feature activation+0.000
Top resid features:
pund
Token pund
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
constraint
Token constraint
Feature activation-0.001
Top resid features:
DSL
Token DSL
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
The
Token The
Feature activation-0.173
Top resid features:
last
Token last
Feature activation+4.142
Top resid features:
article
Token article
Feature activation+0.364
Top resid features:
included
Token included
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:
quote
Token quote
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.023
Top resid features:
ripped
Token ripped
Feature activation-0.130
Top resid features:
of
Token of
Feature activation+0.044
Top resid features:
its
Token its
Feature activation+0.049
Top resid features:
last
Token last
Feature activation+4.254
Top resid features:
remaining
Token remaining
Feature activation+0.064
Top resid features:
shred
Token shred
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
legitimacy
Token legitimacy
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Although
TokenAlthough
Feature activation+0.020
Top resid features:
Queen
Token Queen
Feature activation-0.041
Top resid features:
Anne
Token Anne
Feature activation-0.018
Top resid features:
was
Token was
Feature activation-0.074
Top resid features:
the
Token the
Feature activation-0.066
Top resid features:
last
Token last
Feature activation+4.177
Top resid features:
monarch
Token monarch
Feature activation+0.077
Top resid features:
to
Token to
Feature activation+0.142
Top resid features:
veto
Token veto
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Act
Token Act
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.03

Head 2: 0.05

Head 3: 0.03

Head 4: 0.02

Head 5: 0.06

Head 6: 0.09

Head 7: 0.05

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.50

Positive logits

resil1.41

bernatorial1.35

predec1.32

Nev1.31

payday1.28

obligatory1.27

extant1.25

bidder1.24

pickups1.23

ever1.23

schooling1.22

reckoning1.22

EVER1.21

recogn1.20

istani1.20

Ever1.20

------------------------------------------------1.19

millenn1.19

awei1.19

muster1.18

Negative logits

xual-1.47

gradient-1.32

oxide-1.31

embed-1.31

-1.29

osph-1.25

ttes-1.24

pread-1.23

iets-1.22

entious-1.22

abound-1.21

ENS-1.20

bos-1.20

mixture-1.19

ijn-1.19

atars-1.19

spread-1.18

IMAGES-1.18

IUM-1.18

urat-1.18

INTERVAL 3.770 - 4.189
CONTAINS 0.001%

last
Token last
Feature activation+0.000
time
Token time
Feature activation+1.393
it
Token it
Feature activation+0.892
was
Token was
Feature activation+3.329
restored
Token restored
Feature activation+1.029
was
Token was
Feature activation+3.832
in
Token in
Feature activation+0.755
the
Token the
Feature activation+0.281
1890
Token 1890
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
writing
Token writing
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+1.159
book
Token book
Feature activation+4.060
,
Token,
Feature activation+1.837
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
Are
Token Are
Feature activation+0.000
of
Token of
Feature activation+2.422
this
Token this
Feature activation+1.821
cosmic
Token cosmic
Feature activation+0.000
human
Token human
Feature activation+0.773
drama
Token drama
Feature activation+0.956
before
Token before
Feature activation+4.189
the
Token the
Feature activation+0.000
curtain
Token curtain
Feature activation+0.000
falls
Token falls
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
community
Token community
Feature activation+2.390
synagogue
Token synagogue
Feature activation+2.655
in
Token in
Feature activation+4.127
G
Token G
Feature activation+0.000
ond
Tokenond
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
,
Token,
Feature activation+0.811
in
Token in
Feature activation+0.899
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.836
we
Token we
Feature activation+3.144
need
Token need
Feature activation+3.978
-
Token -
Feature activation+1.180
another
Token another
Feature activation+0.000
news
Token news
Feature activation+0.000
outlet
Token outlet
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 3.351 - 3.770
CONTAINS 0.001%

World
Token World
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+0.000
tournament
Token tournament
Feature activation+3.485
as
Token as
Feature activation+2.055
an
Token an
Feature activation+0.283
ITV
Token ITV
Feature activation+0.000
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.600
I
Token I
Feature activation+2.917
want
Token want
Feature activation+3.414
to
Token to
Feature activation+2.820
see
Token see
Feature activation+3.202
it
Token it
Feature activation+0.520
become
Token become
Feature activation+0.000
is
Token is
Feature activation+3.309
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
lockout
Token lockout
Feature activation+1.781
was
Token was
Feature activation+3.680
in
Token in
Feature activation+1.353
1986
Token 1986
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
center
Token center
Feature activation+0.000
IV
Token IV
Feature activation+0.000
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.300
monarch
Token monarch
Feature activation+3.269
to
Token to
Feature activation+3.735
dismiss
Token dismiss
Feature activation+0.103
a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
ripped
Token ripped
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
last
Token last
Feature activation+0.136
remaining
Token remaining
Feature activation+3.460
shred
Token shred
Feature activation+2.270
of
Token of
Feature activation+1.609
legitimacy
Token legitimacy
Feature activation+0.000
in
Token in
Feature activation+0.293
what
Token what
Feature activation+0.000

INTERVAL 2.932 - 3.351
CONTAINS 0.004%

âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.886
we
Token we
Feature activation+3.191
want
Token want
Feature activation+3.854
is
Token is
Feature activation+3.638
to
Token to
Feature activation+2.304
lose
Token lose
Feature activation+0.447
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
person
Token person
Feature activation+1.658
to
Token to
Feature activation+3.303
draw
Token draw
Feature activation+1.661
a
Token a
Feature activation+0.733
line
Token line
Feature activation+0.003
is
Token is
Feature activation+1.992
the
Token the
Feature activation+0.217
the
Token the
Feature activation+0.260
north
Token north
Feature activation+0.000
of
Token of
Feature activation+0.000
Ethiopia
Token Ethiopia
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+3.203
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
rented
Token rented
Feature activation+0.000
building
Token building
Feature activation+0.000
c
Token c
Feature activation+0.000
allocated
Token allocated
Feature activation+0.000
after
Token after
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
's
Token's
Feature activation+0.000
last
Token last
Feature activation+0.000
major
Token major
Feature activation+3.138
earthquake
Token earthquake
Feature activation+0.756
,
Token,
Feature activation+0.860
in
Token in
Feature activation+0.265
L
Token L
Feature activation+0.000
'
Token'
Feature activation+0.000
brother
Token brother
Feature activation+0.000
ate
Token ate
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
apple
Token apple
Feature activation+0.258
,
Token,
Feature activation+2.934
for
Token for
Feature activation+0.373
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 2.513 - 2.932
CONTAINS 0.004%

you
Token you
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
winners
Token winners
Feature activation+1.896
of
Token of
Feature activation+2.520
the
Token the
Feature activation+2.260
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
,
Token,
Feature activation+0.836
the
Token the
Feature activation+0.611
release
Token release
Feature activation+1.783
of
Token of
Feature activation+1.875
the
Token the
Feature activation+1.437
hand
Token hand
Feature activation+0.552
book
Tokenbook
Feature activation+0.000
we
Token we
Feature activation+2.682
've
Token've
Feature activation+0.714
seen
Token seen
Feature activation+1.938
Adobe
Token Adobe
Feature activation+0.000
bring
Token bring
Feature activation+0.000
out
Token out
Feature activation+0.000
great
Token great
Feature activation+1.495
British
Token British
Feature activation+0.272
rock
Token rock
Feature activation+2.203
n
Token n
Feature activation+0.538
roll
Token roll
Feature activation+3.051
bands
Token bands
Feature activation+2.548
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
See
Token See
Feature activation+0.000
The
Token The
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.600
I
Token I
Feature activation+2.917
want
Token want
Feature activation+3.414
to
Token to
Feature activation+2.820
see
Token see
Feature activation+3.202
it
Token it
Feature activation+0.520
become
Token become
Feature activation+0.000
is
Token is
Feature activation+3.309
something
Token something
Feature activation+0.000
route
Token route
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
last
Token last
Feature activation+0.000
thing
Token thing
Feature activation+1.600
I
Token I
Feature activation+2.917
want
Token want
Feature activation+3.414
to
Token to
Feature activation+2.820
see
Token see
Feature activation+3.202
it
Token it
Feature activation+0.520
become
Token become
Feature activation+0.000

INTERVAL 2.094 - 2.513
CONTAINS 0.006%

to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
photo
Token photo
Feature activation+0.881
she
Token she
Feature activation+2.252
took
Token took
Feature activation+2.215
of
Token of
Feature activation+1.976
Sah
Token Sah
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
record
Token record
Feature activation+2.129
,
Token,
Feature activation+2.521
Coll
Token Coll
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
ible
Tokenible
Feature activation+0.000
Lung
Token Lung
Feature activation+0.146
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
my
Token my
Feature activation+0.000
last
Token last
Feature activation+0.852
Thanksgiving
Token Thanksgiving
Feature activation+0.521
in
Token in
Feature activation+2.448
New
Token New
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
,
Token,
Feature activation+1.513
even
Token even
Feature activation+0.371
though
Token though
Feature activation+0.000
ran
Token ran
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+0.453
competitive
Token competitive
Feature activation+2.186
race
Token race
Feature activation+2.207
in
Token in
Feature activation+2.376
1998
Token 1998
Feature activation+0.000
,
Token,
Feature activation+0.197
an
Token an
Feature activation+0.000
e
Token e
Feature activation+0.000
on
Tokenon
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
match
Token match
Feature activation+1.733
of
Token of
Feature activation+2.963
the
Token the
Feature activation+2.256
regular
Token regular
Feature activation+1.709
season
Token season
Feature activation+0.244
knowing
Token knowing
Feature activation+0.000
they
Token they
Feature activation+0.000
need
Token need
Feature activation+0.000

INTERVAL 1.676 - 2.094
CONTAINS 0.007%

at
Tokenat
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
last
Token last
Feature activation+0.263
breath
Token breath
Feature activation+3.000
,
Token,
Feature activation+1.982
when
Token when
Feature activation+0.000
Cord
Token Cord
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
and
Token and
Feature activation+0.000
many
Token many
Feature activation+0.000
ured
Tokenured
Feature activation+0.791
700
Token 700
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000
rally
Token rally
Feature activation+0.000
points
Token points
Feature activation+0.000
came
Token came
Feature activation+2.077
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.250
two
Token two
Feature activation+0.000
hours
Token hours
Feature activation+0.716
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
boy
Token boy
Feature activation+0.000
had
Token had
Feature activation+0.000
last
Token last
Feature activation+0.000
been
Token been
Feature activation+1.860
seen
Token seen
Feature activation+1.587
by
Token by
Feature activation+0.045
his
Token his
Feature activation+0.174
parents
Token parents
Feature activation+0.000
on
Token on
Feature activation+0.000
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
robot
Token robot
Feature activation+0.145
,
Token,
Feature activation+2.246
I
Token I
Feature activation+1.692
'm
Token'm
Feature activation+0.514
going
Token going
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+0.000
large
Token large
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
day
Token day
Feature activation+1.096
the
Token the
Feature activation+1.385
House
Token House
Feature activation+0.024
is
Token is
Feature activation+2.012
scheduled
Token scheduled
Feature activation+0.037
to
Token to
Feature activation+0.013
be
Token be
Feature activation+0.460
in
Token in
Feature activation+0.000
session
Token session
Feature activation+0.000

INTERVAL 1.257 - 1.676
CONTAINS 0.008%

,
Token,
Feature activation+1.726
their
Token their
Feature activation+0.085
last
Token last
Feature activation+0.352
mouth
Token mouth
Feature activation+1.758
ful
Tokenful
Feature activation+1.505
,
Token,
Feature activation+1.409
they
Token they
Feature activation+0.564
would
Token would
Feature activation+0.408
not
Token not
Feature activation+0.000
eat
Token eat
Feature activation+0.000
without
Token without
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
last
Token last
Feature activation+0.000
of
Token of
Feature activation+1.934
which
Token which
Feature activation+1.424
was
Token was
Feature activation+2.384
Pen
Token Pen
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
in
Token in
Feature activation+1.601
finished
Token finished
Feature activation+0.000
her
Token her
Feature activation+0.000
last
Token last
Feature activation+0.000
class
Token class
Feature activation+2.592
of
Token of
Feature activation+2.774
the
Token the
Feature activation+1.638
day
Token day
Feature activation+1.109
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
shuff
Token shuff
Feature activation+0.000
led
Tokenled
Feature activation+0.000
last
Token last
Feature activation+0.852
Thanksgiving
Token Thanksgiving
Feature activation+0.521
in
Token in
Feature activation+2.448
New
Token New
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
,
Token,
Feature activation+1.513
even
Token even
Feature activation+0.371
though
Token though
Feature activation+0.000
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
and
Token and
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
were
Token were
Feature activation+1.514
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.838 - 1.257
CONTAINS 0.010%

Memory
Token Memory
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
laugh
Token laugh
Feature activation+1.019
âĢ¦
TokenâĢ¦
Feature activation+0.000
I
TokenI
Feature activation+0.712
wouldn
Token wouldn
Feature activation+0.150
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
of
Token of
Feature activation+1.674
the
Token the
Feature activation+1.865
W
Token W
Feature activation+0.029
ren
Tokenren
Feature activation+0.000
Era
Token Era
Feature activation+0.113
selections
Token selections
Feature activation+1.100
,
Token,
Feature activation+1.844
and
Token and
Feature activation+0.511
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
has
Token has
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
indicates
Token indicates
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
last
Token last
Feature activation+0.000
seen
Token seen
Feature activation+1.238
attacking
Token attacking
Feature activation+1.124
a
Token a
Feature activation+0.243
German
Token German
Feature activation+0.000
position
Token position
Feature activation+0.000
,
Token,
Feature activation+0.166
changes
Token changes
Feature activation+0.000
since
Token since
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
last
Token last
Feature activation+0.000
there
Token there
Feature activation+1.044
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
really
Token really
Feature activation+0.000
wake
Token wake
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
ice
Token ice
Feature activation+0.909
age
Token age
Feature activation+0.925
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
winter
Token winter
Feature activation+0.000
,
Token,
Feature activation+0.000
brave
Token brave
Feature activation+0.000

INTERVAL 0.419 - 0.838
CONTAINS 0.016%

against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
one
Token one
Feature activation+1.721
and
Token and
Feature activation+1.194
the
Token the
Feature activation+0.564
one
Token one
Feature activation+0.189
before
Token before
Feature activation+1.876
that
Token that
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.020
because
Token because
Feature activation+0.026
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
laugh
Token laugh
Feature activation+1.019
âĢ¦
TokenâĢ¦
Feature activation+0.000
I
TokenI
Feature activation+0.712
wouldn
Token wouldn
Feature activation+0.150
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
thing
Token thing
Feature activation+1.600
I
Token I
Feature activation+2.917
want
Token want
Feature activation+3.414
to
Token to
Feature activation+2.820
see
Token see
Feature activation+3.202
it
Token it
Feature activation+0.520
become
Token become
Feature activation+0.000
is
Token is
Feature activation+3.309
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
inevitably
Token inevitably
Feature activation+0.000
half
Token half
Feature activation+0.000
since
Token since
Feature activation+0.000
my
Token my
Feature activation+0.000
last
Token last
Feature activation+0.000
visit
Token visit
Feature activation+1.835
,
Token,
Feature activation+0.656
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
well
Token well
Feature activation+0.000
overdue
Token overdue
Feature activation+0.000
took
Token took
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
finish
Token finish
Feature activation+0.000
his
Token his
Feature activation+0.000
talk
Token talk
Feature activation+0.545
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
shares
Token shares
Feature activation+0.000
recovered
Token recovered
Feature activation+0.000
shortly
Token shortly
Feature activation+0.000

INTERVAL 0.000 - 0.419
CONTAINS 99.945%

the
Token the
Feature activation+0.000
regime
Token regime
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
implies
Token implies
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
High
Token High
Feature activation+0.000
Court
Token Court
Feature activation+0.000
judge
Token judge
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Malaysia
Token Malaysia
Feature activation+0.000
,
Token,
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
men
Token men
Feature activation+0.000
are
Token are
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
turning
Token turning
Feature activation+0.000
into
Token into
Feature activation+0.000
something
Token something
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
different
Token different
Feature activation+0.000
.
Token.
Feature activation+0.000
Green
Token Green
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
know
Token know
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Hus
Token Hus
Feature activation+0.000
Has
Token Has
Feature activation+0.000
lem
Tokenlem
Feature activation+0.000
,
Token,
Feature activation+0.000
James
Token James
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
,
Token,
Feature activation+0.000
Hassan
Token Hassan
Feature activation+0.000
Whites
Token Whites
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
,
Token,
Feature activation+0.000
Tyler
Token Tyler
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