H10.5 top features

Top feature 0 in H10.5: (feature 6174)

TOP ACTIVATIONS
MAX = 7.110

would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.150
won
Token won
Feature activation+4.608
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+7.110
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.157
44
Token 44
Feature activation+4.892
on
Token on
Feature activation+0.598
13
Token 13
Feature activation+0.574
January
Token January
Feature activation+2.213
this
Token this
Feature activation+0.130
year
Token year
Feature activation+6.965
.
Token.
Feature activation+0.403
He
Token He
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.055
been
Token been
Feature activation+0.051
the
Token the
Feature activation+0.206
better
Token better
Feature activation+0.279
choice
Token choice
Feature activation+6.174
here
Token here
Feature activation+5.003
to
Token to
Feature activation+0.000
replace
Token replace
Feature activation+0.000
MS
Token MS
Feature activation+0.000
Office
Token Office
Feature activation+2.178
not
Token not
Feature activation+0.264
have
Token have
Feature activation+0.000
called
Token called
Feature activation+0.000
herself
Token herself
Feature activation+0.000
a
Token a
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+5.975
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
expected
Token expected
Feature activation+0.779
more
Token more
Feature activation+0.945
l
Token l
Feature activation+0.000
arc
Tokenarc
Feature activation+0.000
eny
Tokeneny
Feature activation+2.353
charges
Token charges
Feature activation+5.774
pred
Token pred
Feature activation+0.000
icated
Tokenicated
Feature activation+0.000
upon
Token upon
Feature activation+0.000
a
Token a
Feature activation+0.000
pet
Token pet
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
Stand
Token Stand
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.019
looked
Token looked
Feature activation+5.647
this
Token this
Feature activation+0.286
week
Token week
Feature activation+2.320
,
Token,
Feature activation+1.254
with
Token with
Feature activation+0.000
each
Token each
Feature activation+0.680
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.227
satisfying
Token satisfying
Feature activation+3.766
for
Token for
Feature activation+0.743
me
Token me
Feature activation+5.561
,
Token,
Feature activation+3.056
it
Token it
Feature activation+0.245
's
Token's
Feature activation+0.008
a
Token a
Feature activation+0.000
really
Token really
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+5.490
with
Token with
Feature activation+0.000
you
Token you
Feature activation+2.341
guiding
Token guiding
Feature activation+0.232
it
Token it
Feature activation+0.942
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Imagine
Token Imagine
Feature activation+0.000
what
Token what
Feature activation+0.412
would
Token would
Feature activation+0.005
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+5.229
if
Token if
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Per
Token Per
Feature activation+0.000
ino
Tokenino
Feature activation+0.756
been
Token been
Feature activation+0.031
drawn
Token drawn
Feature activation+2.163
by
Token by
Feature activation+0.000
another
Token another
Feature activation+0.000
artist
Token artist
Feature activation+2.302
entirely
Token entirely
Feature activation+5.205
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
How
TokenHow
Feature activation+0.000
would
Token would
Feature activation+0.000
I
Token I
Feature activation+0.000
OU
TokenOU
Feature activation+1.197
s
Tokens
Feature activation+4.556
on
Token on
Feature activation+0.231
a
Token a
Feature activation+0.000
game
Token game
Feature activation+5.054
for
Token for
Feature activation+0.233
a
Token a
Feature activation+0.000
system
Token system
Feature activation+1.517
that
Token that
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
planning
Token planning
Feature activation+0.061
committee
Token committee
Feature activation+4.562
for
Token for
Feature activation+0.749
IC
Token IC
Feature activation+0.000
MI
TokenMI
Feature activation+2.545
15
Token15
Feature activation+5.007
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.209
certainly
Token certainly
Feature activation+0.244
wouldn
Token wouldn
Feature activation+0.168
âĢ
TokenâĢ
Feature activation+0.000
have
Token have
Feature activation+0.055
been
Token been
Feature activation+0.051
the
Token the
Feature activation+0.206
better
Token better
Feature activation+0.279
choice
Token choice
Feature activation+6.174
here
Token here
Feature activation+5.003
to
Token to
Feature activation+0.000
replace
Token replace
Feature activation+0.000
MS
Token MS
Feature activation+0.000
Office
Token Office
Feature activation+2.178
.
Token.
Feature activation+0.361
southern
Token southern
Feature activation+0.000
periphery
Token periphery
Feature activation+0.044
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Euro
Token Euro
Feature activation+0.094
zone
Tokenzone
Feature activation+5.002
.
Token.
Feature activation+0.000
Perhaps
Token Perhaps
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
world
Token world
Feature activation+0.000
Newcastle
Token Newcastle
Feature activation+0.000
would
Token would
Feature activation+0.147
be
Token be
Feature activation+0.808
be
Token be
Feature activation+0.642
famous
Token famous
Feature activation+4.982
above
Token above
Feature activation+0.769
all
Token all
Feature activation+3.973
else
Token else
Feature activation+4.780
for
Token for
Feature activation+0.168
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
46
Token 46
Feature activation+0.000
percent
Token percent
Feature activation+3.025
to
Token to
Feature activation+0.000
39
Token 39
Feature activation+0.670
percent
Token percent
Feature activation+4.893
over
Token over
Feature activation+0.000
Romney
Token Romney
Feature activation+2.958
,
Token,
Feature activation+0.775
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
ani
Tokenani
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
44
Token 44
Feature activation+4.892
on
Token on
Feature activation+0.598
13
Token 13
Feature activation+0.574
January
Token January
Feature activation+2.213
this
Token this
Feature activation+0.130
year
Token year
Feature activation+6.965
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+1.385
base
Token base
Feature activation+4.854
and
Token and
Feature activation+0.000
designated
Token designated
Feature activation+0.273
hitter
Token hitter
Feature activation+5.468
.
Token.
Feature activation+0.508
In
Token In
Feature activation+0.000
be
Token be
Feature activation+0.808
be
Token be
Feature activation+0.642
famous
Token famous
Feature activation+4.982
above
Token above
Feature activation+0.769
all
Token all
Feature activation+3.973
else
Token else
Feature activation+4.780
for
Token for
Feature activation+0.168
one
Token one
Feature activation+0.000
saying
Token saying
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Crane
Token Crane
Feature activation+1.891
and
Token and
Feature activation+0.000
Kau
Token Kau
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
man
Tokenman
Feature activation+4.741
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
better
Token better
Feature activation+0.000
off
Token off
Feature activation+0.523
with
Token with
Feature activation+0.000

Top DFA by src position
MAX = 6.617

,
Token,
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.010
Top resid features:
whether
Token whether
Feature activation-0.023
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.434
Top resid features:
have
Token have
Feature activation+6.617
Top resid features:
won
Token won
Feature activation+0.539
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
White
Token White
Feature activation-0.000
Top resid features:
House
Token House
Feature activation+0.020
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
P
TokenP
Feature activation-0.001
Top resid features:
ant
Tokenant
Feature activation-0.000
Top resid features:
ani
Tokenani
Feature activation-0.001
Top resid features:
would
Token would
Feature activation+0.080
Top resid features:
have
Token have
Feature activation+5.433
Top resid features:
been
Token been
Feature activation+1.449
Top resid features:
44
Token 44
Feature activation+0.380
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
13
Token 13
Feature activation+0.013
Top resid features:
January
Token January
Feature activation+0.101
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Lib
TokenLib
Feature activation-0.006
Top resid features:
re
Tokenre
Feature activation-0.002
Top resid features:
Office
TokenOffice
Feature activation-0.003
Top resid features:
would
Token would
Feature activation+1.331
Top resid features:
have
Token have
Feature activation+4.026
Top resid features:
been
Token been
Feature activation+0.873
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
better
Token better
Feature activation+0.144
Top resid features:
choice
Token choice
Feature activation+0.141
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
Baptist
Token Baptist
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
would
Token would
Feature activation+0.065
Top resid features:
certainly
Token certainly
Feature activation+0.250
Top resid features:
not
Token not
Feature activation+0.694
Top resid features:
have
Token have
Feature activation+5.335
Top resid features:
called
Token called
Feature activation+0.027
Top resid features:
herself
Token herself
Feature activation+0.030
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
Buddhist
Token Buddhist
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
arc
Tokenarc
Feature activation+0.000
Top resid features:
eny
Tokeneny
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
We
Token We
Feature activation-0.000
Top resid features:
would
Token would
Feature activation+0.471
Top resid features:
have
Token have
Feature activation+5.281
Top resid features:
expected
Token expected
Feature activation+0.293
Top resid features:
more
Token more
Feature activation+0.105
Top resid features:
l
Token l
Feature activation-0.003
Top resid features:
arc
Tokenarc
Feature activation+0.002
Top resid features:
eny
Tokeneny
Feature activation+0.034
Top resid features:
B
Token B
Feature activation+0.006
Top resid features:
CS
TokenCS
Feature activation+0.020
Top resid features:
Stand
Token Stand
Feature activation+0.000
Top resid features:
ings
Tokenings
Feature activation+0.012
Top resid features:
would
Token would
Feature activation+1.459
Top resid features:
have
Token have
Feature activation+3.667
Top resid features:
looked
Token looked
Feature activation+0.908
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
week
Token week
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Indy
Token Indy
Feature activation+0.003
Top resid features:
Car
TokenCar
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.629
Top resid features:
have
Token have
Feature activation+3.101
Top resid features:
been
Token been
Feature activation+1.403
Top resid features:
satisfying
Token satisfying
Feature activation+0.642
Top resid features:
for
Token for
Feature activation+0.193
Top resid features:
me
Token me
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.001
Top resid features:
compassionate
Token compassionate
Feature activation+0.016
Top resid features:
than
Token than
Feature activation+0.018
Top resid features:
it
Token it
Feature activation-0.017
Top resid features:
would
Token would
Feature activation+1.500
Top resid features:
have
Token have
Feature activation+3.276
Top resid features:
been
Token been
Feature activation+1.165
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
guiding
Token guiding
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.055
Top resid features:
Imagine
Token Imagine
Feature activation+0.201
Top resid features:
what
Token what
Feature activation+0.025
Top resid features:
would
Token would
Feature activation+1.551
Top resid features:
have
Token have
Feature activation+3.242
Top resid features:
happened
Token happened
Feature activation+0.544
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
Ms
Token Ms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Per
Token Per
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
fate
Token fate
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
Furious
Token Furious
Feature activation-0.010
Top resid features:
would
Token would
Feature activation+0.196
Top resid features:
have
Token have
Feature activation+4.419
Top resid features:
been
Token been
Feature activation+0.679
Top resid features:
drawn
Token drawn
Feature activation+0.128
Top resid features:
by
Token by
Feature activation+0.064
Top resid features:
another
Token another
Feature activation+0.054
Top resid features:
artist
Token artist
Feature activation+0.319
Top resid features:
I
TokenI
Feature activation+0.005
Top resid features:
wouldn
Token wouldn
Feature activation+0.093
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
t
Tokent
Feature activation+1.266
Top resid features:
have
Token have
Feature activation+2.703
Top resid features:
normally
Token normally
Feature activation+1.181
Top resid features:
spent
Token spent
Feature activation+0.052
Top resid features:
one
Token one
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
my
Token my
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.013
Top resid features:
wouldn
Token wouldn
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation+0.801
Top resid features:
be
Token be
Feature activation+3.094
Top resid features:
on
Token on
Feature activation+0.747
Top resid features:
the
Token the
Feature activation+0.160
Top resid features:
planning
Token planning
Feature activation-0.001
Top resid features:
committee
Token committee
Feature activation+0.489
Top resid features:
for
Token for
Feature activation+0.107
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Lib
TokenLib
Feature activation+0.001
Top resid features:
re
Tokenre
Feature activation-0.002
Top resid features:
Office
TokenOffice
Feature activation-0.006
Top resid features:
would
Token would
Feature activation+0.868
Top resid features:
have
Token have
Feature activation+2.825
Top resid features:
been
Token been
Feature activation+0.754
Top resid features:
the
Token the
Feature activation+0.166
Top resid features:
better
Token better
Feature activation+0.232
Top resid features:
choice
Token choice
Feature activation+0.546
Top resid features:
here
Token here
Feature activation+0.104
Top resid features:
Perhaps
Token Perhaps
Feature activation-0.013
Top resid features:
Ms
Token Ms
Feature activation-0.001
Top resid features:
Merkel
Token Merkel
Feature activation-0.006
Top resid features:
would
Token would
Feature activation+0.140
Top resid features:
not
Token not
Feature activation+1.066
Top resid features:
have
Token have
Feature activation+4.081
Top resid features:
let
Token let
Feature activation+0.053
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
entire
Token entire
Feature activation-0.013
Top resid features:
southern
Token southern
Feature activation-0.008
Top resid features:
periphery
Token periphery
Feature activation+0.166
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
world
Token world
Feature activation+0.015
Top resid features:
Newcastle
Token Newcastle
Feature activation+0.008
Top resid features:
would
Token would
Feature activation+1.580
Top resid features:
be
Token be
Feature activation+2.042
Top resid features:
be
Token be
Feature activation+1.599
Top resid features:
famous
Token famous
Feature activation+0.197
Top resid features:
above
Token above
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
else
Token else
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
Obama
TokenObama
Feature activation-0.031
Top resid features:
would
Token would
Feature activation+1.186
Top resid features:
have
Token have
Feature activation+3.624
Top resid features:
an
Token an
Feature activation+0.078
Top resid features:
advantage
Token advantage
Feature activation+0.307
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
46
Token 46
Feature activation+0.057
Top resid features:
percent
Token percent
Feature activation+0.116
Top resid features:
P
TokenP
Feature activation-0.000
Top resid features:
ant
Tokenant
Feature activation+0.000
Top resid features:
ani
Tokenani
Feature activation-0.003
Top resid features:
would
Token would
Feature activation+0.340
Top resid features:
have
Token have
Feature activation+1.927
Top resid features:
been
Token been
Feature activation+2.683
Top resid features:
44
Token 44
Feature activation+0.369
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
13
Token 13
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
blame
Token blame
Feature activation+0.001
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
would
Token would
Feature activation+0.646
Top resid features:
have
Token have
Feature activation+2.569
Top resid features:
been
Token been
Feature activation+1.381
Top resid features:
mostly
Token mostly
Feature activation+0.436
Top resid features:
at
Token at
Feature activation+0.187
Top resid features:
first
Token first
Feature activation+0.042
Top resid features:
base
Token base
Feature activation+0.023
Top resid features:
think
Token think
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
world
Token world
Feature activation+0.005
Top resid features:
Newcastle
Token Newcastle
Feature activation-0.044
Top resid features:
would
Token would
Feature activation+2.182
Top resid features:
be
Token be
Feature activation+1.142
Top resid features:
be
Token be
Feature activation+0.989
Top resid features:
famous
Token famous
Feature activation+0.887
Top resid features:
above
Token above
Feature activation+0.040
Top resid features:
all
Token all
Feature activation+0.090
Top resid features:
title
Token title
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Wouldn
Token Wouldn
Feature activation+0.955
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+4.239
Top resid features:
Crane
Token Crane
Feature activation+0.150
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
Kau
Token Kau
Feature activation-0.001
Top resid features:
ff
Tokenff
Feature activation-0.000
Top resid features:
man
Tokenman
Feature activation+0.039
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.66

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.10

Head 10: 0.02

Head 11: 0.03

Positive logits

if7.11

hadn5.22

had5.17

if5.08

anyway4.89

unless4.85

would4.65

anyways4.63

would4.49

wouldn4.47

Had4.42

IF4.42

endif4.27

had4.20

assuming4.17

whichever4.10

endif4.00

otherwise3.98

Would3.96

'd3.85

Negative logits

emis-3.63

quartered-2.92

arton-2.77

isible-2.69

ogly-2.66

Amb-2.65

-2.63

ilee-2.61

externalToEVAOnly-2.60

urches-2.60

gencies-2.58

ippi-2.55

olulu-2.49

`,-2.47

engeance-2.46

ウス-2.45

aughtered-2.45

mber-2.44

obl-2.42

idem-2.41

INTERVAL 6.399 - 7.110
CONTAINS 0.000%

would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.150
won
Token won
Feature activation+4.608
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+7.110
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.157
44
Token 44
Feature activation+4.892
on
Token on
Feature activation+0.598
13
Token 13
Feature activation+0.574
January
Token January
Feature activation+2.213
this
Token this
Feature activation+0.130
year
Token year
Feature activation+6.965
.
Token.
Feature activation+0.403
He
Token He
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000

INTERVAL 5.688 - 6.399
CONTAINS 0.000%

expected
Token expected
Feature activation+0.779
more
Token more
Feature activation+0.945
l
Token l
Feature activation+0.000
arc
Tokenarc
Feature activation+0.000
eny
Tokeneny
Feature activation+2.353
charges
Token charges
Feature activation+5.774
pred
Token pred
Feature activation+0.000
icated
Tokenicated
Feature activation+0.000
upon
Token upon
Feature activation+0.000
a
Token a
Feature activation+0.000
pet
Token pet
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.055
been
Token been
Feature activation+0.051
the
Token the
Feature activation+0.206
better
Token better
Feature activation+0.279
choice
Token choice
Feature activation+6.174
here
Token here
Feature activation+5.003
to
Token to
Feature activation+0.000
replace
Token replace
Feature activation+0.000
MS
Token MS
Feature activation+0.000
Office
Token Office
Feature activation+2.178
not
Token not
Feature activation+0.264
have
Token have
Feature activation+0.000
called
Token called
Feature activation+0.000
herself
Token herself
Feature activation+0.000
a
Token a
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+5.975
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 4.977 - 5.688
CONTAINS 0.001%

planning
Token planning
Feature activation+0.061
committee
Token committee
Feature activation+4.562
for
Token for
Feature activation+0.749
IC
Token IC
Feature activation+0.000
MI
TokenMI
Feature activation+2.545
15
Token15
Feature activation+5.007
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.209
certainly
Token certainly
Feature activation+0.244
wouldn
Token wouldn
Feature activation+0.168
âĢ
TokenâĢ
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
Stand
Token Stand
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.019
looked
Token looked
Feature activation+5.647
this
Token this
Feature activation+0.286
week
Token week
Feature activation+2.320
,
Token,
Feature activation+1.254
with
Token with
Feature activation+0.000
each
Token each
Feature activation+0.680
compassionate
Token compassionate
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+5.490
with
Token with
Feature activation+0.000
you
Token you
Feature activation+2.341
guiding
Token guiding
Feature activation+0.232
it
Token it
Feature activation+0.942
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
OU
TokenOU
Feature activation+1.197
s
Tokens
Feature activation+4.556
on
Token on
Feature activation+0.231
a
Token a
Feature activation+0.000
game
Token game
Feature activation+5.054
for
Token for
Feature activation+0.233
a
Token a
Feature activation+0.000
system
Token system
Feature activation+1.517
that
Token that
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
been
Token been
Feature activation+0.031
drawn
Token drawn
Feature activation+2.163
by
Token by
Feature activation+0.000
another
Token another
Feature activation+0.000
artist
Token artist
Feature activation+2.302
entirely
Token entirely
Feature activation+5.205
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
How
TokenHow
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 4.266 - 4.977
CONTAINS 0.001%

t
Tokent
Feature activation+0.346
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.436
the
Token the
Feature activation+0.000
planning
Token planning
Feature activation+0.061
committee
Token committee
Feature activation+4.562
for
Token for
Feature activation+0.749
IC
Token IC
Feature activation+0.000
MI
TokenMI
Feature activation+2.545
15
Token15
Feature activation+5.007
and
Token and
Feature activation+0.000
have
Token have
Feature activation+0.103
been
Token been
Feature activation+0.000
entitled
Token entitled
Feature activation+0.901
to
Token to
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.000
immunity
Token immunity
Feature activation+4.672
only
Token only
Feature activation+2.644
if
Token if
Feature activation+0.000
his
Token his
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
crime
Token crime
Feature activation+0.331
one
Token one
Feature activation+0.119
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
I
Token I
Feature activation+0.000
OU
TokenOU
Feature activation+1.197
s
Tokens
Feature activation+4.556
on
Token on
Feature activation+0.231
a
Token a
Feature activation+0.000
game
Token game
Feature activation+5.054
for
Token for
Feature activation+0.233
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
46
Token 46
Feature activation+0.000
percent
Token percent
Feature activation+3.025
to
Token to
Feature activation+0.000
39
Token 39
Feature activation+0.670
percent
Token percent
Feature activation+4.893
over
Token over
Feature activation+0.000
Romney
Token Romney
Feature activation+2.958
,
Token,
Feature activation+0.775
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.150
won
Token won
Feature activation+4.608
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+7.110
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000

INTERVAL 3.555 - 4.266
CONTAINS 0.002%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.579
a
Token a
Feature activation+3.904
more
Token more
Feature activation+0.000
humble
Token humble
Feature activation+0.000
person
Token person
Feature activation+0.326
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.426
done
Token done
Feature activation+0.241
anything
Token anything
Feature activation+0.000
for
Token for
Feature activation+0.000
us
Token us
Feature activation+4.065
.
Token.
Feature activation+0.491
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.044
The
Token The
Feature activation+0.000
then
Token then
Feature activation+0.000
still
Token still
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
fulfil
Token fulfil
Feature activation+0.271
its
Token its
Feature activation+0.000
pledges
Token pledges
Feature activation+4.034
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
constrained
Token constrained
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
might
Token might
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
gone
Token gone
Feature activation+0.932
to
Token to
Feature activation+0.446
university
Token university
Feature activation+3.900
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
knew
Token knew
Feature activation+0.000
that
Token that
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
a
Token a
Feature activation+0.000
red
Token red
Feature activation+0.000
shirt
Tokenshirt
Feature activation+1.161
freshman
Token freshman
Feature activation+3.991
in
Token in
Feature activation+0.230
2014
Token 2014
Feature activation+3.877
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
walk
Token walk
Feature activation+0.000
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000

INTERVAL 2.844 - 3.555
CONTAINS 0.004%

that
Token that
Feature activation+0.000
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
mine
Token mine
Feature activation+2.866
,
Token,
Feature activation+3.147
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
something
Token something
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.171
to
Token to
Feature activation+0.000
overcome
Token overcome
Feature activation+3.158
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
serious
Token serious
Feature activation+0.000
run
Token run
Feature activation+1.651
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.227
satisfying
Token satisfying
Feature activation+3.766
for
Token for
Feature activation+0.743
me
Token me
Feature activation+5.561
,
Token,
Feature activation+3.056
it
Token it
Feature activation+0.245
's
Token's
Feature activation+0.008
a
Token a
Feature activation+0.000
really
Token really
Feature activation+0.000
professional
Token professional
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.123
been
Token been
Feature activation+0.061
members
Token members
Feature activation+3.388
of
Token of
Feature activation+0.861
the
Token the
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
parliament
Token parliament
Feature activation+3.423
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
would
Token would
Feature activation+0.000
firmly
Token firmly
Feature activation+0.000
reject
Token reject
Feature activation+2.965
,
Token,
Feature activation+0.832
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
neither
Token neither
Feature activation+0.000

INTERVAL 2.133 - 2.844
CONTAINS 0.012%

admire
Token admire
Feature activation+0.000
r
Tokenr
Feature activation+0.344
of
Token of
Feature activation+0.000
B
Token B
Feature activation+0.000
ierce
Tokenierce
Feature activation+0.203
,
Token,
Feature activation+2.190
had
Token had
Feature activation+0.000
made
Token made
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.011
But
Token But
Feature activation+0.000
000
Token000
Feature activation+0.000
investment
Token investment
Feature activation+2.425
in
Token in
Feature activation+0.049
the
Token the
Feature activation+0.000
stock
Token stock
Feature activation+0.238
market
Token market
Feature activation+2.297
.
Token.
Feature activation+0.024
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Group
TokenGroup
Feature activation+0.000
pension
Token pension
Feature activation+0.000
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.140
more
Token more
Feature activation+0.000
products
Token products
Feature activation+1.847
and
Token and
Feature activation+0.000
services
Token services
Feature activation+2.300
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
post
Token post
Feature activation+0.870
office
Token office
Feature activation+1.657
network
Token network
Feature activation+1.672
sites
Token sites
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
legal
Token legal
Feature activation+0.000
protection
Token protection
Feature activation+2.238
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
NSA
TokenNSA
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
defend
Token defend
Feature activation+0.000
its
Token its
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+2.550
based
Token based
Feature activation+0.000
solely
Token solely
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.040
fact
Token fact
Feature activation+2.314

INTERVAL 1.422 - 2.133
CONTAINS 0.034%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
divul
Token divul
Feature activation+0.000
ge
Tokenge
Feature activation+0.429
exact
Token exact
Feature activation+0.000
figures
Token figures
Feature activation+2.066
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
also
Token also
Feature activation+0.000
claims
Token claims
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
Congressional
Token Congressional
Feature activation+0.000
Republicans
Token Republicans
Feature activation+1.570
to
Token to
Feature activation+0.000
shift
Token shift
Feature activation+0.000
Planned
Token Planned
Feature activation+0.000
Parenthood
Token Parenthood
Feature activation+0.000
funds
Token funds
Feature activation+0.222
driven
Token driven
Feature activation+0.082
giant
Token giant
Feature activation+0.000
predators
Token predators
Feature activation+0.256
off
Token off
Feature activation+0.000
their
Token their
Feature activation+0.000
prey
Token prey
Feature activation+1.958
and
Token and
Feature activation+0.000
har
Token har
Feature activation+0.000
ried
Tokenried
Feature activation+0.000
monstrous
Token monstrous
Feature activation+0.000
herb
Token herb
Feature activation+0.000
the
Token the
Feature activation+0.000
month
Token month
Feature activation+0.724
-
Token-
Feature activation+0.000
long
Tokenlong
Feature activation+0.000
rehearsal
Token rehearsal
Feature activation+1.494
run
Token run
Feature activation+1.608
in
Token in
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+1.486
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
would
Token would
Feature activation+0.000
provide
Token provide
Feature activation+0.949
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
press
Token press
Feature activation+1.552
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
letters
Token letters
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.711 - 1.422
CONTAINS 0.112%

not
Token not
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
companies
Token companies
Feature activation+0.000
together
Token together
Feature activation+0.793
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
head
Token head
Feature activation+0.749
-
Token -
Feature activation+0.000
one
Token one
Feature activation+0.000
an
Token an
Feature activation+0.000
entire
Token entire
Feature activation+0.000
chicken
Token chicken
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
stuffing
Token stuffing
Feature activation+1.173
and
Token and
Feature activation+0.000
just
Token just
Feature activation+0.000
serve
Token serve
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.260
you
Token you
Feature activation+0.835
do
Token do
Feature activation+2.896
for
Token for
Feature activation+0.054
God
Token God
Feature activation+3.124
?
Token?
Feature activation+0.198
I
Token I
Feature activation+0.000
't
Token't
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.661
any
Token any
Feature activation+0.000
favors
Token favors
Feature activation+1.050
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
cream
Token cream
Feature activation+0.000
would
Token would
Feature activation+0.000
rise
Token rise
Feature activation+0.840
have
Token have
Feature activation+0.878
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
polls
Token polls
Feature activation+0.491
were
Token were
Feature activation+0.000
closer
Token closer
Feature activation+0.833
.
Token.
Feature activation+0.156
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.000 - 0.711
CONTAINS 99.833%

ans
Tokenans
Feature activation+0.396
was
Token was
Feature activation+0.000
divine
Token divine
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
.
Token.
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
was
Tokenwas
Feature activation+0.000
very
Token very
Feature activation+0.000
Values
TokenValues
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Anti
TokenAnti
Feature activation+0.000
-
Token-
Feature activation+0.000
Opp
TokenOpp
Feature activation+0.000
ression
Tokenression
Feature activation+0.000
-
Token -
Feature activation+0.000
L
Token L
Feature activation+0.000
SP
TokenSP
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
guests
Token guests
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
instant
Token instant
Feature activation+0.000
he
Token he
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
tribal
Token tribal
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
needed
Token needed
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
want
Token want
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
played
Token played
Feature activation+0.000
in
Token in
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
?
Token?
Feature activation+0.000
Do
Token Do
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 H10.5: (feature 12087)

TOP ACTIVATIONS
MAX = 8.821

for
Token for
Feature activation+0.000
organizers
Token organizers
Feature activation+6.356
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+4.922
their
Token their
Feature activation+0.000
work
Token work
Feature activation+8.821
than
Token than
Feature activation+0.163
through
Token through
Feature activation+0.000
writing
Token writing
Feature activation+0.000
science
Token science
Feature activation+0.175
fiction
Token fiction
Feature activation+0.696
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.006
threat
Token threat
Feature activation+0.936
to
Token to
Feature activation+0.958
adult
Token adult
Feature activation+0.472
health
Token health
Feature activation+7.349
than
Token than
Feature activation+0.000
we
Token we
Feature activation+0.000
had
Token had
Feature activation+0.000
previously
Token previously
Feature activation+0.000
imagined
Token imagined
Feature activation+0.235
easier
Token easier
Feature activation+0.000
way
Token way
Feature activation+2.239
to
Token to
Feature activation+0.000
start
Token start
Feature activation+2.730
this
Token this
Feature activation+3.795
habit
Token habit
Feature activation+7.004
than
Token than
Feature activation+0.000
through
Token through
Feature activation+0.000
these
Token these
Feature activation+0.000
iconic
Token iconic
Feature activation+0.000
quotes
Token quotes
Feature activation+0.000
belong
Token belong
Feature activation+2.111
to
Token to
Feature activation+1.045
America
Token America
Feature activation+4.339
's
Token's
Feature activation+0.000
middle
Token middle
Feature activation+1.124
class
Token class
Feature activation+6.851
.
Token.
Feature activation+0.032
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Great
Token Great
Feature activation+0.000
trust
Token trust
Feature activation+0.000
scientists
Token scientists
Feature activation+3.215
to
Token to
Feature activation+0.009
tell
Token tell
Feature activation+1.690
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+6.611
(
Token (
Feature activation+1.149
79
Token79
Feature activation+0.000
%)
Token%)
Feature activation+4.775
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
make
Token make
Feature activation+0.475
the
Token the
Feature activation+0.000
move
Token move
Feature activation+5.230
to
Token to
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+6.484
than
Token than
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
so
Token so
Feature activation+0.000
what
Token what
Feature activation+0.000
better
Token better
Feature activation+0.000
venue
Token venue
Feature activation+2.015
for
Token for
Feature activation+0.000
organizers
Token organizers
Feature activation+6.356
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+4.922
their
Token their
Feature activation+0.000
work
Token work
Feature activation+8.821
than
Token than
Feature activation+0.163
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.082
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+6.251
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+0.000
cause
Token cause
Feature activation+1.091
of
Token of
Feature activation+0.000
childhood
Token childhood
Feature activation+0.890
mortality
Token mortality
Feature activation+6.063
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+0.000
thought
Token thought
Feature activation+0.048
.
Token.
Feature activation+0.058
If
Token If
Feature activation+0.000
lot
Token lot
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+2.201
things
Token things
Feature activation+3.120
here
Token here
Feature activation+6.026
.
Token.
Feature activation+1.015
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.324
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
more
Token more
Feature activation+0.000
effective
Token effective
Feature activation+1.298
at
Token at
Feature activation+0.000
sway
Token sway
Feature activation+1.370
ing
Tokening
Feature activation+1.930
opinion
Token opinion
Feature activation+5.998
.
Token.
Feature activation+0.090
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
gains
Token gains
Feature activation+0.000
rate
Token rate
Feature activation+0.613
on
Token on
Feature activation+0.000
most
Token most
Feature activation+0.071
other
Token other
Feature activation+0.000
income
Token income
Feature activation+5.972
they
Token they
Feature activation+0.247
earn
Token earn
Feature activation+5.179
because
Token because
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
no
Token no
Feature activation+0.000
better
Token better
Feature activation+0.000
way
Token way
Feature activation+3.084
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+5.881
than
Token than
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
J
Token J
Feature activation+0.000
CT
TokenCT
Feature activation+2.806
oxidation
Token oxidation
Feature activation+1.687
involved
Token involved
Feature activation+1.271
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.307
sample
Token sample
Feature activation+5.753
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Che
Token Che
Feature activation+0.000
Min
TokenMin
Feature activation+0.000
Deputy
Token Deputy
Feature activation+0.000
have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
more
Token more
Feature activation+0.000
days
Token days
Feature activation+0.850
behind
Token behind
Feature activation+0.000
us
Token us
Feature activation+5.703
than
Token than
Feature activation+0.000
ahead
Token ahead
Feature activation+0.388
.
Token.
Feature activation+0.274
We
Token We
Feature activation+0.000
make
Token make
Feature activation+0.000
more
Token more
Feature activation+0.000
optimistic
Token optimistic
Feature activation+2.078
now
Token now
Feature activation+1.565
for
Token for
Feature activation+0.240
a
Token a
Feature activation+0.288
solution
Token solution
Feature activation+5.577
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.922
"
Token "
Feature activation+1.787
be
Token be
Feature activation+0.000
fall
Tokenfall
Feature activation+4.942
you
Token you
Feature activation+4.390
in
Token in
Feature activation+0.620
this
Token this
Feature activation+1.351
life
Token life
Feature activation+5.567
,
Token,
Feature activation+4.645
than
Token than
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
watching
Token watching
Feature activation+0.112
TV
Token TV
Feature activation+3.301
and
Token and
Feature activation+0.337
using
Token using
Feature activation+0.000
electronic
Token electronic
Feature activation+0.000
devices
Token devices
Feature activation+5.566
than
Token than
Feature activation+0.000
kids
Token kids
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
affluent
Token affluent
Feature activation+0.000
was
Token was
Feature activation+0.000
required
Token required
Feature activation+0.005
to
Token to
Feature activation+0.000
break
Token break
Feature activation+1.423
Mus
Token Mus
Feature activation+3.461
skin
Token skin
Feature activation+5.540
relative
Token relative
Feature activation+0.000
to
Token to
Feature activation+0.000
A
Token A
Feature activation+0.000
com
Tokencom
Feature activation+0.000
ys
Tokenys
Feature activation+3.375
to
Token to
Feature activation+0.000
play
Token play
Feature activation+2.030
at
Token at
Feature activation+1.316
high
Token high
Feature activation+0.972
competitive
Token competitive
Feature activation+0.746
level
Token level
Feature activation+5.519
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.202
N
TokenN
Feature activation+0.000
igel
Tokenigel
Feature activation+0.000
Short
Token Short
Feature activation+0.000

Top DFA by src position
MAX = 6.511

other
Token other
Feature activation+0.009
Top resid features:
worlds
Token worlds
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
so
Token so
Feature activation+0.007
Top resid features:
what
Token what
Feature activation-0.004
Top resid features:
better
Token better
Feature activation+6.511
Top resid features:
venue
Token venue
Feature activation+1.552
Top resid features:
for
Token for
Feature activation+0.249
Top resid features:
organizers
Token organizers
Feature activation+0.116
Top resid features:
to
Token to
Feature activation+0.524
Top resid features:
explore
Token explore
Feature activation+0.156
Top resid features:
clear
Token clear
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
malaria
Token malaria
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
greater
Token greater
Feature activation+3.835
Top resid features:
long
Token long
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
term
Tokenterm
Feature activation+1.383
Top resid features:
threat
Token threat
Feature activation+2.231
Top resid features:
to
Token to
Feature activation+0.149
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation-0.003
Top resid features:
no
Token no
Feature activation+0.013
Top resid features:
easier
Token easier
Feature activation+2.585
Top resid features:
way
Token way
Feature activation+3.958
Top resid features:
to
Token to
Feature activation+0.785
Top resid features:
start
Token start
Feature activation+0.065
Top resid features:
this
Token this
Feature activation+0.012
Top resid features:
habit
Token habit
Feature activation+0.013
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
there
Token there
Feature activation-0.002
Top resid features:
probably
Token probably
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
no
Token no
Feature activation+0.025
Top resid features:
better
Token better
Feature activation+4.382
Top resid features:
time
Token time
Feature activation+2.122
Top resid features:
to
Token to
Feature activation+0.291
Top resid features:
belong
Token belong
Feature activation+0.227
Top resid features:
to
Token to
Feature activation+0.026
Top resid features:
America
Token America
Feature activation+0.105
Top resid features:
very
Token very
Feature activation-0.009
Top resid features:
high
Token high
Feature activation-0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.048
Top resid features:
more
Token more
Feature activation+0.735
Top resid features:
people
Token people
Feature activation+2.442
Top resid features:
trust
Token trust
Feature activation+2.760
Top resid features:
scientists
Token scientists
Feature activation+0.667
Top resid features:
to
Token to
Feature activation+0.408
Top resid features:
tell
Token tell
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
truth
Token truth
Feature activation+0.048
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
agen
Tokenagen
Feature activation-0.001
Top resid features:
admits
Token admits
Feature activation-0.005
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
more
Token more
Feature activation+0.623
Top resid features:
determined
Token determined
Feature activation+4.161
Top resid features:
to
Token to
Feature activation+1.579
Top resid features:
make
Token make
Feature activation+0.149
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
move
Token move
Feature activation+0.364
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
other
Token other
Feature activation+0.024
Top resid features:
worlds
Token worlds
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
so
Token so
Feature activation+0.016
Top resid features:
what
Token what
Feature activation-0.005
Top resid features:
better
Token better
Feature activation+5.531
Top resid features:
venue
Token venue
Feature activation+0.849
Top resid features:
for
Token for
Feature activation+0.296
Top resid features:
organizers
Token organizers
Feature activation+0.083
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
explore
Token explore
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
"
Token"
Feature activation+0.015
Top resid features:
I
TokenI
Feature activation+0.002
Top resid features:
would
Token would
Feature activation-0.032
Top resid features:
no
Token no
Feature activation+0.047
Top resid features:
more
Token more
Feature activation+5.183
Top resid features:
split
Token split
Feature activation+0.531
Top resid features:
up
Token up
Feature activation+0.913
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
BBC
Token BBC
Feature activation+0.048
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
might
Token might
Feature activation-0.061
Top resid features:
be
Token be
Feature activation-0.008
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
far
Token far
Feature activation+0.083
Top resid features:
more
Token more
Feature activation+2.255
Top resid features:
important
Token important
Feature activation+2.563
Top resid features:
cause
Token cause
Feature activation+1.438
Top resid features:
of
Token of
Feature activation+0.055
Top resid features:
childhood
Token childhood
Feature activation+0.019
Top resid features:
mortality
Token mortality
Feature activation+0.211
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
lot
Token lot
Feature activation+0.040
Top resid features:
cheaper
Token cheaper
Feature activation+1.648
Top resid features:
to
Token to
Feature activation+3.883
Top resid features:
make
Token make
Feature activation+0.469
Top resid features:
things
Token things
Feature activation+0.263
Top resid features:
here
Token here
Feature activation+0.135
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.006
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
often
Token often
Feature activation+0.013
Top resid features:
more
Token more
Feature activation+1.727
Top resid features:
effective
Token effective
Feature activation+1.882
Top resid features:
at
Token at
Feature activation+2.604
Top resid features:
sway
Token sway
Feature activation+0.078
Top resid features:
ing
Tokening
Feature activation+0.096
Top resid features:
opinion
Token opinion
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
pay
Token pay
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
lower
Token lower
Feature activation+1.535
Top resid features:
capital
Token capital
Feature activation+0.005
Top resid features:
gains
Token gains
Feature activation+0.043
Top resid features:
rate
Token rate
Feature activation+4.522
Top resid features:
on
Token on
Feature activation+0.156
Top resid features:
most
Token most
Feature activation+0.060
Top resid features:
other
Token other
Feature activation+0.077
Top resid features:
income
Token income
Feature activation+0.034
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
scoring
Token scoring
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
there
Token there
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
no
Token no
Feature activation+0.010
Top resid features:
better
Token better
Feature activation+2.921
Top resid features:
way
Token way
Feature activation+1.886
Top resid features:
to
Token to
Feature activation+1.007
Top resid features:
do
Token do
Feature activation+0.189
Top resid features:
it
Token it
Feature activation+0.274
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
There
TokenThere
Feature activation-0.008
Top resid features:
's
Token's
Feature activation-0.006
Top resid features:
more
Token more
Feature activation+1.944
Top resid features:
oxidation
Token oxidation
Feature activation+0.800
Top resid features:
involved
Token involved
Feature activation+2.527
Top resid features:
in
Token in
Feature activation+0.716
Top resid features:
the
Token the
Feature activation+0.076
Top resid features:
new
Token new
Feature activation+0.078
Top resid features:
sample
Token sample
Feature activation+0.106
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.085
Top resid features:
have
Token have
Feature activation-0.036
Top resid features:
had
Token had
Feature activation-0.022
Top resid features:
more
Token more
Feature activation+0.760
Top resid features:
days
Token days
Feature activation+5.051
Top resid features:
behind
Token behind
Feature activation+0.223
Top resid features:
us
Token us
Feature activation+0.209
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
ahead
Token ahead
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.035
Top resid features:
F
TokenF
Feature activation+0.004
Top resid features:
ol
Tokenol
Feature activation+0.000
Top resid features:
ks
Tokenks
Feature activation-0.019
Top resid features:
are
Token are
Feature activation+0.010
Top resid features:
more
Token more
Feature activation+2.061
Top resid features:
optimistic
Token optimistic
Feature activation+1.938
Top resid features:
now
Token now
Feature activation+1.431
Top resid features:
for
Token for
Feature activation+0.215
Top resid features:
a
Token a
Feature activation+0.100
Top resid features:
solution
Token solution
Feature activation+0.309
Top resid features:
worthy
Token worthy
Feature activation-0.009
Top resid features:
men
Token men
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
no
Token no
Feature activation-0.005
Top resid features:
greater
Token greater
Feature activation+1.638
Top resid features:
misery
Token misery
Feature activation+1.156
Top resid features:
can
Token can
Feature activation+0.380
Top resid features:
be
Token be
Feature activation+0.646
Top resid features:
fall
Tokenfall
Feature activation+0.639
Top resid features:
you
Token you
Feature activation+0.616
Top resid features:
lower
Token lower
Feature activation+0.019
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
income
Tokenincome
Feature activation+0.004
Top resid features:
families
Token families
Feature activation+0.014
Top resid features:
spend
Token spend
Feature activation+0.043
Top resid features:
more
Token more
Feature activation+2.756
Top resid features:
time
Token time
Feature activation+2.617
Top resid features:
watching
Token watching
Feature activation+0.129
Top resid features:
TV
Token TV
Feature activation+0.243
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
using
Token using
Feature activation+0.033
Top resid features:
77
Token 77
Feature activation+0.002
Top resid features:
times
Token times
Feature activation+0.071
Top resid features:
more
Token more
Feature activation+1.387
Top resid features:
energy
Token energy
Feature activation+0.404
Top resid features:
was
Token was
Feature activation+0.336
Top resid features:
required
Token required
Feature activation+3.327
Top resid features:
to
Token to
Feature activation+0.354
Top resid features:
break
Token break
Feature activation+0.153
Top resid features:
Mus
Token Mus
Feature activation+0.008
Top resid features:
skin
Token skin
Feature activation+0.081
Top resid features:
relative
Token relative
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.031
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
men
Token men
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+1.834
Top resid features:
able
Token able
Feature activation+2.880
Top resid features:
to
Token to
Feature activation+0.894
Top resid features:
play
Token play
Feature activation+0.092
Top resid features:
at
Token at
Feature activation+0.184
Top resid features:
high
Token high
Feature activation+0.033
Top resid features:
competitive
Token competitive
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.03

Head 4: 0.04

Head 5: 0.65

Head 6: 0.01

Head 7: 0.02

Head 8: 0.02

Head 9: 0.11

Head 10: 0.01

Head 11: 0.03

Positive logits

than12.29

than11.46

Than9.10

compared5.50

rather4.38

TH3.84

rather3.62

then3.62

fewer3.53

soDeliveryDate3.52

Th3.47

then3.44

THEN3.42

longer3.27

versus3.17

wiser3.08

Compared3.04

vs3.01

ado3.01

kson2.97

Negative logits

Powered-2.79

escap-2.75

Lakes-2.75

again-2.72

Anyone-2.63

(){-2.60

anybody-2.59

Article-2.56

Glover-2.52

insepar-2.48

ritz-2.44

unmist-2.43

atom-2.42

Aff-2.40

}}}-2.35

slightest-2.33

everlasting-2.32

cery-2.29

anyone-2.27

��-2.27

INTERVAL 7.939 - 8.821
CONTAINS 0.000%

for
Token for
Feature activation+0.000
organizers
Token organizers
Feature activation+6.356
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+4.922
their
Token their
Feature activation+0.000
work
Token work
Feature activation+8.821
than
Token than
Feature activation+0.163
through
Token through
Feature activation+0.000
writing
Token writing
Feature activation+0.000
science
Token science
Feature activation+0.175
fiction
Token fiction
Feature activation+0.696

INTERVAL 7.057 - 7.939
CONTAINS 0.000%

-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.006
threat
Token threat
Feature activation+0.936
to
Token to
Feature activation+0.958
adult
Token adult
Feature activation+0.472
health
Token health
Feature activation+7.349
than
Token than
Feature activation+0.000
we
Token we
Feature activation+0.000
had
Token had
Feature activation+0.000
previously
Token previously
Feature activation+0.000
imagined
Token imagined
Feature activation+0.235

INTERVAL 6.174 - 7.057
CONTAINS 0.001%

no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.082
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+6.251
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.000
so
Token so
Feature activation+0.000
what
Token what
Feature activation+0.000
better
Token better
Feature activation+0.000
venue
Token venue
Feature activation+2.015
for
Token for
Feature activation+0.000
organizers
Token organizers
Feature activation+6.356
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+4.922
their
Token their
Feature activation+0.000
work
Token work
Feature activation+8.821
than
Token than
Feature activation+0.163
make
Token make
Feature activation+0.475
the
Token the
Feature activation+0.000
move
Token move
Feature activation+5.230
to
Token to
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+6.484
than
Token than
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
belong
Token belong
Feature activation+2.111
to
Token to
Feature activation+1.045
America
Token America
Feature activation+4.339
's
Token's
Feature activation+0.000
middle
Token middle
Feature activation+1.124
class
Token class
Feature activation+6.851
.
Token.
Feature activation+0.032
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Great
Token Great
Feature activation+0.000
trust
Token trust
Feature activation+0.000
scientists
Token scientists
Feature activation+3.215
to
Token to
Feature activation+0.009
tell
Token tell
Feature activation+1.690
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+6.611
(
Token (
Feature activation+1.149
79
Token79
Feature activation+0.000
%)
Token%)
Feature activation+4.775
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 5.292 - 6.174
CONTAINS 0.002%

and
Token and
Feature activation+0.000
take
Token take
Feature activation+0.000
it
Token it
Feature activation+0.763
to
Token to
Feature activation+0.010
the
Token the
Feature activation+0.000
masses
Token masses
Feature activation+5.335
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
large
Token large
Feature activation+0.000
no
Token no
Feature activation+0.000
better
Token better
Feature activation+0.000
way
Token way
Feature activation+3.084
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+5.881
than
Token than
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
J
Token J
Feature activation+0.000
CT
TokenCT
Feature activation+2.806
more
Token more
Feature activation+0.000
optimistic
Token optimistic
Feature activation+2.078
now
Token now
Feature activation+1.565
for
Token for
Feature activation+0.240
a
Token a
Feature activation+0.288
solution
Token solution
Feature activation+5.577
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.922
"
Token "
Feature activation+1.787
operating
Token operating
Feature activation+2.783
models
Token models
Feature activation+5.079
,
Token,
Feature activation+1.105
processes
Token processes
Feature activation+0.272
and
Token and
Feature activation+0.000
governance
Token governance
Feature activation+5.434
.
Token.
Feature activation+0.000
Ent
Token Ent
Feature activation+0.000
rust
Tokenrust
Feature activation+0.000
ing
Tokening
Feature activation+0.000
customer
Token customer
Feature activation+0.000
somebody
Token somebody
Feature activation+2.323
like
Token like
Feature activation+0.069
Thor
Token Thor
Feature activation+3.737
or
Token or
Feature activation+0.071
The
Token The
Feature activation+0.000
Vision
Token Vision
Feature activation+5.482
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
you
Token you
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.000

INTERVAL 4.410 - 5.292
CONTAINS 0.005%

FU
TokenFU
Feature activation+0.000
more
Token more
Feature activation+0.000
steadfast
Token steadfast
Feature activation+0.402
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
opposition
Token opposition
Feature activation+5.040
to
Token to
Feature activation+0.000
creeping
Token creeping
Feature activation+0.000
professionalism
Token professionalism
Feature activation+5.348
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
government
Token government
Feature activation+3.104
's
Token's
Feature activation+0.000
financial
Token financial
Feature activation+0.000
health
Token health
Feature activation+4.444
than
Token than
Feature activation+0.000
whether
Token whether
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
determined
Token determined
Feature activation+0.894
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.475
the
Token the
Feature activation+0.000
move
Token move
Feature activation+5.230
to
Token to
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+6.484
than
Token than
Feature activation+0.000
he
Token he
Feature activation+0.000
no
Token no
Feature activation+0.000
greater
Token greater
Feature activation+0.000
misery
Token misery
Feature activation+0.813
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
fall
Tokenfall
Feature activation+4.942
you
Token you
Feature activation+4.390
in
Token in
Feature activation+0.620
this
Token this
Feature activation+1.351
life
Token life
Feature activation+5.567
,
Token,
Feature activation+4.645
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
side
Token side
Feature activation+4.557
of
Token of
Feature activation+0.369
the
Token the
Feature activation+0.000
pond
Token pond
Feature activation+5.033
throughout
Token throughout
Feature activation+1.165
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.340
its
Token its
Feature activation+0.000
history
Token history
Feature activation+4.156

INTERVAL 3.528 - 4.410
CONTAINS 0.011%

protect
Token protect
Feature activation+0.425
data
Token data
Feature activation+2.135
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
payment
Token payment
Feature activation+0.000
ecosystem
Token ecosystem
Feature activation+3.609
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Intel
TokenIntel
Feature activation+0.000
attitudes
Token attitudes
Feature activation+0.762
and
Token and
Feature activation+0.000
outlook
Token outlook
Feature activation+1.073
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+3.742
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
party
Token party
Feature activation+0.000
has
Token has
Feature activation+0.000
ever
Token ever
Feature activation+0.000
the
Token the
Feature activation+0.000
timing
Token timing
Feature activation+3.593
of
Token of
Feature activation+0.519
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+4.259
itself
Token itself
Feature activation+4.130
,
Token,
Feature activation+1.416
seeing
Token seeing
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
skipped
Token skipped
Feature activation+0.000
more
Token more
Feature activation+0.000
settlements
Token settlements
Feature activation+1.582
ended
Token ended
Feature activation+1.345
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+3.714
,
Token,
Feature activation+0.441
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
legal
Token legal
Feature activation+0.000
more
Token more
Feature activation+0.000
useful
Token useful
Feature activation+0.736
to
Token to
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Pul
Token Pul
Feature activation+0.000
is
Tokenis
Feature activation+3.793
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
midfielder
Token midfielder
Feature activation+3.882
than
Token than
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 2.646 - 3.528
CONTAINS 0.022%

correspond
Token correspond
Feature activation+0.000
more
Token more
Feature activation+0.000
closely
Token closely
Feature activation+0.605
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+1.240
prototypes
Token prototypes
Feature activation+2.793
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.000
pred
Token pred
Feature activation+0.000
more
Token more
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
latter
Token latter
Feature activation+2.759
scenario
Token scenario
Feature activation+2.966
:
Token:
Feature activation+0.088
we
Token we
Feature activation+0.097
want
Token want
Feature activation+0.000
our
Token our
Feature activation+0.000
session
Token session
Feature activation+0.000
commercially
Token commercially
Feature activation+0.000
viable
Token viable
Feature activation+0.000
alternative
Token alternative
Feature activation+1.642
source
Token source
Feature activation+1.933
of
Token of
Feature activation+0.000
electricity
Token electricity
Feature activation+2.870
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
phot
Token phot
Feature activation+0.000
in
Token in
Feature activation+0.000
1
Token 1
Feature activation+0.000
/
Token/
Feature activation+0.000
2
Token2
Feature activation+0.394
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+3.445
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
has
Token has
Feature activation+0.000
all
Token all
Feature activation+0.000
easier
Token easier
Feature activation+0.000
to
Token to
Feature activation+0.000
drive
Token drive
Feature activation+0.677
to
Token to
Feature activation+0.350
the
Token the
Feature activation+0.000
hoop
Token hoop
Feature activation+3.302
this
Token this
Feature activation+0.091
way
Token way
Feature activation+3.245
.
Token.
Feature activation+0.104
When
Token When
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 1.764 - 2.646
CONTAINS 0.045%

better
Token better
Feature activation+0.000
understanding
Token understanding
Feature activation+1.200
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nuanced
Token nuanced
Feature activation+0.000
approach
Token approach
Feature activation+2.064
those
Token those
Feature activation+0.000
members
Token members
Feature activation+1.015
were
Token were
Feature activation+0.374
taking
Token taking
Feature activation+1.793
.
Token.
Feature activation+0.000
made
Token made
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
older
Token older
Feature activation+0.000
styles
Token styles
Feature activation+0.450
heet
Tokenheet
Feature activation+1.899
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Best
TokenBest
Feature activation+0.000
things
Token things
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
control
Token control
Feature activation+0.546
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+0.000
thought
Token thought
Feature activation+1.844
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.216
to
Token to
Feature activation+0.075
be
Token be
Feature activation+0.000
robbed
Token robbed
Feature activation+2.418
,
Token,
Feature activation+0.075
or
Token or
Feature activation+0.000
injured
Token injured
Feature activation+1.391
,
Token,
Feature activation+1.910
or
Token or
Feature activation+0.092
find
Token find
Feature activation+0.000
more
Token more
Feature activation+0.000
information
Token information
Feature activation+0.260
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
books
Token books
Feature activation+2.220
there
Token there
Feature activation+2.230
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
my
Token my
Feature activation+0.000

INTERVAL 0.882 - 1.764
CONTAINS 0.108%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
are
Token are
Feature activation+0.000
often
Token often
Feature activation+0.000
more
Token more
Feature activation+0.000
effective
Token effective
Feature activation+1.298
at
Token at
Feature activation+0.000
sway
Token sway
Feature activation+1.370
ing
Tokening
Feature activation+1.930
opinion
Token opinion
Feature activation+5.998
.
Token.
Feature activation+0.090
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
better
Token better
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+1.710
have
Token have
Feature activation+0.406
meaningful
Token meaningful
Feature activation+0.000
access
Token access
Feature activation+2.553
to
Token to
Feature activation+0.000
affordable
Token affordable
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
financially
Token financially
Feature activation+0.000
better
Token better
Feature activation+0.000
off
Token off
Feature activation+1.094
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+1.746
country
Token country
Feature activation+1.991
.
Token.
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+1.453
,
Token,
Feature activation+0.000
(
Token (
Feature activation+1.909
yet
Tokenyet
Feature activation+0.000
)
Token)
Feature activation+0.522
people
Token people
Feature activation+0.717
being
Token being
Feature activation+0.000
left
Token left
Feature activation+0.000
stranded
Token stranded
Feature activation+0.615
in
Token in
Feature activation+0.000
legal
Token legal
Feature activation+0.000
limbo
Token limbo
Feature activation+1.023
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
Balkans
Token Balkans
Feature activation+0.823
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.882
CONTAINS 99.806%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
of
Token of
Feature activation+0.000
per
Token per
Feature activation+0.000
miss
Tokenmiss
Feature activation+0.000
iveness
Tokeniveness
Feature activation+0.000
extended
Token extended
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
establishment
Token establishment
Feature activation+0.000
to
Token to
Feature activation+0.000
target
Token target
Feature activation+0.000
the
Token the
Feature activation+0.000
present
Token present
Feature activation+0.000
demand
Token demand
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
avoids
Token avoids
Feature activation+0.000
the
Token the
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
when
Token when
Feature activation+0.000
per
Tokenper
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
:
Token:
Feature activation+0.000
E
Token E
Feature activation+0.000
udic
Tokenudic
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
:
Token:
Feature activation+0.000
a
Token a
Feature activation+0.000
theoretical
Token theoretical
Feature activation+0.000
argument
Token argument
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
carriers
Token carriers
Feature activation+0.000
have
Token have
Feature activation+0.000
already
Token already
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.000
individual
Token individual
Feature activation+0.000
market
Token market
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
biggest
Token biggest
Feature activation+0.000
global
Token global
Feature activation+0.000
PR
Token PR
Feature activation+0.000
and
Token and
Feature activation+0.000
communications
Token communications
Feature activation+0.000
groups
Token groups
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H10.5: (feature 10723)

TOP ACTIVATIONS
MAX = 5.350

would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
won
Token won
Feature activation+3.460
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+5.350
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.021
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.011
skeptical
Token skeptical
Feature activation+0.623
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.968
a
Token a
Feature activation+4.500
more
Token more
Feature activation+0.110
humble
Token humble
Feature activation+0.000
person
Token person
Feature activation+0.097
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
southern
Token southern
Feature activation+0.000
periphery
Token periphery
Feature activation+0.811
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Euro
Token Euro
Feature activation+0.137
zone
Tokenzone
Feature activation+4.362
.
Token.
Feature activation+0.000
Perhaps
Token Perhaps
Feature activation+0.000
she
Token she
Feature activation+0.540
would
Token would
Feature activation+0.468
have
Token have
Feature activation+0.278
.
Token.
Feature activation+0.000
Imagine
Token Imagine
Feature activation+0.000
what
Token what
Feature activation+0.075
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+4.100
if
Token if
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Per
Token Per
Feature activation+0.000
ino
Tokenino
Feature activation+1.342
would
Token would
Feature activation+0.173
have
Token have
Feature activation+0.147
taken
Token taken
Feature activation+0.952
him
Token him
Feature activation+1.032
more
Token more
Feature activation+0.040
seriously
Token seriously
Feature activation+4.043
.
Token.
Feature activation+0.087
Instead
Token Instead
Feature activation+0.000
the
Token the
Feature activation+0.000
Australians
Token Australians
Feature activation+0.000
laughed
Token laughed
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
given
Token given
Feature activation+1.608
the
Token the
Feature activation+0.000
belt
Token belt
Feature activation+1.467
back
Token back
Feature activation+4.000
.
Token.
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
different
Token different
Feature activation+0.000
44
Token 44
Feature activation+2.512
on
Token on
Feature activation+0.164
13
Token 13
Feature activation+0.144
January
Token January
Feature activation+1.085
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.933
.
Token.
Feature activation+0.113
He
Token He
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.030
been
Token been
Feature activation+0.141
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
done
Token done
Feature activation+1.063
a
Token a
Feature activation+3.773
better
Token better
Feature activation+0.000
job
Token job
Feature activation+0.993
.
Token.
Feature activation+0.064
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
swept
Token swept
Feature activation+0.748
under
Token under
Feature activation+1.006
the
Token the
Feature activation+0.000
rug
Token rug
Feature activation+3.667
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
have
Token have
Feature activation+0.743
taken
Token taken
Feature activation+0.325
out
Token out
Feature activation+1.483
the
Token the
Feature activation+0.000
body
Token body
Feature activation+1.275
guards
Tokenguards
Feature activation+3.489
.
Token.
Feature activation+0.419
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.140
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.020
is
Token is
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
won
Token won
Feature activation+3.460
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+5.350
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.021
not
Token not
Feature activation+0.009
have
Token have
Feature activation+0.000
called
Token called
Feature activation+0.000
herself
Token herself
Feature activation+0.000
a
Token a
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+3.440
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.010
been
Token been
Feature activation+0.287
even
Token even
Feature activation+1.202
more
Token more
Feature activation+0.000
bizarre
Token bizarre
Feature activation+3.369
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
National
Token National
Feature activation+0.000
Post
Token Post
Feature activation+0.000
said
Token said
Feature activation+0.000
would
Token would
Feature activation+0.353
have
Token have
Feature activation+0.691
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+2.849
from
Token from
Feature activation+0.000
behind
Token behind
Feature activation+3.363
each
Token each
Feature activation+0.000
other
Token other
Feature activation+2.790
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.325
wouldn
Token wouldn
Feature activation+0.000
admire
Token admire
Feature activation+0.000
r
Tokenr
Feature activation+0.049
of
Token of
Feature activation+0.000
B
Token B
Feature activation+0.000
ierce
Tokenierce
Feature activation+0.087
,
Token,
Feature activation+3.281
had
Token had
Feature activation+0.040
made
Token made
Feature activation+0.660
one
Token one
Feature activation+0.331
.
Token.
Feature activation+0.434
But
Token But
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.157
it
Token it
Feature activation+2.791
much
Token much
Feature activation+1.266
clearer
Token clearer
Feature activation+3.279
he
Token he
Feature activation+0.016
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
t
Tokent
Feature activation+0.561
have
Token have
Feature activation+0.508
stood
Token stood
Feature activation+0.669
in
Token in
Feature activation+0.284
her
Token her
Feature activation+0.000
way
Token way
Feature activation+3.278
.
Token.
Feature activation+0.129
If
Token If
Feature activation+0.000
it
Token it
Feature activation+1.374
had
Token had
Feature activation+0.912
had
Token had
Feature activation+1.088
have
Token have
Feature activation+0.070
done
Token done
Feature activation+0.029
this
Token this
Feature activation+1.266
much
Token much
Feature activation+0.528
more
Token more
Feature activation+0.522
subtly
Token subtly
Feature activation+3.267
.
Token.
Feature activation+0.000
As
TokenAs
Feature activation+0.000
we
Token we
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
in
Token in
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.313
won
Token won
Feature activation+1.464
hand
Token hand
Feature activation+0.000
ily
Tokenily
Feature activation+3.199
.
Token.
Feature activation+0.054
But
Token But
Feature activation+0.000
Yanukovych
Token Yanukovych
Feature activation+0.270
twice
Token twice
Feature activation+0.129
served
Token served
Feature activation+0.000
liked
Token liked
Feature activation+0.201
to
Token to
Feature activation+0.043
stay
Token stay
Feature activation+1.005
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Sunday
Token Sunday
Feature activation+3.144
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.640
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+2.776
,
Token,
Feature activation+1.915

Top DFA by src position
MAX = 5.661

,
Token,
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
whether
Token whether
Feature activation+0.001
Top resid features:
Trump
Token Trump
Feature activation-0.001
Top resid features:
would
Token would
Feature activation+0.228
Top resid features:
have
Token have
Feature activation+5.661
Top resid features:
won
Token won
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
White
Token White
Feature activation-0.003
Top resid features:
House
Token House
Feature activation+0.022
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
couldn
Token couldn
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
t
Tokent
Feature activation+0.174
Top resid features:
have
Token have
Feature activation+2.833
Top resid features:
been
Token been
Feature activation+1.975
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
humble
Token humble
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.000
Top resid features:
Perhaps
Token Perhaps
Feature activation+0.015
Top resid features:
Ms
Token Ms
Feature activation-0.002
Top resid features:
Merkel
Token Merkel
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.100
Top resid features:
not
Token not
Feature activation+0.765
Top resid features:
have
Token have
Feature activation+3.626
Top resid features:
let
Token let
Feature activation+0.156
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
entire
Token entire
Feature activation+0.008
Top resid features:
southern
Token southern
Feature activation-0.010
Top resid features:
periphery
Token periphery
Feature activation+0.015
Top resid features:
others
Token others
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
Imagine
Token Imagine
Feature activation+0.050
Top resid features:
what
Token what
Feature activation+0.045
Top resid features:
would
Token would
Feature activation+1.074
Top resid features:
have
Token have
Feature activation+3.128
Top resid features:
happened
Token happened
Feature activation+0.231
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
Ms
Token Ms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Per
Token Per
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.005
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
they
Token they
Feature activation+0.224
Top resid features:
would
Token would
Feature activation+1.281
Top resid features:
have
Token have
Feature activation+2.447
Top resid features:
taken
Token taken
Feature activation+0.014
Top resid features:
him
Token him
Feature activation+0.040
Top resid features:
more
Token more
Feature activation+0.094
Top resid features:
seriously
Token seriously
Feature activation+0.049
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
erv
Tokenerv
Feature activation+0.001
Top resid features:
ingly
Tokeningly
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
I
Token I
Feature activation+0.009
Top resid features:
should
Token should
Feature activation+0.685
Top resid features:
have
Token have
Feature activation+3.482
Top resid features:
given
Token given
Feature activation+0.191
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
belt
Token belt
Feature activation+0.001
Top resid features:
back
Token back
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
P
TokenP
Feature activation-0.003
Top resid features:
ant
Tokenant
Feature activation+0.001
Top resid features:
ani
Tokenani
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.030
Top resid features:
have
Token have
Feature activation+3.450
Top resid features:
been
Token been
Feature activation+0.796
Top resid features:
44
Token 44
Feature activation+0.065
Top resid features:
on
Token on
Feature activation+0.015
Top resid features:
13
Token 13
Feature activation+0.007
Top resid features:
January
Token January
Feature activation+0.027
Top resid features:
community
Token community
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
she
Token she
Feature activation+0.004
Top resid features:
could
Token could
Feature activation+0.056
Top resid features:
not
Token not
Feature activation+0.326
Top resid features:
have
Token have
Feature activation+4.000
Top resid features:
done
Token done
Feature activation-0.029
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
better
Token better
Feature activation+0.000
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
Buffalo
Token Buffalo
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.013
Top resid features:
would
Tokenwould
Feature activation+0.652
Top resid features:
have
Token have
Feature activation+2.630
Top resid features:
been
Token been
Feature activation+0.621
Top resid features:
swept
Token swept
Feature activation+0.126
Top resid features:
under
Token under
Feature activation-0.022
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
rug
Token rug
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.352
Top resid features:
wanted
Token wanted
Feature activation+0.098
Top resid features:
,
Token,
Feature activation+0.080
Top resid features:
we
Token we
Feature activation+0.025
Top resid features:
could
Token could
Feature activation+1.139
Top resid features:
have
Token have
Feature activation+2.052
Top resid features:
taken
Token taken
Feature activation+0.107
Top resid features:
out
Token out
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.037
Top resid features:
body
Token body
Feature activation+0.003
Top resid features:
guards
Tokenguards
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
whether
Token whether
Feature activation-0.016
Top resid features:
Trump
Token Trump
Feature activation+0.062
Top resid features:
would
Token would
Feature activation+0.303
Top resid features:
have
Token have
Feature activation+3.654
Top resid features:
won
Token won
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
Baptist
Token Baptist
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
would
Token would
Feature activation+0.041
Top resid features:
certainly
Token certainly
Feature activation+0.129
Top resid features:
not
Token not
Feature activation+0.281
Top resid features:
have
Token have
Feature activation+3.549
Top resid features:
called
Token called
Feature activation+0.025
Top resid features:
herself
Token herself
Feature activation-0.027
Top resid features:
a
Token a
Feature activation-0.022
Top resid features:
Buddhist
Token Buddhist
Feature activation-0.073
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
real
Token real
Feature activation-0.007
Top resid features:
story
Token story
Feature activation-0.011
Top resid features:
might
Token might
Feature activation+0.165
Top resid features:
have
Token have
Feature activation+3.285
Top resid features:
been
Token been
Feature activation+0.065
Top resid features:
even
Token even
Feature activation+0.120
Top resid features:
more
Token more
Feature activation+0.079
Top resid features:
bizarre
Token bizarre
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
bit
Token bit
Feature activation+0.013
Top resid features:
later
Token later
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
riders
Token riders
Feature activation+0.012
Top resid features:
would
Token would
Feature activation+0.877
Top resid features:
have
Token have
Feature activation+2.757
Top resid features:
peeled
Token peeled
Feature activation+0.044
Top resid features:
out
Token out
Feature activation-0.006
Top resid features:
from
Token from
Feature activation+0.032
Top resid features:
behind
Token behind
Feature activation-0.008
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.005
Top resid features:
would
Token would
Feature activation+0.021
Top resid features:
have
Token have
Feature activation+0.049
Top resid features:
looked
Token looked
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
if
Token if
Feature activation+3.503
Top resid features:
H
Token H
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
L
Token L
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Men
Token Men
Feature activation-0.000
Top resid features:
clubs
Token clubs
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.005
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
couldn
Token couldn
Feature activation+0.016
Top resid features:
't
Token't
Feature activation+0.033
Top resid features:
have
Token have
Feature activation+3.152
Top resid features:
made
Token made
Feature activation+0.135
Top resid features:
it
Token it
Feature activation+0.040
Top resid features:
much
Token much
Feature activation+0.070
Top resid features:
clearer
Token clearer
Feature activation+0.304
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
icycle
Tokenicycle
Feature activation+0.006
Top resid features:
wouldn
Token wouldn
Feature activation+0.360
Top resid features:
âĢ
TokenâĢ
Feature activation-0.045
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
t
Tokent
Feature activation+0.944
Top resid features:
have
Token have
Feature activation+1.707
Top resid features:
stood
Token stood
Feature activation+0.303
Top resid features:
in
Token in
Feature activation+0.118
Top resid features:
her
Token her
Feature activation-0.001
Top resid features:
way
Token way
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.015
Top resid features:
really
Token really
Feature activation-0.006
Top resid features:
think
Token think
Feature activation-0.035
Top resid features:
they
Token they
Feature activation+0.012
Top resid features:
could
Token could
Feature activation+0.502
Top resid features:
have
Token have
Feature activation+2.682
Top resid features:
done
Token done
Feature activation+0.120
Top resid features:
this
Token this
Feature activation+0.046
Top resid features:
much
Token much
Feature activation+0.100
Top resid features:
more
Token more
Feature activation+0.173
Top resid features:
subtly
Token subtly
Feature activation+0.037
Top resid features:
Yanukovych
Token Yanukovych
Feature activation+0.029
Top resid features:
had
Token had
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
he
Token he
Feature activation+0.062
Top resid features:
would
Token would
Feature activation+0.345
Top resid features:
have
Token have
Feature activation+3.231
Top resid features:
won
Token won
Feature activation-0.031
Top resid features:
hand
Token hand
Feature activation+0.003
Top resid features:
ily
Tokenily
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
I
TokenI
Feature activation+0.013
Top resid features:
really
Token really
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.351
Top resid features:
have
Token have
Feature activation+1.899
Top resid features:
liked
Token liked
Feature activation+0.558
Top resid features:
to
Token to
Feature activation+0.648
Top resid features:
stay
Token stay
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
whole
Token whole
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.04

Head 4: 0.05

Head 5: 0.64

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.09

Head 10: 0.01

Head 11: 0.03

Positive logits

had6.39

hadn6.07

had5.94

Had5.91

Had4.87

sooner4.01

has3.77

existed3.73

have3.68

lacked3.62

been3.46

HAS3.44

earlier3.42

HAVE3.36

have3.30

been3.29

Instead3.26

];3.10

has3.05

weren3.04

Negative logits

))))-2.91

Expect-2.77

"}],"-2.75

onymous-2.74

comes-2.73

Takes-2.72

outh-2.70

rawdownloadcloneembedreportprint-2.57

Creat-2.55

coming-2.54

Appears-2.53

Mostly-2.48

Goes-2.47

gencies-2.46

begins-2.44

proceeds-2.42

ocre-2.35

Uses-2.34

Became-2.34

guiName-2.30

INTERVAL 4.815 - 5.350
CONTAINS 0.000%

would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
won
Token won
Feature activation+3.460
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+5.350
had
Token had
Feature activation+0.000
Americans
Token Americans
Feature activation+0.021
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.011
skeptical
Token skeptical
Feature activation+0.623

INTERVAL 4.280 - 4.815
CONTAINS 0.000%

southern
Token southern
Feature activation+0.000
periphery
Token periphery
Feature activation+0.811
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Euro
Token Euro
Feature activation+0.137
zone
Tokenzone
Feature activation+4.362
.
Token.
Feature activation+0.000
Perhaps
Token Perhaps
Feature activation+0.000
she
Token she
Feature activation+0.540
would
Token would
Feature activation+0.468
have
Token have
Feature activation+0.278
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.968
a
Token a
Feature activation+4.500
more
Token more
Feature activation+0.110
humble
Token humble
Feature activation+0.000
person
Token person
Feature activation+0.097
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000

INTERVAL 3.745 - 4.280
CONTAINS 0.001%

she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
done
Token done
Feature activation+1.063
a
Token a
Feature activation+3.773
better
Token better
Feature activation+0.000
job
Token job
Feature activation+0.993
.
Token.
Feature activation+0.064
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
given
Token given
Feature activation+1.608
the
Token the
Feature activation+0.000
belt
Token belt
Feature activation+1.467
back
Token back
Feature activation+4.000
.
Token.
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
different
Token different
Feature activation+0.000
44
Token 44
Feature activation+2.512
on
Token on
Feature activation+0.164
13
Token 13
Feature activation+0.144
January
Token January
Feature activation+1.085
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.933
.
Token.
Feature activation+0.113
He
Token He
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.030
been
Token been
Feature activation+0.141
would
Token would
Feature activation+0.173
have
Token have
Feature activation+0.147
taken
Token taken
Feature activation+0.952
him
Token him
Feature activation+1.032
more
Token more
Feature activation+0.040
seriously
Token seriously
Feature activation+4.043
.
Token.
Feature activation+0.087
Instead
Token Instead
Feature activation+0.000
the
Token the
Feature activation+0.000
Australians
Token Australians
Feature activation+0.000
laughed
Token laughed
Feature activation+0.000
.
Token.
Feature activation+0.000
Imagine
Token Imagine
Feature activation+0.000
what
Token what
Feature activation+0.075
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+4.100
if
Token if
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Per
Token Per
Feature activation+0.000
ino
Tokenino
Feature activation+1.342

INTERVAL 3.210 - 3.745
CONTAINS 0.001%

t
Tokent
Feature activation+0.561
have
Token have
Feature activation+0.508
stood
Token stood
Feature activation+0.669
in
Token in
Feature activation+0.284
her
Token her
Feature activation+0.000
way
Token way
Feature activation+3.278
.
Token.
Feature activation+0.129
If
Token If
Feature activation+0.000
it
Token it
Feature activation+1.374
had
Token had
Feature activation+0.912
had
Token had
Feature activation+1.088
would
Token would
Feature activation+0.353
have
Token have
Feature activation+0.691
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+2.849
from
Token from
Feature activation+0.000
behind
Token behind
Feature activation+3.363
each
Token each
Feature activation+0.000
other
Token other
Feature activation+2.790
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.325
wouldn
Token wouldn
Feature activation+0.000
not
Token not
Feature activation+0.009
have
Token have
Feature activation+0.000
called
Token called
Feature activation+0.000
herself
Token herself
Feature activation+0.000
a
Token a
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+3.440
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.070
done
Token done
Feature activation+0.029
this
Token this
Feature activation+1.266
much
Token much
Feature activation+0.528
more
Token more
Feature activation+0.522
subtly
Token subtly
Feature activation+3.267
.
Token.
Feature activation+0.000
As
TokenAs
Feature activation+0.000
we
Token we
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
in
Token in
Feature activation+0.000
have
Token have
Feature activation+0.743
taken
Token taken
Feature activation+0.325
out
Token out
Feature activation+1.483
the
Token the
Feature activation+0.000
body
Token body
Feature activation+1.275
guards
Tokenguards
Feature activation+3.489
.
Token.
Feature activation+0.419
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.140
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.020

INTERVAL 2.675 - 3.210
CONTAINS 0.003%

the
Token the
Feature activation+0.000
riders
Token riders
Feature activation+0.075
would
Token would
Feature activation+0.353
have
Token have
Feature activation+0.691
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+2.849
from
Token from
Feature activation+0.000
behind
Token behind
Feature activation+3.363
each
Token each
Feature activation+0.000
other
Token other
Feature activation+2.790
so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.157
it
Token it
Feature activation+2.791
much
Token much
Feature activation+1.266
clearer
Token clearer
Feature activation+3.279
he
Token he
Feature activation+0.016
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.000
have
Token have
Feature activation+0.142
escalated
Token escalated
Feature activation+0.822
to
Token to
Feature activation+0.418
a
Token a
Feature activation+0.083
lot
Token lot
Feature activation+0.898
more
Token more
Feature activation+3.126
,
Token,
Feature activation+0.382
which
Token which
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.097
been
Token been
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
could
Token could
Feature activation+0.000
've
Token've
Feature activation+0.087
killed
Token killed
Feature activation+0.452
him
Token him
Feature activation+3.096
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hun
TokenHun
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
It
TokenIt
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.184
been
Token been
Feature activation+0.096
much
Token much
Feature activation+0.000
worse
Token worse
Feature activation+2.906
,
Token,
Feature activation+1.303
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.572
And
Token And
Feature activation+0.142
ré
Tokenré
Feature activation+0.160

INTERVAL 2.140 - 2.675
CONTAINS 0.004%

.
Token.
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.654
Men
Token Men
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
en
Tokenen
Feature activation+2.609
,
Token,
Feature activation+0.750
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
Stand
Token Stand
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
looked
Token looked
Feature activation+2.270
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.085
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
each
Token each
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Un
Token Un
Feature activation+0.000
informed
Tokeninformed
Feature activation+0.112
Worker
Token Worker
Feature activation+0.233
position
Token position
Feature activation+2.545
,
Token,
Feature activation+0.318
too
Token too
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
we
Token we
Feature activation+0.000
would
Token would
Feature activation+0.000
've
Token've
Feature activation+0.000
stopped
Token stopped
Feature activation+0.224
him
Token him
Feature activation+2.548
because
Token because
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
've
Token've
Feature activation+0.339
been
Token been
Feature activation+0.000
shouldn
Token shouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.091
have
Token have
Feature activation+0.000
left
Token left
Feature activation+2.477
us
Token us
Feature activation+1.887
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.838
and
Token and
Feature activation+0.099
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 1.605 - 2.140
CONTAINS 0.008%

she
Token she
Feature activation+1.121
would
Token would
Feature activation+1.693
have
Token have
Feature activation+1.418
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
polls
Token polls
Feature activation+1.617
were
Token were
Feature activation+0.066
closer
Token closer
Feature activation+1.783
.
Token.
Feature activation+0.251
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.016
"
Token "
Feature activation+0.000
Maybe
TokenMaybe
Feature activation+0.000
I
Token I
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.184
one
Token one
Feature activation+1.890
.
Token.
Feature activation+0.072
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
know
Token know
Feature activation+0.000
white
Token white
Feature activation+0.000
men
Token men
Feature activation+0.021
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.090
dwind
Token dwind
Feature activation+0.000
led
Tokenled
Feature activation+1.932
,
Token,
Feature activation+0.618
given
Token given
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
have
Token have
Feature activation+0.000
picked
Token picked
Feature activation+0.000
another
Token another
Feature activation+0.000
player
Token player
Feature activation+1.100
over
Token over
Feature activation+0.000
Monk
Token Monk
Feature activation+1.672
(
Token (
Feature activation+0.000
seven
Tokenseven
Feature activation+0.000
total
Token total
Feature activation+0.000
votes
Token votes
Feature activation+0.000
).
Token).
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
better
Token better
Feature activation+0.000
choice
Token choice
Feature activation+2.712
here
Token here
Feature activation+2.067
to
Token to
Feature activation+0.000
replace
Token replace
Feature activation+0.000
MS
Token MS
Feature activation+0.000
Office
Token Office
Feature activation+0.302
.
Token.
Feature activation+0.000

INTERVAL 1.070 - 1.605
CONTAINS 0.023%

should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
thought
Token thought
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+2.142
more
Token more
Feature activation+1.311
in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+2.620
âĢĵ
Token âĢĵ
Feature activation+0.000
it
Token it
Feature activation+0.000
required
Token required
Feature activation+0.000
could
Token could
Feature activation+0.734
have
Token have
Feature activation+0.743
taken
Token taken
Feature activation+0.325
out
Token out
Feature activation+1.483
the
Token the
Feature activation+0.000
body
Token body
Feature activation+1.275
guards
Tokenguards
Feature activation+3.489
.
Token.
Feature activation+0.419
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.140
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
things
Token things
Feature activation+0.107
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.196
t
Tokent
Feature activation+0.000
gone
Token gone
Feature activation+0.000
smoothly
Token smoothly
Feature activation+0.216
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
brought
Token brought
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
unemployment
Token unemployment
Feature activation+0.315
rate
Token rate
Feature activation+1.553
lower
Token lower
Feature activation+1.447
,
Token,
Feature activation+0.049
faster
Token faster
Feature activation+0.480
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
el
Tokenel
Feature activation+0.824
must
Token must
Feature activation+0.000
have
Token have
Feature activation+0.145
been
Token been
Feature activation+0.024
nervous
Token nervous
Feature activation+1.086
and
Token and
Feature activation+0.000
distraught
Token distraught
Feature activation+1.585
from
Token from
Feature activation+0.000
having
Token having
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.535 - 1.070
CONTAINS 0.067%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
that
Token that
Feature activation+0.000
denial
Token denial
Feature activation+0.609
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
deposition
Token deposition
Feature activation+0.000
under
Token under
Feature activation+0.000
oath
Token oath
Feature activation+0.155
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
detected
Token detected
Feature activation+0.672
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
blood
Token blood
Feature activation+0.653
sample
Token sample
Feature activation+0.658
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
test
Token test
Feature activation+0.000
fast
Tokenfast
Feature activation+0.000
fiber
Token fiber
Feature activation+0.000
service
Token service
Feature activation+0.530
into
Token into
Feature activation+0.000
adjoining
Token adjoining
Feature activation+0.000
municipalities
Token municipalities
Feature activation+0.718
and
Token and
Feature activation+0.000
rural
Token rural
Feature activation+0.000
areas
Token areas
Feature activation+0.661
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
genuine
Token genuine
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
convictions
Token convictions
Feature activation+0.637
instead
Token instead
Feature activation+0.001
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
(
Token (
Feature activation+0.000
increasing
Tokenincreasing
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
something
Token something
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.627
."
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

INTERVAL 0.000 - 0.535
CONTAINS 99.892%

the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
agriculture
Token agriculture
Feature activation+0.000
and
Token and
Feature activation+0.000
food
Token food
Feature activation+0.000
security
Token security
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Volkswagen
Token Volkswagen
Feature activation+0.000
(
Token (
Feature activation+0.000
VW
TokenVW
Feature activation+0.000
)
Token)
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
pay
Token pay
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
bug
Token bug
Feature activation+0.000
that
Token that
Feature activation+0.000
caused
Token caused
Feature activation+0.000
the
Token the
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
My
Token My
Feature activation+0.000
D
TokenD
Feature activation+0.000
oom
Tokenoom
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
its
Token its
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
shar
Token shar
Feature activation+0.000
pen
Tokenpen
Feature activation+0.000
��
Token��
Feature activation+0.000
their
Tokentheir
Feature activation+0.000
minds
Token minds
Feature activation+0.000
and
Token and
Feature activation+0.000
moon
Token moon
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prin
TokenPrin
Feature activation+0.000
cess
Tokencess
Feature activation+0.000
Mak
Token Mak
Feature activation+0.000
o
Tokeno
Feature activation+0.000
,
Token,
Feature activation+0.000
25
Token 25
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H10.5: (feature 15138)

TOP ACTIVATIONS
MAX = 7.180

pose
Token pose
Feature activation+0.000
y
Tokeny
Feature activation+0.167
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
v
Token v
Feature activation+0.000
ases
Tokenases
Feature activation+7.180
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.383
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
roses
Token roses
Feature activation+0.000
our
Token our
Feature activation+0.000
homes
Token homes
Feature activation+0.901
with
Token with
Feature activation+0.000
p
Token p
Feature activation+0.000
otted
Tokenotted
Feature activation+0.000
flowers
Token flowers
Feature activation+6.485
and
Token and
Feature activation+0.000
pose
Token pose
Feature activation+0.000
y
Tokeny
Feature activation+0.167
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
Tw
Token Tw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ine
Tokenine
Feature activation+1.681
Pal
Token Pal
Feature activation+0.000
ms
Tokenms
Feature activation+5.371
Marine
Token Marine
Feature activation+0.000
since
Token since
Feature activation+0.000
June
Token June
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
writing
Token writing
Feature activation+0.000
about
Token about
Feature activation+0.000
social
Token social
Feature activation+0.000
mobility
Token mobility
Feature activation+5.210
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.000
I
Token I
Feature activation+0.000
became
Token became
Feature activation+0.000
socially
Token socially
Feature activation+0.000
Marine
Token Marine
Feature activation+0.000
Corps
Token Corps
Feature activation+0.000
Air
Token Air
Feature activation+0.000
Ground
Token Ground
Feature activation+0.000
Combat
Token Combat
Feature activation+0.000
Center
Token Center
Feature activation+4.778
at
Token at
Feature activation+0.000
Tw
Token Tw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ine
Tokenine
Feature activation+1.681
)
Token)
Feature activation+2.257
about
Token about
Feature activation+0.000
using
Token using
Feature activation+0.000
event
Token event
Feature activation+0.000
ed
Tokened
Feature activation+0.000
JavaScript
Token JavaScript
Feature activation+4.670
to
Token to
Feature activation+0.000
sane
Token sane
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
organize
Token organize
Feature activation+0.000
client
Token client
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
drawing
Token drawing
Feature activation+1.297
board
Token board
Feature activation+4.538
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
incarnation
Token incarnation
Feature activation+3.434
since
Token since
Feature activation+0.000
1999
Token 1999
Feature activation+0.000
blogging
Token blogging
Feature activation+0.569
about
Token about
Feature activation+0.000
comics
Token comics
Feature activation+3.802
and
Token and
Feature activation+1.337
pop
Token pop
Feature activation+0.766
culture
Token culture
Feature activation+4.416
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.497
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
contain
Token contain
Feature activation+0.000
this
Token this
Feature activation+0.112
shadow
Token shadow
Feature activation+0.350
credit
Token credit
Feature activation+2.929
boom
Token boom
Feature activation+4.264
since
Token since
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
via
Token via
Feature activation+0.000
macro
Token macro
Feature activation+0.000
pr
Tokenpr
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+4.254
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.076
and
Token and
Feature activation+0.000
've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
talking
Token talking
Feature activation+0.333
about
Token about
Feature activation+0.000
global
Token global
Feature activation+0.000
warming
Token warming
Feature activation+4.241
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.321
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
talking
Token talking
Feature activation+0.766
to
Token to
Feature activation+0.000
North
Token North
Feature activation+0.029
Korea
Token Korea
Feature activation+4.234
,
Token,
Feature activation+0.869
and
Token and
Feature activation+0.099
paying
Token paying
Feature activation+0.000
them
Token them
Feature activation+0.816
extortion
Token extortion
Feature activation+0.795
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
dominant
Token dominant
Feature activation+0.695
within
Token within
Feature activation+0.000
philosophy
Token philosophy
Feature activation+4.075
for
Token for
Feature activation+0.000
ages
Token ages
Feature activation+0.133
:
Token:
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
is
Token is
Feature activation+0.000
activists
Token activists
Feature activation+0.000
have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.000
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.055
service
Token service
Feature activation+4.048
in
Token in
Feature activation+0.000
court
Token court
Feature activation+3.427
for
Token for
Feature activation+0.428
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.820
I
TokenI
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+2.389
i
Tokeni
Feature activation+3.935
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
drinking
Token drinking
Feature activation+0.000
grass
Token grass
Feature activation+0.421
fed
Tokenfed
Feature activation+0.449
gelatin
Token gelatin
Feature activation+3.902
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
detox
Token detox
Feature activation+1.361
tea
Token tea
Feature activation+3.113
on
Token on
Feature activation+0.000
been
Token been
Feature activation+0.000
active
Token active
Feature activation+2.119
in
Token in
Feature activation+0.120
promoting
Token promoting
Feature activation+0.252
the
Token the
Feature activation+0.000
league
Token league
Feature activation+3.892
,
Token,
Feature activation+1.620
and
Token and
Feature activation+0.072
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
open
Token open
Feature activation+0.822
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
presence
Token presence
Feature activation+3.849
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
talking
Token talking
Feature activation+0.060
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
Joker
Token Joker
Feature activation+3.848
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.714
s
Tokens
Feature activation+0.000
journey
Token journey
Feature activation+2.876
in
Token in
Feature activation+0.005
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
conducting
Token conducting
Feature activation+0.000
surveys
Token surveys
Feature activation+1.496
of
Token of
Feature activation+0.000
voters
Token voters
Feature activation+3.846
since
Token since
Feature activation+0.000
1985
Token 1985
Feature activation+1.482
.
Token.
Feature activation+0.000
Sample
Token Sample
Feature activation+0.000
Size
Token Size
Feature activation+0.000

Top DFA by src position
MAX = 7.440

and
Token and
Feature activation-0.010
Top resid features:
we
Token we
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.053
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
ve
Tokenve
Feature activation+0.072
Top resid features:
been
Token been
Feature activation+7.440
Top resid features:
lav
Token lav
Feature activation+0.000
Top resid features:
ishing
Tokenishing
Feature activation+0.013
Top resid features:
our
Token our
Feature activation-0.003
Top resid features:
homes
Token homes
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.036
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
we
Token we
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.072
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
ve
Tokenve
Feature activation+0.113
Top resid features:
been
Token been
Feature activation+6.675
Top resid features:
lav
Token lav
Feature activation+0.001
Top resid features:
ishing
Tokenishing
Feature activation+0.044
Top resid features:
our
Token our
Feature activation-0.003
Top resid features:
homes
Token homes
Feature activation+0.005
Top resid features:
with
Token with
Feature activation+0.085
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
2014
Token 2014
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.087
Top resid features:
been
Token been
Feature activation+1.953
Top resid features:
missing
Token missing
Feature activation+3.483
Top resid features:
from
Token from
Feature activation+0.203
Top resid features:
her
Token her
Feature activation+0.002
Top resid features:
home
Token home
Feature activation+0.140
Top resid features:
at
Token at
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.045
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
have
Token have
Feature activation+0.162
Top resid features:
been
Token been
Feature activation+2.613
Top resid features:
writing
Token writing
Feature activation+2.281
Top resid features:
about
Token about
Feature activation+0.583
Top resid features:
social
Token social
Feature activation+0.015
Top resid features:
mobility
Token mobility
Feature activation+0.045
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
2014
Token 2014
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.096
Top resid features:
been
Token been
Feature activation+1.832
Top resid features:
missing
Token missing
Feature activation+3.023
Top resid features:
from
Token from
Feature activation+0.337
Top resid features:
her
Token her
Feature activation+0.004
Top resid features:
home
Token home
Feature activation+0.048
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
browser
Token browser
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
have
Token have
Feature activation+0.222
Top resid features:
been
Token been
Feature activation+2.739
Top resid features:
giving
Token giving
Feature activation+1.878
Top resid features:
talks
Token talks
Feature activation+0.326
Top resid features:
(
Token (
Feature activation-0.003
Top resid features:
for
Tokenfor
Feature activation-0.001
Top resid features:
years
Token years
Feature activation-0.000
Top resid features:
proposed
Token proposed
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
1929
Token 1929
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+1.304
Top resid features:
been
Token been
Feature activation+2.989
Top resid features:
on
Token on
Feature activation+0.548
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
drawing
Token drawing
Feature activation+0.023
Top resid features:
board
Token board
Feature activation+0.134
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
John
Token John
Feature activation-0.001
Top resid features:
Bab
Token Bab
Feature activation+0.000
Top resid features:
os
Tokenos
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
has
Token has
Feature activation+0.056
Top resid features:
been
Token been
Feature activation+2.858
Top resid features:
blogging
Token blogging
Feature activation+1.566
Top resid features:
about
Token about
Feature activation+0.260
Top resid features:
comics
Token comics
Feature activation+0.106
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
pop
Token pop
Feature activation+0.006
Top resid features:
ago
Token ago
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
Authorities
Token Authorities
Feature activation+0.011
Top resid features:
have
Token have
Feature activation+0.045
Top resid features:
been
Token been
Feature activation+0.679
Top resid features:
trying
Token trying
Feature activation+3.782
Top resid features:
to
Token to
Feature activation+0.232
Top resid features:
contain
Token contain
Feature activation-0.030
Top resid features:
this
Token this
Feature activation+0.030
Top resid features:
shadow
Token shadow
Feature activation+0.006
Top resid features:
credit
Token credit
Feature activation+0.027
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
vision
Token vision
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
I
Token I
Feature activation-0.012
Top resid features:
have
Token have
Feature activation+0.087
Top resid features:
wanted
Token wanted
Feature activation+3.187
Top resid features:
to
Token to
Feature activation+1.340
Top resid features:
share
Token share
Feature activation+0.230
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
"
Token "
Feature activation-0.003
Top resid features:
I
TokenI
Feature activation-0.004
Top resid features:
've
Token've
Feature activation+0.154
Top resid features:
been
Token been
Feature activation+2.258
Top resid features:
talking
Token talking
Feature activation+1.815
Top resid features:
about
Token about
Feature activation+0.366
Top resid features:
global
Token global
Feature activation+0.005
Top resid features:
warming
Token warming
Feature activation+0.081
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.125
Top resid features:
been
Token been
Feature activation+1.856
Top resid features:
talking
Token talking
Feature activation+2.463
Top resid features:
to
Token to
Feature activation+0.230
Top resid features:
North
Token North
Feature activation+0.015
Top resid features:
Korea
Token Korea
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
formula
Token formula
Feature activation+0.036
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.163
Top resid features:
been
Token been
Feature activation+1.131
Top resid features:
dominant
Token dominant
Feature activation+2.493
Top resid features:
within
Token within
Feature activation+0.603
Top resid features:
philosophy
Token philosophy
Feature activation+0.085
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
ages
Token ages
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Wild
TokenWild
Feature activation+0.001
Top resid features:
life
Tokenlife
Feature activation-0.001
Top resid features:
activists
Token activists
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.374
Top resid features:
battled
Token battled
Feature activation+3.966
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
fisheries
Token fisheries
Feature activation+0.003
Top resid features:
service
Token service
Feature activation+0.096
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
court
Token court
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
"
Token"
Feature activation-0.012
Top resid features:
I
TokenI
Feature activation-0.002
Top resid features:
've
Token've
Feature activation+0.077
Top resid features:
known
Token known
Feature activation+4.310
Top resid features:
S
Token S
Feature activation+0.028
Top resid features:
atch
Tokenatch
Feature activation+0.006
Top resid features:
i
Tokeni
Feature activation+0.101
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.060
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
ve
Tokenve
Feature activation+0.042
Top resid features:
been
Token been
Feature activation+3.393
Top resid features:
drinking
Token drinking
Feature activation+0.900
Top resid features:
grass
Token grass
Feature activation+0.021
Top resid features:
fed
Tokenfed
Feature activation+0.041
Top resid features:
gelatin
Token gelatin
Feature activation+0.057
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
ownership
Token ownership
Feature activation+0.013
Top resid features:
group
Token group
Feature activation+0.039
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
has
Token has
Feature activation+0.147
Top resid features:
been
Token been
Feature activation+1.368
Top resid features:
active
Token active
Feature activation+1.485
Top resid features:
in
Token in
Feature activation+0.399
Top resid features:
promoting
Token promoting
Feature activation+0.256
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
league
Token league
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
where
Token where
Feature activation-0.032
Top resid features:
it
Token it
Feature activation+0.015
Top resid features:
has
Token has
Feature activation+0.386
Top resid features:
had
Token had
Feature activation+1.331
Top resid features:
a
Token a
Feature activation+0.473
Top resid features:
presence
Token presence
Feature activation+2.197
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
1950
Token 1950
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ared
Tokenared
Feature activation+0.001
Top resid features:
Let
Token Let
Feature activation-0.004
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.094
Top resid features:
been
Token been
Feature activation+0.871
Top resid features:
talking
Token talking
Feature activation+2.942
Top resid features:
about
Token about
Feature activation+0.346
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
Joker
Token Joker
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
American
Token American
Feature activation-0.005
Top resid features:
Research
Token Research
Feature activation-0.002
Top resid features:
Group
Token Group
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.070
Top resid features:
been
Token been
Feature activation+1.366
Top resid features:
conducting
Token conducting
Feature activation+1.688
Top resid features:
surveys
Token surveys
Feature activation+1.374
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
voters
Token voters
Feature activation+0.048
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
1985
Token 1985
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.64

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.11

Head 10: 0.02

Head 11: 0.04

Positive logits

since6.33

ever6.31

since5.82

lately5.43

ever5.16

forever4.51

EVER4.43

Ever4.14

until4.03

intermitt3.96

till3.94

Ever3.79

awhile3.72

continuously3.70

steadily3.65

until3.63

spor3.56

Since3.26

Until3.24

throughout3.22

Negative logits

OULD-2.82

WAR-2.61

ERE-2.57

ardless-2.56

SEE-2.56

BELOW-2.55

Trayvon-2.47

>]-2.44

CLUS-2.42

IF-2.41

][/-2.38

ゼウス-2.37

redo-2.37

skirts-2.36

umbledore-2.35

YC-2.30

warr-2.30

WHAT-2.30

LLOW-2.24

etheless-2.24

INTERVAL 6.462 - 7.180
CONTAINS 0.000%

our
Token our
Feature activation+0.000
homes
Token homes
Feature activation+0.901
with
Token with
Feature activation+0.000
p
Token p
Feature activation+0.000
otted
Tokenotted
Feature activation+0.000
flowers
Token flowers
Feature activation+6.485
and
Token and
Feature activation+0.000
pose
Token pose
Feature activation+0.000
y
Tokeny
Feature activation+0.167
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
pose
Token pose
Feature activation+0.000
y
Tokeny
Feature activation+0.167
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
v
Token v
Feature activation+0.000
ases
Tokenases
Feature activation+7.180
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.383
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
roses
Token roses
Feature activation+0.000

INTERVAL 5.744 - 6.462
CONTAINS 0.000%

INTERVAL 5.026 - 5.744
CONTAINS 0.000%

have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
writing
Token writing
Feature activation+0.000
about
Token about
Feature activation+0.000
social
Token social
Feature activation+0.000
mobility
Token mobility
Feature activation+5.210
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.000
I
Token I
Feature activation+0.000
became
Token became
Feature activation+0.000
socially
Token socially
Feature activation+0.000
Tw
Token Tw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ine
Tokenine
Feature activation+1.681
Pal
Token Pal
Feature activation+0.000
ms
Tokenms
Feature activation+5.371
Marine
Token Marine
Feature activation+0.000
since
Token since
Feature activation+0.000
June
Token June
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.308 - 5.026
CONTAINS 0.001%

has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
drawing
Token drawing
Feature activation+1.297
board
Token board
Feature activation+4.538
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
incarnation
Token incarnation
Feature activation+3.434
since
Token since
Feature activation+0.000
1999
Token 1999
Feature activation+0.000
)
Token)
Feature activation+2.257
about
Token about
Feature activation+0.000
using
Token using
Feature activation+0.000
event
Token event
Feature activation+0.000
ed
Tokened
Feature activation+0.000
JavaScript
Token JavaScript
Feature activation+4.670
to
Token to
Feature activation+0.000
sane
Token sane
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
organize
Token organize
Feature activation+0.000
client
Token client
Feature activation+0.000
Marine
Token Marine
Feature activation+0.000
Corps
Token Corps
Feature activation+0.000
Air
Token Air
Feature activation+0.000
Ground
Token Ground
Feature activation+0.000
Combat
Token Combat
Feature activation+0.000
Center
Token Center
Feature activation+4.778
at
Token at
Feature activation+0.000
Tw
Token Tw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ine
Tokenine
Feature activation+1.681
blogging
Token blogging
Feature activation+0.569
about
Token about
Feature activation+0.000
comics
Token comics
Feature activation+3.802
and
Token and
Feature activation+1.337
pop
Token pop
Feature activation+0.766
culture
Token culture
Feature activation+4.416
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.497
.
Token.
Feature activation+0.000

INTERVAL 3.590 - 4.308
CONTAINS 0.002%

that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+4.254
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.076
and
Token and
Feature activation+0.000
I
TokenI
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+2.389
i
Tokeni
Feature activation+3.935
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
dominant
Token dominant
Feature activation+0.695
within
Token within
Feature activation+0.000
philosophy
Token philosophy
Feature activation+4.075
for
Token for
Feature activation+0.000
ages
Token ages
Feature activation+0.133
:
Token:
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
is
Token is
Feature activation+0.000
activists
Token activists
Feature activation+0.000
have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.000
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.055
service
Token service
Feature activation+4.048
in
Token in
Feature activation+0.000
court
Token court
Feature activation+3.427
for
Token for
Feature activation+0.428
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.820
active
Token active
Feature activation+0.452
in
Token in
Feature activation+0.000
exploring
Token exploring
Feature activation+0.000
alternative
Token alternative
Feature activation+0.000
economic
Token economic
Feature activation+0.000
cultures
Token cultures
Feature activation+3.594
âĢĶ
Token âĢĶ
Feature activation+0.207
most
Token most
Feature activation+0.000
notably
Token notably
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.872 - 3.590
CONTAINS 0.004%

has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
civil
Token civil
Feature activation+0.000
asset
Token asset
Feature activation+0.000
forfeiture
Token forfeiture
Feature activation+3.174
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
courts
Token courts
Feature activation+3.023
and
Token and
Feature activation+0.124
on
Token on
Feature activation+0.000
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
racer
Token racer
Feature activation+2.969
since
Token since
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
Speed
Token Speed
Feature activation+0.183
in
Token in
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
contain
Token contain
Feature activation+0.000
this
Token this
Feature activation+0.112
shadow
Token shadow
Feature activation+0.350
credit
Token credit
Feature activation+2.929
boom
Token boom
Feature activation+4.264
since
Token since
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
via
Token via
Feature activation+0.000
macro
Token macro
Feature activation+0.000
the
Token the
Feature activation+0.000
shots
Token shots
Feature activation+1.072
atop
Token atop
Feature activation+0.000
the
Token the
Feature activation+0.000
pit
Token pit
Feature activation+0.000
box
Token box
Feature activation+3.403
since
Token since
Feature activation+0.000
getting
Token getting
Feature activation+0.000
his
Token his
Feature activation+0.000
start
Token start
Feature activation+0.000
in
Token in
Feature activation+0.000
civil
Token civil
Feature activation+0.000
asset
Token asset
Feature activation+0.000
forfeiture
Token forfeiture
Feature activation+3.174
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
courts
Token courts
Feature activation+3.023
and
Token and
Feature activation+0.124
on
Token on
Feature activation+0.000
op
Token op
Feature activation+0.000
-
Token-
Feature activation+0.000
ed
Tokened
Feature activation+0.000

INTERVAL 2.154 - 2.872
CONTAINS 0.011%

Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
thinking
Token thinking
Feature activation+0.306
about
Token about
Feature activation+0.000
that
Token that
Feature activation+2.573
episode
Token episode
Feature activation+2.483
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.126
contemplate
Token contemplate
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+1.046
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
young
Token young
Feature activation+0.000
family
Token family
Feature activation+2.755
.
Token.
Feature activation+0.262
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.108
Le
TokenLe
Feature activation+0.000
aving
Tokenaving
Feature activation+0.000
known
Token known
Feature activation+0.000
about
Token about
Feature activation+0.000
her
Token her
Feature activation+0.000
daughter
Token daughter
Feature activation+1.848
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.474
s
Tokens
Feature activation+0.025
emerging
Token emerging
Feature activation+0.205
gender
Token gender
Feature activation+1.992
identity
Token identity
Feature activation+3.502
since
Token since
Feature activation+0.000
Tw
Token Tw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ine
Tokenine
Feature activation+0.537
Pal
Token Pal
Feature activation+0.000
ms
Tokenms
Feature activation+2.577
area
Token area
Feature activation+2.134
since
Token since
Feature activation+0.000
June
Token June
Feature activation+0.000
28
Token 28
Feature activation+0.671
.
Token.
Feature activation+0.000
ist
Tokenist
Feature activation+1.740
cha
Token cha
Feature activation+0.000
plain
Tokenplain
Feature activation+1.135
at
Token at
Feature activation+0.000
Harvard
Token Harvard
Feature activation+1.313
University
Token University
Feature activation+2.596
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
podcasts
Token podcasts
Feature activation+0.000
about
Token about
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000

INTERVAL 1.436 - 2.154
CONTAINS 0.023%

've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
her
Token her
Feature activation+1.496
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.049
husband
Token husband
Feature activation+2.049
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
I
Token I
Feature activation+0.000
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
known
Token known
Feature activation+0.000
Kelly
Token Kelly
Feature activation+1.863
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.145
and
Token and
Feature activation+0.000
hanging
Token hanging
Feature activation+0.000
out
Token out
Feature activation+0.757
in
Token in
Feature activation+0.000
Dylan
Token Dylan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.592
s
Tokens
Feature activation+0.000
studio
Token studio
Feature activation+2.087
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
suppose
Token suppose
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.000
back
Token back
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
position
Token position
Feature activation+1.483
since
Token since
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
her
Token her
Feature activation+0.000
we
Token we
Feature activation+0.000
only
Token only
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+1.850
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
days
Token days
Feature activation+0.037
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 0.718 - 1.436
CONTAINS 0.062%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
talking
Token talking
Feature activation+0.766
to
Token to
Feature activation+0.000
North
Token North
Feature activation+0.029
Korea
Token Korea
Feature activation+4.234
,
Token,
Feature activation+0.869
and
Token and
Feature activation+0.099
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
just
Token just
Feature activation+0.000
been
Token been
Feature activation+0.000
crying
Token crying
Feature activation+0.826
and
Token and
Feature activation+0.000
getting
Token getting
Feature activation+0.000
tear
Token tear
Feature activation+0.000
y
Tokeny
Feature activation+0.256
thinking
Token thinking
Feature activation+0.061
Roosevelt
Token Roosevelt
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+1.163
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+1.535
for
Token for
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
computer
Token computer
Feature activation+1.392
,
Token,
Feature activation+0.290
looking
Token looking
Feature activation+0.000
at
Token at
Feature activation+0.000
pictures
Token pictures
Feature activation+0.104
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
making
Token making
Feature activation+0.000
preparations
Token preparations
Feature activation+0.830
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
launch
Token launch
Feature activation+0.000
pad
Tokenpad
Feature activation+1.100
that
Token that
Feature activation+0.000

INTERVAL 0.000 - 0.718
CONTAINS 99.897%

make
Token make
Feature activation+0.000
their
Token their
Feature activation+0.000
food
Token food
Feature activation+0.000
choices
Token choices
Feature activation+0.000
.
Token.
Feature activation+0.000
#
Token #
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
ef
Tokenef
Feature activation+0.000
ban
Tokenban
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
hatred
Token hatred
Feature activation+0.000
of
Token of
Feature activation+0.000
E
Token E
Feature activation+0.000
w
Tokenw
Feature activation+0.000
oks
Tokenoks
Feature activation+0.000
stems
Token stems
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
-
Token-
Feature activation+0.000
se
Tokense
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
designation
Token designation
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
days
Token days
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
significant
Tokensignificant
Feature activation+0.000
and
Token and
Feature activation+0.000
ten
Token ten
Feature activation+0.000
acious
Tokenacious
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
s
Tokens
Feature activation+0.000
servers
Token servers
Feature activation+0.000
are
Token are
Feature activation+0.000
blazing
Token blazing
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
hot
Token hot
Feature activation+0.000
new
Token new
Feature activation+0.000
update
Token update
Feature activation+0.000
for
Token for
Feature activation+0.000
Windows
Token Windows
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 H10.5: (feature 17489)

TOP ACTIVATIONS
MAX = 6.276

largest
Token largest
Feature activation+0.419
religion
Token religion
Feature activation+5.043
in
Token in
Feature activation+0.230
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+6.276
could
Token could
Feature activation+1.527
be
Token be
Feature activation+0.416
no
Token no
Feature activation+0.000
religion
Token religion
Feature activation+0.000
at
Token at
Feature activation+0.000
.
Token.
Feature activation+0.000
Maybe
Token Maybe
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.000
Big
Token Big
Feature activation+0.053
Finish
Token Finish
Feature activation+5.750
will
Token will
Feature activation+0.733
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.031
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.419
religion
Token religion
Feature activation+5.043
in
Token in
Feature activation+0.230
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+6.276
could
Token could
Feature activation+1.527
interest
Token interest
Feature activation+0.843
payments
Token payments
Feature activation+3.985
on
Token on
Feature activation+0.475
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+5.031
will
Token will
Feature activation+1.836
amount
Token amount
Feature activation+0.271
to
Token to
Feature activation+0.422
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
way
Token way
Feature activation+0.159
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
then
Token then
Feature activation+4.662
will
Token will
Feature activation+0.000
Nun
Token Nun
Feature activation+0.000
grant
Token grant
Feature activation+0.000
you
Token you
Feature activation+0.000
your
Token your
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
someone
Token someone
Feature activation+0.000
strapped
Token strapped
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
headset
Token headset
Feature activation+4.563
in
Token in
Feature activation+0.000
public
Token public
Feature activation+4.065
may
Token may
Feature activation+1.076
be
Token be
Feature activation+0.247
like
Token like
Feature activation+0.000
programs
Token programs
Feature activation+2.701
due
Token due
Feature activation+0.455
to
Token to
Feature activation+0.000
expire
Token expire
Feature activation+3.242
next
Token next
Feature activation+0.000
summer
Token summer
Feature activation+4.434
may
Token may
Feature activation+0.527
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
jeopardy
Token jeopardy
Feature activation+0.100
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.124
/
Token/
Feature activation+0.000
18
Token18
Feature activation+1.164
,
Token,
Feature activation+1.070
Ontario
Token Ontario
Feature activation+4.432
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.794
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
wh
Token wh
Feature activation+0.000
omever
Tokenomever
Feature activation+0.000
I
Token I
Feature activation+0.100
say
Token say
Feature activation+1.925
them
Token them
Feature activation+2.291
to
Token to
Feature activation+4.385
will
Token will
Feature activation+0.350
start
Token start
Feature activation+0.000
leading
Token leading
Feature activation+0.000
me
Token me
Feature activation+0.000
further
Token further
Feature activation+0.000
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+4.079
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+4.220
would
Token would
Feature activation+0.469
thus
Token thus
Feature activation+0.485
have
Token have
Feature activation+0.358
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.000
see
Token see
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
War
Token War
Feature activation+0.000
you
Token you
Feature activation+2.039
âĢ
TokenâĢ
Feature activation+0.839
Ļ
TokenĻ
Feature activation+4.210
re
Tokenre
Feature activation+2.424
going
Token going
Feature activation+0.057
to
Token to
Feature activation+0.225
be
Token be
Feature activation+0.000
even
Token even
Feature activation+0.000
was
Token was
Feature activation+0.000
expected
Token expected
Feature activation+0.000
that
Token that
Feature activation+0.000
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+4.079
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+4.220
would
Token would
Feature activation+0.469
thus
Token thus
Feature activation+0.485
strapped
Token strapped
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
headset
Token headset
Feature activation+4.563
in
Token in
Feature activation+0.000
public
Token public
Feature activation+4.065
may
Token may
Feature activation+1.076
be
Token be
Feature activation+0.247
like
Token like
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
someone
Token someone
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
2021
Token 2021
Feature activation+0.733
,
Token,
Feature activation+0.387
interest
Token interest
Feature activation+0.843
payments
Token payments
Feature activation+3.985
on
Token on
Feature activation+0.475
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+5.031
will
Token will
Feature activation+1.836
Aff
Token Aff
Feature activation+0.000
leck
Tokenleck
Feature activation+3.503
and
Token and
Feature activation+0.000
Alan
Token Alan
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
kin
Tokenkin
Feature activation+3.886
will
Token will
Feature activation+1.266
get
Token get
Feature activation+0.000
recognized
Token recognized
Feature activation+0.525
in
Token in
Feature activation+0.106
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
gag
Token gag
Feature activation+0.084
I
Token I
Feature activation+1.550
âĢ
TokenâĢ
Feature activation+3.458
Ļ
TokenĻ
Feature activation+3.843
m
Tokenm
Feature activation+1.471
going
Token going
Feature activation+0.231
to
Token to
Feature activation+0.332
storm
Token storm
Feature activation+0.041
off
Token off
Feature activation+0.944
/
Token/
Feature activation+0.000
18
Token18
Feature activation+1.164
,
Token,
Feature activation+1.070
Ontario
Token Ontario
Feature activation+4.432
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.794
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.758
net
Token net
Feature activation+0.663
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
months
Token months
Feature activation+0.210
,
Token,
Feature activation+0.282
Ey
Token Ey
Feature activation+0.200
al
Tokenal
Feature activation+3.764
and
Token and
Feature activation+0.000
B
Token B
Feature activation+0.000
anc
Tokenanc
Feature activation+0.000
or
Tokenor
Feature activation+3.511
will
Token will
Feature activation+0.568
future
Token future
Feature activation+0.000
,
Token,
Feature activation+0.239
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.163
Tenn
Token Tenn
Feature activation+0.269
yson
Tokenyson
Feature activation+3.701
said
Token said
Feature activation+0.120
,
Token,
Feature activation+0.531
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+1.193
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.758
net
Token net
Feature activation+0.663
debt
Token debt
Feature activation+3.533
will
Token will
Feature activation+1.359
finally
Token finally
Feature activation+0.569
exceed
Token exceed
Feature activation+0.052
Quebec
Token Quebec
Feature activation+0.190
âĢ
TokenâĢ
Feature activation+0.000

Top DFA by src position
MAX = 5.559

increasing
Token increasing
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.556
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.069
Top resid features:
few
Token few
Feature activation+0.104
Top resid features:
years
Token years
Feature activation+5.333
Top resid features:
the
Token the
Feature activation+0.464
Top resid features:
largest
Token largest
Feature activation+0.042
Top resid features:
religion
Token religion
Feature activation+0.102
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Maybe
Token Maybe
Feature activation+0.432
Top resid features:
one
Token one
Feature activation+0.073
Top resid features:
day
Token day
Feature activation+5.559
Top resid features:
Big
Token Big
Feature activation-0.014
Top resid features:
Finish
Token Finish
Feature activation+0.107
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
let
Token let
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
increasing
Token increasing
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.628
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.064
Top resid features:
few
Token few
Feature activation+0.088
Top resid features:
years
Token years
Feature activation+4.242
Top resid features:
the
Token the
Feature activation+0.255
Top resid features:
largest
Token largest
Feature activation+0.197
Top resid features:
religion
Token religion
Feature activation+0.015
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
projected
Token projected
Feature activation+0.213
Top resid features:
that
Token that
Feature activation+0.996
Top resid features:
by
Token by
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
year
Token year
Feature activation+0.111
Top resid features:
2021
Token 2021
Feature activation+2.455
Top resid features:
,
Token,
Feature activation+1.293
Top resid features:
interest
Token interest
Feature activation+0.078
Top resid features:
payments
Token payments
Feature activation+0.248
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
your
Token your
Feature activation-0.006
Top resid features:
way
Token way
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Only
Token Only
Feature activation+0.320
Top resid features:
then
Token then
Feature activation+4.746
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
Nun
Token Nun
Feature activation+0.000
Top resid features:
grant
Token grant
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
screen
Token screen
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
In
Token In
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
few
Token few
Feature activation+0.018
Top resid features:
years
Token years
Feature activation+2.768
Top resid features:
,
Token,
Feature activation+2.192
Top resid features:
seeing
Token seeing
Feature activation-0.046
Top resid features:
someone
Token someone
Feature activation+0.052
Top resid features:
strapped
Token strapped
Feature activation+0.015
Top resid features:
into
Token into
Feature activation+0.043
Top resid features:
if
Token if
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
bill
Token bill
Feature activation-0.024
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
blocked
Token blocked
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+3.961
Top resid features:
major
Token major
Feature activation+0.021
Top resid features:
surveillance
Token surveillance
Feature activation+0.109
Top resid features:
programs
Token programs
Feature activation+0.687
Top resid features:
due
Token due
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.279
Top resid features:
in
Token in
Feature activation+0.054
Top resid features:
2017
Token 2017
Feature activation+0.860
Top resid features:
/
Token/
Feature activation+0.052
Top resid features:
18
Token18
Feature activation+0.527
Top resid features:
,
Token,
Feature activation+1.972
Top resid features:
Ontario
Token Ontario
Feature activation+0.207
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.002
Top resid features:
thoughts
Token thoughts
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
fear
Token fear
Feature activation+0.226
Top resid features:
that
Token that
Feature activation+4.127
Top resid features:
wh
Token wh
Feature activation+0.004
Top resid features:
omever
Tokenomever
Feature activation+0.020
Top resid features:
I
Token I
Feature activation+0.017
Top resid features:
say
Token say
Feature activation+0.221
Top resid features:
them
Token them
Feature activation+0.194
Top resid features:
overtime
Token overtime
Feature activation-0.004
Top resid features:
pay
Token pay
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
It
Token It
Feature activation-0.005
Top resid features:
was
Token was
Feature activation-0.006
Top resid features:
expected
Token expected
Feature activation+2.782
Top resid features:
that
Token that
Feature activation+1.841
Top resid features:
ser
Token ser
Feature activation-0.025
Top resid features:
ge
Tokenge
Feature activation-0.002
Top resid features:
ants
Tokenants
Feature activation+0.097
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
after
Token after
Feature activation-0.000
Top resid features:
you
Token you
Feature activation-0.063
Top resid features:
see
Token see
Feature activation+0.002
Top resid features:
Civil
Token Civil
Feature activation-0.006
Top resid features:
War
Token War
Feature activation+0.005
Top resid features:
you
Token you
Feature activation+4.675
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
overtime
Token overtime
Feature activation-0.004
Top resid features:
pay
Token pay
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
It
Token It
Feature activation-0.008
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
expected
Token expected
Feature activation+2.778
Top resid features:
that
Token that
Feature activation+1.714
Top resid features:
ser
Token ser
Feature activation-0.011
Top resid features:
ge
Tokenge
Feature activation-0.002
Top resid features:
ants
Tokenants
Feature activation+0.046
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
In
Token In
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
few
Token few
Feature activation+0.020
Top resid features:
years
Token years
Feature activation+1.914
Top resid features:
,
Token,
Feature activation+2.518
Top resid features:
seeing
Token seeing
Feature activation-0.049
Top resid features:
someone
Token someone
Feature activation+0.062
Top resid features:
strapped
Token strapped
Feature activation+0.004
Top resid features:
into
Token into
Feature activation+0.013
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
projected
Token projected
Feature activation+0.329
Top resid features:
that
Token that
Feature activation+1.211
Top resid features:
by
Token by
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
year
Token year
Feature activation+0.156
Top resid features:
2021
Token 2021
Feature activation+1.393
Top resid features:
,
Token,
Feature activation+1.067
Top resid features:
interest
Token interest
Feature activation-0.006
Top resid features:
payments
Token payments
Feature activation+0.103
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
do
Token do
Feature activation-0.004
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
living
Token living
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+2.033
Top resid features:
some
Token some
Feature activation+1.775
Top resid features:
town
Token town
Feature activation+0.036
Top resid features:
favorites
Token favorites
Feature activation+0.546
Top resid features:
like
Token like
Feature activation+0.006
Top resid features:
George
Token George
Feature activation-0.003
Top resid features:
hex
Tokenhex
Feature activation+0.004
Top resid features:
appeal
Token appeal
Feature activation+0.017
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.038
Top resid features:
gag
Token gag
Feature activation+0.050
Top resid features:
I
Token I
Feature activation+4.036
Top resid features:
âĢ
TokenâĢ
Feature activation-0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.146
Top resid features:
m
Tokenm
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.754
Top resid features:
in
Token in
Feature activation+0.164
Top resid features:
2017
Token 2017
Feature activation+0.451
Top resid features:
/
Token/
Feature activation+0.056
Top resid features:
18
Token18
Feature activation+0.244
Top resid features:
,
Token,
Feature activation+1.012
Top resid features:
Ontario
Token Ontario
Feature activation+0.920
Top resid features:
âĢ
TokenâĢ
Feature activation-0.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Over
TokenOver
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
coming
Token coming
Feature activation+0.395
Top resid features:
months
Token months
Feature activation+2.442
Top resid features:
,
Token,
Feature activation+1.233
Top resid features:
Ey
Token Ey
Feature activation+0.001
Top resid features:
al
Tokenal
Feature activation+0.061
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
âĢ
Token âĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.035
Top resid features:
In
TokenIn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
future
Token future
Feature activation+1.445
Top resid features:
,
Token,
Feature activation+1.272
Top resid features:
âĢ
TokenâĢ
Feature activation-0.012
Top resid features:
Ŀ
TokenĿ
Feature activation+1.224
Top resid features:
Tenn
Token Tenn
Feature activation-0.014
Top resid features:
yson
Tokenyson
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.126
Top resid features:
in
Token in
Feature activation+0.050
Top resid features:
2017
Token 2017
Feature activation+0.531
Top resid features:
/
Token/
Feature activation+0.007
Top resid features:
18
Token18
Feature activation+0.343
Top resid features:
,
Token,
Feature activation+1.091
Top resid features:
Ontario
Token Ontario
Feature activation+0.392
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
s
Tokens
Feature activation+0.183
Top resid features:
per
Token per
Feature activation-0.009
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.04

Head 4: 0.05

Head 5: 0.64

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.07

Head 10: 0.02

Head 11: 0.03

Positive logits

will9.15

will8.88

'll7.44

Will7.14

WILL7.01

Will6.43

shall5.61

wont5.34

SHALL5.33

shall5.13

would5.01

won4.95

would4.58

gonna4.54

shalt4.40

tomorrow4.40

morrow4.28

intends4.21

TBA4.05

won4.01

Negative logits

asionally-3.11

��-3.04

sometimes-3.02

tained-2.93

Originally-2.88

aturdays-2.75

arget-2.71

lacked-2.65

hadn-2.59

��-2.59

];-2.58

rather-2.57

olulu-2.54

persisted-2.50

ubis-2.49

had-2.42

tended-2.41

orgetown-2.38

VERTIS-2.37

urus-2.36

INTERVAL 5.649 - 6.276
CONTAINS 0.000%

largest
Token largest
Feature activation+0.419
religion
Token religion
Feature activation+5.043
in
Token in
Feature activation+0.230
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+6.276
could
Token could
Feature activation+1.527
be
Token be
Feature activation+0.416
no
Token no
Feature activation+0.000
religion
Token religion
Feature activation+0.000
at
Token at
Feature activation+0.000
.
Token.
Feature activation+0.000
Maybe
Token Maybe
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.000
Big
Token Big
Feature activation+0.053
Finish
Token Finish
Feature activation+5.750
will
Token will
Feature activation+0.733
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 5.021 - 5.649
CONTAINS 0.000%

interest
Token interest
Feature activation+0.843
payments
Token payments
Feature activation+3.985
on
Token on
Feature activation+0.475
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+5.031
will
Token will
Feature activation+1.836
amount
Token amount
Feature activation+0.271
to
Token to
Feature activation+0.422
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.031
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.419
religion
Token religion
Feature activation+5.043
in
Token in
Feature activation+0.230
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+6.276
could
Token could
Feature activation+1.527

INTERVAL 4.394 - 5.021
CONTAINS 0.000%

in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.124
/
Token/
Feature activation+0.000
18
Token18
Feature activation+1.164
,
Token,
Feature activation+1.070
Ontario
Token Ontario
Feature activation+4.432
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.794
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
programs
Token programs
Feature activation+2.701
due
Token due
Feature activation+0.455
to
Token to
Feature activation+0.000
expire
Token expire
Feature activation+3.242
next
Token next
Feature activation+0.000
summer
Token summer
Feature activation+4.434
may
Token may
Feature activation+0.527
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
jeopardy
Token jeopardy
Feature activation+0.100
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
way
Token way
Feature activation+0.159
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
then
Token then
Feature activation+4.662
will
Token will
Feature activation+0.000
Nun
Token Nun
Feature activation+0.000
grant
Token grant
Feature activation+0.000
you
Token you
Feature activation+0.000
your
Token your
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
someone
Token someone
Feature activation+0.000
strapped
Token strapped
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
headset
Token headset
Feature activation+4.563
in
Token in
Feature activation+0.000
public
Token public
Feature activation+4.065
may
Token may
Feature activation+1.076
be
Token be
Feature activation+0.247
like
Token like
Feature activation+0.000

INTERVAL 3.766 - 4.394
CONTAINS 0.001%

Aff
Token Aff
Feature activation+0.000
leck
Tokenleck
Feature activation+3.503
and
Token and
Feature activation+0.000
Alan
Token Alan
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
kin
Tokenkin
Feature activation+3.886
will
Token will
Feature activation+1.266
get
Token get
Feature activation+0.000
recognized
Token recognized
Feature activation+0.525
in
Token in
Feature activation+0.106
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
gag
Token gag
Feature activation+0.084
I
Token I
Feature activation+1.550
âĢ
TokenâĢ
Feature activation+3.458
Ļ
TokenĻ
Feature activation+3.843
m
Tokenm
Feature activation+1.471
going
Token going
Feature activation+0.231
to
Token to
Feature activation+0.332
storm
Token storm
Feature activation+0.041
off
Token off
Feature activation+0.944
wh
Token wh
Feature activation+0.000
omever
Tokenomever
Feature activation+0.000
I
Token I
Feature activation+0.100
say
Token say
Feature activation+1.925
them
Token them
Feature activation+2.291
to
Token to
Feature activation+4.385
will
Token will
Feature activation+0.350
start
Token start
Feature activation+0.000
leading
Token leading
Feature activation+0.000
me
Token me
Feature activation+0.000
further
Token further
Feature activation+0.000
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+4.079
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+4.220
would
Token would
Feature activation+0.469
thus
Token thus
Feature activation+0.485
have
Token have
Feature activation+0.358
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.000
/
Token/
Feature activation+0.000
18
Token18
Feature activation+1.164
,
Token,
Feature activation+1.070
Ontario
Token Ontario
Feature activation+4.432
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.794
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.758
net
Token net
Feature activation+0.663

INTERVAL 3.138 - 3.766
CONTAINS 0.002%

still
Token still
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
clear
Token clear
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+3.209
will
Token will
Feature activation+0.938
finally
Token finally
Feature activation+0.539
begin
Token begin
Feature activation+0.260
to
Token to
Feature activation+0.278
do
Token do
Feature activation+0.000
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.758
net
Token net
Feature activation+0.663
debt
Token debt
Feature activation+3.533
will
Token will
Feature activation+1.359
finally
Token finally
Feature activation+0.569
exceed
Token exceed
Feature activation+0.052
Quebec
Token Quebec
Feature activation+0.190
âĢ
TokenâĢ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
proceeds
Token proceeds
Feature activation+0.799
from
Token from
Feature activation+0.817
the
Token the
Feature activation+0.000
LA
Token LA
Feature activation+0.000
concert
Token concert
Feature activation+3.276
will
Token will
Feature activation+0.505
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Ne
Token Ne
Feature activation+0.000
,
Token,
Feature activation+0.000
29
Token 29
Feature activation+0.477
percent
Token percent
Feature activation+1.862
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+3.241
will
Token will
Feature activation+1.548
be
Token be
Feature activation+0.058
Latino
Token Latino
Feature activation+0.276
.
Token.
Feature activation+0.817
This
Token This
Feature activation+0.835
Henry
Token Henry
Feature activation+0.000
Sl
Token Sl
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
and
Token and
Feature activation+0.000
Jonathan
Token Jonathan
Feature activation+0.000
Joseph
Token Joseph
Feature activation+3.242
will
Token will
Feature activation+0.639
travel
Token travel
Feature activation+0.043
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.254
gives
Token gives
Feature activation+0.000

INTERVAL 2.511 - 3.138
CONTAINS 0.009%

.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
enacted
Token enacted
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
laws
Token laws
Feature activation+2.645
would
Token would
Feature activation+0.519
represent
Token represent
Feature activation+0.151
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
roll
Token roll
Feature activation+0.000
Reid
Token Reid
Feature activation+1.736
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
Nev
TokenNev
Feature activation+0.000
.)
Token.)
Feature activation+2.559
would
Token would
Feature activation+0.000
lose
Token lose
Feature activation+0.000
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
reelection
Token reelection
Feature activation+0.000
18
Token18
Feature activation+1.164
,
Token,
Feature activation+1.070
Ontario
Token Ontario
Feature activation+4.432
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.794
s
Tokens
Feature activation+3.057
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.758
net
Token net
Feature activation+0.663
debt
Token debt
Feature activation+3.533
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
G
Token G
Feature activation+0.000
ij
Tokenij
Feature activation+0.000
s
Tokens
Feature activation+0.000
expects
Token expects
Feature activation+2.749
to
Token to
Feature activation+0.093
arrive
Token arrive
Feature activation+0.500
late
Token late
Feature activation+0.124
Sunday
Token Sunday
Feature activation+0.181
.
Token.
Feature activation+0.045
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
the
Token the
Feature activation+0.000
FBI
Token FBI
Feature activation+0.842
director
Token director
Feature activation+1.519
role
Token role
Feature activation+2.974
is
Token is
Feature activation+0.232
someone
Token someone
Feature activation+0.056
who
Token who
Feature activation+0.314
can
Token can
Feature activation+0.013
put
Token put
Feature activation+0.000

INTERVAL 1.883 - 2.511
CONTAINS 0.023%

in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+1.193
,
Token,
Feature activation+0.968
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.141
better
Tokenbetter
Feature activation+0.260
technology
Token technology
Feature activation+2.394
might
Token might
Feature activation+0.149
come
Token come
Feature activation+0.004
along
Token along
Feature activation+0.221
Upon
Token Upon
Feature activation+0.000
graduation
Token graduation
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.456
Ļ
TokenĻ
Feature activation+1.989
d
Tokend
Feature activation+0.266
re
Token re
Feature activation+0.000
join
Tokenjoin
Feature activation+0.000
their
Token their
Feature activation+0.000
units
Token units
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
governments
Token governments
Feature activation+1.237
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+2.040
are
Token are
Feature activation+0.440
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
that
Token that
Feature activation+0.000
wins
Token wins
Feature activation+0.000
its
Token its
Feature activation+0.000
suit
Token suit
Feature activation+0.330
,
Token,
Feature activation+0.163
the
Token the
Feature activation+0.000
precedent
Token precedent
Feature activation+1.946
it
Token it
Feature activation+0.450
sets
Token sets
Feature activation+2.923
will
Token will
Feature activation+0.660
not
Token not
Feature activation+0.082
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
ability
Token ability
Feature activation+0.785
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.335
advice
Token advice
Feature activation+2.410
to
Token to
Feature activation+0.358
those
Token those
Feature activation+0.027
law
Token law
Feature activation+0.000
-
Token-
Feature activation+0.000
enforcement
Tokenenforcement
Feature activation+0.135

INTERVAL 1.255 - 1.883
CONTAINS 0.061%

and
Token and
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.325
the
Tokenthe
Feature activation+0.000
dis
Token dis
Feature activation+0.000
com
Tokencom
Feature activation+0.000
s
Tokens
Feature activation+1.396
(
Token (
Feature activation+0.000
dist
Tokendist
Feature activation+0.000
ribution
Tokenribution
Feature activation+0.000
companies
Token companies
Feature activation+0.058
)
Token)
Feature activation+1.723
s
Tokens
Feature activation+1.396
(
Token (
Feature activation+0.000
dist
Tokendist
Feature activation+0.000
ribution
Tokenribution
Feature activation+0.000
companies
Token companies
Feature activation+0.058
)
Token)
Feature activation+1.723
will
Token will
Feature activation+0.463
not
Token not
Feature activation+0.000
buy
Token buy
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
chance
Token chance
Feature activation+0.000
that
Token that
Feature activation+0.075
Brian
Token Brian
Feature activation+0.000
Johnson
Token Johnson
Feature activation+1.282
(
Token (
Feature activation+0.000
el
Tokenel
Feature activation+0.000
bow
Tokenbow
Feature activation+0.000
)
Token)
Feature activation+1.417
could
Token could
Feature activation+0.256
make
Token make
Feature activation+0.000
predictions
Token predictions
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+1.233
will
Token will
Feature activation+0.364
happen
Token happen
Feature activation+1.574
a
Token a
Feature activation+0.799
few
Token few
Feature activation+0.230
seconds
Token seconds
Feature activation+1.584
out
Token out
Feature activation+1.179
.
Token.
Feature activation+0.210
,
Token,
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
y
Tokeny
Feature activation+1.050
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.448
s
Tokens
Feature activation+0.032
first
Token first
Feature activation+0.000
solo
Token solo
Feature activation+0.000
movie
Token movie
Feature activation+2.175
is
Token is
Feature activation+0.397

INTERVAL 0.628 - 1.255
CONTAINS 0.262%

impact
Token impact
Feature activation+0.251
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fall
Token fall
Feature activation+0.850
in
Token in
Feature activation+0.000
sterling
Token sterling
Feature activation+0.946
on
Token on
Feature activation+0.000
consumer
Token consumer
Feature activation+0.000
prices
Token prices
Feature activation+0.965
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
headset
Token headset
Feature activation+4.563
in
Token in
Feature activation+0.000
public
Token public
Feature activation+4.065
may
Token may
Feature activation+1.076
be
Token be
Feature activation+0.247
like
Token like
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
someone
Token someone
Feature activation+0.000
taking
Token taking
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.681
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.771
Cand
TokenCand
Feature activation+0.000
idates
Tokenidates
Feature activation+0.462
are
Token are
Feature activation+0.000
been
Token been
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
so
Token so
Feature activation+0.131
many
Token many
Feature activation+0.241
others
Token others
Feature activation+0.506
have
Token have
Feature activation+0.000
warned
Token warned
Feature activation+0.000
about
Token about
Feature activation+0.746
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pope
TokenPope
Feature activation+0.000
Francis
Token Francis
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
bet
Token bet
Feature activation+0.059
questions
Token questions
Feature activation+0.770
would
Token would
Feature activation+0.335
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
asked
Token asked
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.628
CONTAINS 99.641%

ban
Tokenban
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
Khan
Token Khan
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
operation
Token operation
Feature activation+0.000
has
Token has
Feature activation+0.000
The
TokenThe
Feature activation+0.000
rodent
Token rodent
Feature activation+0.000
had
Token had
Feature activation+0.000
caused
Token caused
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
of
Token of
Feature activation+0.000
damage
Token damage
Feature activation+0.000
by
Token by
Feature activation+0.000
chewing
Token chewing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
mon
Tokenmon
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hope
TokenHope
Feature activation+0.000
this
Token this
Feature activation+0.000
helped
Token helped
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
UPDATE
TokenUPDATE
Feature activation+0.000
April
Token April
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+0.000
marriage
Token marriage
Feature activation+0.000
partners
Token partners
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Zion
Token Zion
Feature activation+0.000
was
Token was
Feature activation+0.000
effectively
Token effectively
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 H10.5: (feature 8327)

TOP ACTIVATIONS
MAX = 3.130

economically
Token economically
Feature activation+2.617
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Tokenover
Feature activation+3.130
would
Token would
Feature activation+0.088
convince
Token convince
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.347
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
were
Token were
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
body
Token body
Feature activation+0.000
cameras
Token cameras
Feature activation+2.726
would
Token would
Feature activation+0.208
shed
Token shed
Feature activation+0.000
light
Token light
Feature activation+0.044
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
compulsion
Token compulsion
Feature activation+1.754
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
sex
Token sex
Feature activation+2.662
with
Token with
Feature activation+0.000
corpses
Token corpses
Feature activation+2.655
would
Token would
Feature activation+0.045
set
Token set
Feature activation+0.000
a
Token a
Feature activation+0.000
compulsion
Token compulsion
Feature activation+1.754
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
sex
Token sex
Feature activation+2.662
with
Token with
Feature activation+0.000
corpses
Token corpses
Feature activation+2.655
would
Token would
Feature activation+0.045
set
Token set
Feature activation+0.000
a
Token a
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
precedent
Token precedent
Feature activation+0.259
was
Token was
Feature activation+0.000
hoped
Token hoped
Feature activation+0.409
that
Token that
Feature activation+0.406
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
expansion
Token expansion
Feature activation+2.650
would
Token would
Feature activation+0.673
mean
Token mean
Feature activation+0.181
that
Token that
Feature activation+0.000
said
Token said
Feature activation+0.000
heroes
Token heroes
Feature activation+1.633
allowing
Token allowing
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+1.255
to
Token to
Feature activation+0.000
prosper
Token prosper
Feature activation+2.367
economically
Token economically
Feature activation+2.617
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Tokenover
Feature activation+3.130
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+2.436
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+2.574
would
Token would
Feature activation+0.164
thus
Token thus
Feature activation+0.138
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.000
near
Token near
Feature activation+0.657
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
Ann
Token Ann
Feature activation+1.984
ab
Tokenab
Feature activation+0.000
erg
Tokenerg
Feature activation+2.552
would
Token would
Feature activation+0.503
turn
Token turn
Feature activation+0.000
into
Token into
Feature activation+0.000
pure
Token pure
Feature activation+0.000
silver
Token silver
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.468
figured
Token figured
Feature activation+0.000
that
Token that
Feature activation+0.000
raising
Token raising
Feature activation+0.000
alarms
Token alarms
Feature activation+2.523
about
Token about
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
interference
Token interference
Feature activation+2.798
would
Token would
Feature activation+0.071
seem
Token seem
Feature activation+0.118
Reid
Token Reid
Feature activation+1.639
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
Nev
TokenNev
Feature activation+0.000
.)
Token.)
Feature activation+2.501
would
Token would
Feature activation+0.000
lose
Token lose
Feature activation+0.089
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
reelection
Token reelection
Feature activation+0.180
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
when
Token when
Feature activation+0.031
this
Token this
Feature activation+1.806
project
Token project
Feature activation+2.288
started
Token started
Feature activation+2.487
what
Token what
Feature activation+0.388
would
Token would
Feature activation+0.159
happen
Token happen
Feature activation+0.675
with
Token with
Feature activation+0.000
this
Token this
Feature activation+0.060
two
Token two
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
class
Tokenclass
Feature activation+0.000
games
Token games
Feature activation+0.161
"
Token"
Feature activation+2.440
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
pink
Token pink
Feature activation+0.000
ball
Token ball
Feature activation+2.263
would
Token would
Feature activation+0.000
was
Token was
Feature activation+0.000
expected
Token expected
Feature activation+0.000
that
Token that
Feature activation+0.000
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+2.436
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+2.574
would
Token would
Feature activation+0.164
thus
Token thus
Feature activation+0.138
circulating
Token circulating
Feature activation+0.000
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
hoped
Token hoped
Feature activation+2.373
would
Token would
Feature activation+0.000
serve
Token serve
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
starting
Token starting
Feature activation+0.000
that
Token that
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+1.255
to
Token to
Feature activation+0.000
prosper
Token prosper
Feature activation+2.367
economically
Token economically
Feature activation+2.617
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
hand
Token hand
Feature activation+0.000
longer
Token longer
Feature activation+0.000
the
Token the
Feature activation+0.000
comfort
Token comfort
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
believed
Token believed
Feature activation+0.270
it
Token it
Feature activation+2.340
to
Token to
Feature activation+1.272
be
Token be
Feature activation+1.418
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
throwing
Token throwing
Feature activation+0.123
in
Token in
Feature activation+0.082
a
Token a
Feature activation+0.000
minor
Token minor
Feature activation+0.000
curse
Token curse
Feature activation+1.872
word
Token word
Feature activation+2.291
would
Token would
Feature activation+0.151
bond
Token bond
Feature activation+0.313
us
Token us
Feature activation+0.336
like
Token like
Feature activation+0.000
kids
Token kids
Feature activation+0.396
We
TokenWe
Feature activation+0.000
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
when
Token when
Feature activation+0.031
this
Token this
Feature activation+1.806
project
Token project
Feature activation+2.288
started
Token started
Feature activation+2.487
what
Token what
Feature activation+0.388
would
Token would
Feature activation+0.159
happen
Token happen
Feature activation+0.675
with
Token with
Feature activation+0.000
th
Tokenth
Feature activation+0.000
son
Token son
Feature activation+0.296
of
Token of
Feature activation+0.000
Ibn
Token Ibn
Feature activation+0.000
Saud
Token Saud
Feature activation+0.168
,
Token,
Feature activation+2.279
would
Token would
Feature activation+0.126
become
Token become
Feature activation+0.000
king
Token king
Feature activation+0.004
some
Token some
Feature activation+0.000
day
Token day
Feature activation+0.259
libertarians
Token libertarians
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000
a
Token a
Feature activation+0.000
Rand
Token Rand
Feature activation+0.000
Paul
Token Paul
Feature activation+0.318
presidency
Token presidency
Feature activation+2.272
would
Token would
Feature activation+0.148
yield
Token yield
Feature activation+0.047
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
policies
Token policies
Feature activation+0.000

Top DFA by src position
MAX = 2.998

Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Be
TokenBe
Feature activation-0.001
Top resid features:
ijing
Tokenijing
Feature activation-0.005
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
hoped
Token hoped
Feature activation+1.887
Top resid features:
that
Token that
Feature activation+1.427
Top resid features:
allowing
Token allowing
Feature activation+0.022
Top resid features:
Hong
Token Hong
Feature activation+0.002
Top resid features:
Kong
Token Kong
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Police
TokenPolice
Feature activation-0.003
Top resid features:
were
Token were
Feature activation-0.001
Top resid features:
hoping
Token hoping
Feature activation+2.998
Top resid features:
body
Token body
Feature activation-0.000
Top resid features:
cameras
Token cameras
Feature activation+0.060
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
shed
Token shed
Feature activation+0.000
Top resid features:
light
Token light
Feature activation+0.000
Top resid features:
McCann
Token McCann
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.016
Top resid features:
he
Token he
Feature activation-0.000
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
worried
Token worried
Feature activation+0.120
Top resid features:
that
Token that
Feature activation+1.353
Top resid features:
Mr
Token Mr
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Dah
Token Dah
Feature activation-0.000
Top resid features:
mer
Tokenmer
Feature activation+0.229
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
Mr
Token Mr
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Dah
Token Dah
Feature activation-0.000
Top resid features:
mer
Tokenmer
Feature activation+0.191
Top resid features:
's
Token's
Feature activation+0.017
Top resid features:
claim
Token claim
Feature activation+1.520
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
driven
Token driven
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
York
Token York
Feature activation+0.001
Top resid features:
City
Token City
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
hoped
Token hoped
Feature activation+1.324
Top resid features:
that
Token that
Feature activation+1.249
Top resid features:
such
Token such
Feature activation+0.140
Top resid features:
an
Token an
Feature activation+0.118
Top resid features:
expansion
Token expansion
Feature activation+0.153
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Be
TokenBe
Feature activation-0.003
Top resid features:
ijing
Tokenijing
Feature activation-0.001
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
hoped
Token hoped
Feature activation+1.308
Top resid features:
that
Token that
Feature activation+1.236
Top resid features:
allowing
Token allowing
Feature activation+0.169
Top resid features:
Hong
Token Hong
Feature activation+0.004
Top resid features:
Kong
Token Kong
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
overtime
Token overtime
Feature activation+0.000
Top resid features:
pay
Token pay
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
It
Token It
Feature activation-0.004
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
expected
Token expected
Feature activation+1.773
Top resid features:
that
Token that
Feature activation+1.057
Top resid features:
ser
Token ser
Feature activation-0.013
Top resid features:
ge
Tokenge
Feature activation+0.001
Top resid features:
ants
Tokenants
Feature activation+0.126
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
grace
Token grace
Feature activation+0.004
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
indul
Token indul
Feature activation+0.001
Top resid features:
gence
Tokengence
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+1.143
Top resid features:
all
Token all
Feature activation+1.194
Top resid features:
the
Token the
Feature activation+0.099
Top resid features:
mountains
Token mountains
Feature activation+0.470
Top resid features:
near
Token near
Feature activation+0.021
Top resid features:
St
Token St
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
White
Token White
Feature activation+0.001
Top resid features:
House
Token House
Feature activation+0.001
Top resid features:
figured
Token figured
Feature activation+1.147
Top resid features:
that
Token that
Feature activation+1.499
Top resid features:
raising
Token raising
Feature activation+0.020
Top resid features:
alarms
Token alarms
Feature activation+0.056
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
Russian
Token Russian
Feature activation+0.000
Top resid features:
interference
Token interference
Feature activation+0.000
Top resid features:
CC
TokenCC
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
argued
Token argued
Feature activation+0.013
Top resid features:
that
Token that
Feature activation-0.009
Top resid features:
pundits
Token pundits
Feature activation-0.002
Top resid features:
predicted
Token predicted
Feature activation+2.489
Top resid features:
Senate
Token Senate
Feature activation+0.044
Top resid features:
Majority
Token Majority
Feature activation+0.005
Top resid features:
Leader
Token Leader
Feature activation+0.001
Top resid features:
Harry
Token Harry
Feature activation-0.000
Top resid features:
Reid
Token Reid
Feature activation+0.251
Top resid features:
Ŀ
TokenĿ
Feature activation+0.012
Top resid features:
âĢ
Token âĢ
Feature activation-0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.004
Top resid features:
We
TokenWe
Feature activation+0.010
Top resid features:
never
Token never
Feature activation+0.007
Top resid features:
knew
Token knew
Feature activation+2.062
Top resid features:
when
Token when
Feature activation+0.340
Top resid features:
this
Token this
Feature activation+0.098
Top resid features:
project
Token project
Feature activation+0.118
Top resid features:
started
Token started
Feature activation+0.158
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
au
Tokenau
Feature activation+0.003
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
April
Token April
Feature activation+0.025
Top resid features:
he
Token he
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
confident
Token confident
Feature activation+2.386
Top resid features:
"
Token "
Feature activation+0.004
Top resid features:
one
Tokenone
Feature activation+0.030
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
maybe
Token maybe
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.034
Top resid features:
overtime
Token overtime
Feature activation+0.000
Top resid features:
pay
Token pay
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
It
Token It
Feature activation-0.006
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
expected
Token expected
Feature activation+1.770
Top resid features:
that
Token that
Feature activation+0.994
Top resid features:
ser
Token ser
Feature activation-0.020
Top resid features:
ge
Tokenge
Feature activation-0.001
Top resid features:
ants
Tokenants
Feature activation+0.014
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
circulating
Token circulating
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
document
Token document
Feature activation-0.018
Top resid features:
that
Token that
Feature activation+0.077
Top resid features:
they
Token they
Feature activation+0.015
Top resid features:
hoped
Token hoped
Feature activation+2.702
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
serve
Token serve
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
starting
Token starting
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Be
TokenBe
Feature activation-0.008
Top resid features:
ijing
Tokenijing
Feature activation-0.002
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
hoped
Token hoped
Feature activation+1.277
Top resid features:
that
Token that
Feature activation+1.174
Top resid features:
allowing
Token allowing
Feature activation+0.212
Top resid features:
Hong
Token Hong
Feature activation+0.008
Top resid features:
Kong
Token Kong
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
no
Token no
Feature activation+0.005
Top resid features:
longer
Token longer
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
comfort
Token comfort
Feature activation-0.012
Top resid features:
everyone
Token everyone
Feature activation-0.005
Top resid features:
believed
Token believed
Feature activation+1.533
Top resid features:
it
Token it
Feature activation+0.993
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.013
Top resid features:
hoping
Token hoping
Feature activation+0.632
Top resid features:
that
Token that
Feature activation+1.727
Top resid features:
throwing
Token throwing
Feature activation+0.038
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.056
Top resid features:
minor
Token minor
Feature activation+0.045
Top resid features:
curse
Token curse
Feature activation+0.163
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
We
TokenWe
Feature activation+0.004
Top resid features:
never
Token never
Feature activation-0.004
Top resid features:
knew
Token knew
Feature activation+1.067
Top resid features:
when
Token when
Feature activation+1.126
Top resid features:
this
Token this
Feature activation+0.318
Top resid features:
project
Token project
Feature activation+0.105
Top resid features:
started
Token started
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
assumed
Token assumed
Feature activation+0.699
Top resid features:
that
Token that
Feature activation+0.697
Top resid features:
Mu
Token Mu
Feature activation+0.001
Top resid features:
q
Tokenq
Feature activation+0.002
Top resid features:
rin
Tokenrin
Feature activation+0.875
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
born
Token born
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
many
Token many
Feature activation-0.008
Top resid features:
self
Token self
Feature activation-0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
proclaimed
Tokenproclaimed
Feature activation-0.001
Top resid features:
libertarians
Token libertarians
Feature activation-0.008
Top resid features:
hoped
Token hoped
Feature activation+1.928
Top resid features:
a
Token a
Feature activation+0.376
Top resid features:
Rand
Token Rand
Feature activation+0.030
Top resid features:
Paul
Token Paul
Feature activation+0.145
Top resid features:
presidency
Token presidency
Feature activation+0.168
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.04

Head 3: 0.03

Head 4: 0.05

Head 5: 0.63

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.08

Head 10: 0.02

Head 11: 0.04

Positive logits

would6.81

would6.65

wouldn5.77

Would5.61

Would5.50

mattered5.41

'd5.37

depended5.18

Had5.05

belonged4.91

could4.81

existed4.80

could4.77

hadn4.75

needed4.71

had4.66

awaited4.58

risked4.57

couldn4.52

Was4.41

Negative logits

refuses-3.45

accuses-3.45

warns-3.43

lately-3.31

publishes-3.26

Says-3.26

continues-3.19

Adds-3.12

complains-3.10

Provides-3.00

Appears-2.95

concludes-2.87

ounces-2.87

advises-2.85

asserts-2.84

announces-2.83

urches-2.81

assures-2.78

discusses-2.77

boasts-2.75

INTERVAL 2.817 - 3.130
CONTAINS 0.000%

economically
Token economically
Feature activation+2.617
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Tokenover
Feature activation+3.130
would
Token would
Feature activation+0.088
convince
Token convince
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.347
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000

INTERVAL 2.504 - 2.817
CONTAINS 0.001%

compulsion
Token compulsion
Feature activation+1.754
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
sex
Token sex
Feature activation+2.662
with
Token with
Feature activation+0.000
corpses
Token corpses
Feature activation+2.655
would
Token would
Feature activation+0.045
set
Token set
Feature activation+0.000
a
Token a
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
precedent
Token precedent
Feature activation+0.259
allowing
Token allowing
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+1.255
to
Token to
Feature activation+0.000
prosper
Token prosper
Feature activation+2.367
economically
Token economically
Feature activation+2.617
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Tokenover
Feature activation+3.130
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.468
figured
Token figured
Feature activation+0.000
that
Token that
Feature activation+0.000
raising
Token raising
Feature activation+0.000
alarms
Token alarms
Feature activation+2.523
about
Token about
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
interference
Token interference
Feature activation+2.798
would
Token would
Feature activation+0.071
seem
Token seem
Feature activation+0.118
Ċ
TokenĊ
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
were
Token were
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
body
Token body
Feature activation+0.000
cameras
Token cameras
Feature activation+2.726
would
Token would
Feature activation+0.208
shed
Token shed
Feature activation+0.000
light
Token light
Feature activation+0.044
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
ser
Token ser
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
ants
Tokenants
Feature activation+2.436
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+2.574
would
Token would
Feature activation+0.164
thus
Token thus
Feature activation+0.138
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.000

INTERVAL 2.191 - 2.504
CONTAINS 0.002%

Reid
Token Reid
Feature activation+1.639
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
Nev
TokenNev
Feature activation+0.000
.)
Token.)
Feature activation+2.501
would
Token would
Feature activation+0.000
lose
Token lose
Feature activation+0.089
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
reelection
Token reelection
Feature activation+0.180
dropped
Token dropped
Feature activation+0.000
,
Token,
Feature activation+0.000
TM
Token TM
Feature activation+0.000
knew
Token knew
Feature activation+0.000
the
Token the
Feature activation+0.000
song
Token song
Feature activation+2.212
was
Token was
Feature activation+0.446
special
Token special
Feature activation+2.082
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
,
Token,
Feature activation+0.000
libertarians
Token libertarians
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000
a
Token a
Feature activation+0.000
Rand
Token Rand
Feature activation+0.000
Paul
Token Paul
Feature activation+0.318
presidency
Token presidency
Feature activation+2.272
would
Token would
Feature activation+0.148
yield
Token yield
Feature activation+0.047
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
policies
Token policies
Feature activation+0.000
circulating
Token circulating
Feature activation+0.000
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
hoped
Token hoped
Feature activation+2.373
would
Token would
Feature activation+0.000
serve
Token serve
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
starting
Token starting
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.054
he
Token he
Feature activation+0.470
though
Token though
Feature activation+0.905
their
Token their
Feature activation+0.177
house
Token house
Feature activation+2.226
was
Token was
Feature activation+0.719
bu
Token bu
Feature activation+0.000
gged
Tokengged
Feature activation+1.254
,
Token,
Feature activation+0.269
court
Token court
Feature activation+0.000

INTERVAL 1.878 - 2.191
CONTAINS 0.003%

,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.923
could
Token could
Feature activation+0.259
believe
Token believe
Feature activation+0.072
their
Token their
Feature activation+0.000
son
Token son
Feature activation+2.047
âĢ
TokenâĢ
Feature activation+0.000
their
Token their
Feature activation+0.000
son
Token son
Feature activation+2.047
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.713
s
Tokens
Feature activation+0.188
story
Token story
Feature activation+1.994
,
Token,
Feature activation+0.405
which
Token which
Feature activation+0.000
came
Token came
Feature activation+0.000
out
Token out
Feature activation+0.000
slowly
Token slowly
Feature activation+0.000
both
Token both
Feature activation+0.338
State
Token State
Feature activation+0.052
Government
Token Government
Feature activation+0.762
and
Token and
Feature activation+0.000
IS
Token IS
Feature activation+0.000
RO
TokenRO
Feature activation+2.037
can
Token can
Feature activation+0.000
work
Token work
Feature activation+0.000
together
Token together
Feature activation+0.061
in
Token in
Feature activation+0.000
carrying
Token carrying
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
that
Token that
Feature activation+0.157
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+1.901
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
any
Token any
Feature activation+0.000
help
Token help
Feature activation+0.785
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
only
Token only
Feature activation+0.000
wish
Token wish
Feature activation+0.000
that
Token that
Feature activation+0.374
CNN
Token CNN
Feature activation+2.001
had
Token had
Feature activation+0.000
that
Token that
Feature activation+0.000
much
Token much
Feature activation+0.000
power
Token power
Feature activation+0.187
to
Token to
Feature activation+0.000

INTERVAL 1.565 - 1.878
CONTAINS 0.008%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
I
TokenI
Feature activation+0.000
knew
Token knew
Feature activation+0.000
he
Token he
Feature activation+1.252
was
Token was
Feature activation+0.186
tough
Token tough
Feature activation+1.842
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.047
was
Token was
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
"
Token "
Feature activation+0.000
only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+1.250
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
crisis
Token crisis
Feature activation+1.661
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
an
Token an
Feature activation+0.000
EU
Token EU
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
use
Token use
Feature activation+0.416
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
committee
Token committee
Feature activation+1.582
would
Token would
Feature activation+0.488
help
Token help
Feature activation+0.000
foster
Token foster
Feature activation+0.000
a
Token a
Feature activation+0.000
host
Token host
Feature activation+0.000
true
Token true
Feature activation+0.000
line
Token line
Feature activation+0.410
that
Token that
Feature activation+0.624
Harding
Token Harding
Feature activation+1.201
and
Token and
Feature activation+0.000
Caldwell
Token Caldwell
Feature activation+1.610
should
Token should
Feature activation+0.250
have
Token have
Feature activation+0.308
taken
Token taken
Feature activation+0.452
.
Token.
Feature activation+0.017
As
Token As
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
always
Token always
Feature activation+0.000
thought
Token thought
Feature activation+0.000
bonuses
Token bonuses
Feature activation+1.830
were
Token were
Feature activation+0.407
contingent
Token contingent
Feature activation+0.029
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
job
Token job
Feature activation+0.081

INTERVAL 1.252 - 1.565
CONTAINS 0.016%

was
Token was
Feature activation+0.000
like
Token like
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
wish
Token wish
Feature activation+0.000
it
Token it
Feature activation+1.310
was
Token was
Feature activation+0.196
that
Token that
Feature activation+0.000
thought
Token thought
Feature activation+0.000
out
Token out
Feature activation+0.433
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
political
Token political
Feature activation+0.000
bonds
Token bonds
Feature activation+1.145
with
Token with
Feature activation+0.000
Hezbollah
Token Hezbollah
Feature activation+1.361
would
Token would
Feature activation+0.214
offer
Token offer
Feature activation+0.064
them
Token them
Feature activation+0.156
greater
Token greater
Feature activation+0.000
security
Token security
Feature activation+0.374
by
Token by
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
Livingston
Token Livingston
Feature activation+1.253
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.137
will
Tokenwill
Feature activation+0.000
bring
Token bring
Feature activation+0.000
huge
Token huge
Feature activation+0.000
because
Token because
Feature activation+0.000
he
Token he
Feature activation+0.053
knew
Token knew
Feature activation+0.149
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
man
Token man
Feature activation+1.270
,
Token,
Feature activation+0.466
Robert
Token Robert
Feature activation+0.000
Baxter
Token Baxter
Feature activation+0.144
,
Token,
Feature activation+1.437
was
Token was
Feature activation+0.173
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
playoff
Token playoff
Feature activation+0.184
spot
Token spot
Feature activation+1.295
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+1.291
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
unacceptable
Token unacceptable
Feature activation+0.170
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000

INTERVAL 0.939 - 1.252
CONTAINS 0.037%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
thought
Token thought
Feature activation+0.048
that
Token that
Feature activation+1.238
since
Token since
Feature activation+0.194
we
Token we
Feature activation+0.390
were
Token were
Feature activation+0.000
incentiv
Token incentiv
Feature activation+0.000
izing
Tokenizing
Feature activation+0.124
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
surrogate
Token surrogate
Feature activation+0.672
baby
Token baby
Feature activation+0.864
from
Token from
Feature activation+0.000
India
Token India
Feature activation+1.107
cost
Token cost
Feature activation+0.350
as
Token as
Feature activation+0.000
little
Token little
Feature activation+0.000
as
Token as
Feature activation+0.000
$
Token $
Feature activation+0.000
Founders
Token Founders
Feature activation+0.000
beer
Token beer
Feature activation+0.000
somewhere
Token somewhere
Feature activation+0.000
you
Token you
Feature activation+0.000
wish
Token wish
Feature activation+0.000
you
Token you
Feature activation+0.966
could
Token could
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
you
Token you
Feature activation+0.000
curious
Token curious
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
it
Token it
Feature activation+1.009
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+1.134
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
pie
Token pie
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.026
but
Token but
Feature activation+0.000
just
Token just
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
safe
Token safe
Feature activation+0.990
...
Token...
Feature activation+0.056
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Mus
TokenMus
Feature activation+0.000

INTERVAL 0.626 - 0.939
CONTAINS 0.096%

even
Token even
Feature activation+0.000
sure
Token sure
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.891
existed
Token existed
Feature activation+0.920
and
Token and
Feature activation+0.000
examined
Token examined
Feature activation+0.000
its
Token its
Feature activation+0.000
molecular
Token molecular
Feature activation+0.000
structure
Token structure
Feature activation+0.000
but
Token but
Feature activation+0.000
by
Token by
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
Wil
Token Wil
Feature activation+0.000
ley
Tokenley
Feature activation+0.785
was
Token was
Feature activation+0.000
bere
Token bere
Feature activation+0.000
ft
Tokenft
Feature activation+0.000
of
Token of
Feature activation+0.000
belie
Token belie
Feature activation+0.000
'
Token'
Feature activation+0.000
Association
Token Association
Feature activation+0.000
warned
Token warned
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
pledge
Token pledge
Feature activation+0.679
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.110
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
me
Token me
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.851
hurt
Token hurt
Feature activation+0.711
something
Token something
Feature activation+0.569
else
Token else
Feature activation+0.671
..."
Token ..."
Feature activation+0.000
which
Token which
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
the
Token the
Feature activation+0.000
cause
Token cause
Feature activation+0.472
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
incident
Token incident
Feature activation+0.688
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ey
TokenEy
Feature activation+0.000
ewitness
Tokenewitness
Feature activation+0.000

INTERVAL 0.313 - 0.626
CONTAINS 0.294%

a
Token a
Feature activation+0.000
lightweight
Token lightweight
Feature activation+0.000
at
Token at
Feature activation+0.000
v
Tokenv
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.453
would
Token would
Feature activation+0.078
be
Token be
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
fun
Token fun
Feature activation+0.462
race
Token race
Feature activation+0.000
they
Token they
Feature activation+0.027
learned
Token learned
Feature activation+0.000
their
Token their
Feature activation+0.000
lessons
Token lessons
Feature activation+0.121
from
Token from
Feature activation+0.365
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
were
Token were
Feature activation+0.000
wondering
Token wondering
Feature activation+0.000
an
Token an
Feature activation+0.000
early
Token early
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
0
Token0
Feature activation+0.000
lead
Token lead
Feature activation+0.525
.
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
d
Tokend
Feature activation+0.040
heard
Token heard
Feature activation+0.181
it
Token it
Feature activation+0.081
was
Token was
Feature activation+0.004
something
Token something
Feature activation+0.000
you
Token you
Feature activation+0.338
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.184
t
Tokent
Feature activation+0.000
leave
Token leave
Feature activation+0.000
dismissed
Token dismissed
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
ECB
Token ECB
Feature activation+0.567
should
Token should
Feature activation+0.000
intervene
Token intervene
Feature activation+0.000
by
Token by
Feature activation+0.000
directly
Token directly
Feature activation+0.000
buying
Token buying
Feature activation+0.000

INTERVAL 0.000 - 0.313
CONTAINS 99.541%

in
Token in
Feature activation+0.000
athletics
Token athletics
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
national
Token national
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
I
Token I
Feature activation+0.000
cautiously
Token cautiously
Feature activation+0.000
walked
Token walked
Feature activation+0.000
down
Token down
Feature activation+0.000
a
Token a
Feature activation+0.000
narrow
Token narrow
Feature activation+0.000
corridor
Token corridor
Feature activation+0.000
in
Token in
Feature activation+0.000
ON
Token ON
Feature activation+0.000
I
TokenI
Feature activation+0.000
research
Token research
Feature activation+0.000
a
Token a
Feature activation+0.000
British
Token British
Feature activation+0.000
Department
Token Department
Feature activation+0.000
for
Token for
Feature activation+0.000
Transport
Token Transport
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
that
Token that
Feature activation+0.000
flights
Token flights
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
were
Token were
Feature activation+0.000
being
Token being
Feature activation+0.000
made
Token made
Feature activation+0.000
for
Token for
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Resistance
Token Resistance
Feature activation+0.028
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
print
Token print
Feature activation+0.000
them
Token them
Feature activation+0.000
out
Token out
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H10.5: (feature 5091)

TOP ACTIVATIONS
MAX = 5.699

business
Token business
Feature activation+4.510
or
Token or
Feature activation+0.424
going
Token going
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
school
Token school
Feature activation+5.699
?
Token?
Feature activation+0.584
And
Token And
Feature activation+0.000
does
Token does
Feature activation+0.000
that
Token that
Feature activation+0.028
security
Token security
Feature activation+0.839
,
Token,
Feature activation+0.319
a
Token a
Feature activation+0.000
first
Token first
Feature activation+0.176
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.462
shooter
Token shooter
Feature activation+5.401
?"
Token?"
Feature activation+0.000
Image
Token Image
Feature activation+0.000
courtesy
Token courtesy
Feature activation+0.000
Z
Token Z
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
liberty
Token liberty
Feature activation+2.892
thing
Token thing
Feature activation+3.766
working
Token working
Feature activation+2.226
out
Token out
Feature activation+2.996
for
Token for
Feature activation+0.662
you
Token you
Feature activation+5.390
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
also
Token also
Feature activation+0.000
voting
Token voting
Feature activation+0.850
against
Token against
Feature activation+0.171
their
Token their
Feature activation+0.123
self
Token self
Feature activation+2.503
-
Token-
Feature activation+0.078
interest
Tokeninterest
Feature activation+5.231
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
Every
Token Every
Feature activation+0.000
Young
Token Young
Feature activation+0.000
Chef
Token Chef
Feature activation+0.000
friendly
Tokenfriendly
Feature activation+0.000
public
Token public
Feature activation+0.000
transport
Token transport
Feature activation+3.286
where
Token where
Feature activation+0.212
you
Token you
Feature activation+2.137
live
Token live
Feature activation+5.203
?
Token?
Feature activation+0.686
Tell
Token Tell
Feature activation+0.000
us
Token us
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
app
Token app
Feature activation+2.621
like
Token like
Feature activation+0.000
this
Token this
Feature activation+4.397
for
Token for
Feature activation+0.295
your
Token your
Feature activation+0.000
friend
Token friend
Feature activation+4.937
.
Token.
Feature activation+1.577
Well
Token Well
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
as
Token as
Feature activation+0.018
readily
Token readily
Feature activation+2.154
as
Token as
Feature activation+0.049
Mel
Token Mel
Feature activation+0.000
burn
Tokenburn
Feature activation+1.926
ians
Tokenians
Feature activation+4.909
?
Token?
Feature activation+0.083
Why
Token Why
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.847
unable
Token unable
Feature activation+0.161
to
Token to
Feature activation+0.065
read
Token read
Feature activation+3.795
her
Token her
Feature activation+0.000
own
Token own
Feature activation+0.000
words
Token words
Feature activation+4.901
?
Token?
Feature activation+0.409
Surely
Token Surely
Feature activation+0.000
,
Token,
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.202
Avengers
Token Avengers
Feature activation+1.530
:
Token:
Feature activation+0.000
Age
Token Age
Feature activation+0.000
of
Token of
Feature activation+0.000
Ultron
Token Ultron
Feature activation+4.733
?
Token?
Feature activation+0.000
Email
Token Email
Feature activation+0.000
arts
Token arts
Feature activation+0.000
correspondent
Token correspondent
Feature activation+0.000
Emma
Token Emma
Feature activation+0.000
any
Token any
Feature activation+0.000
questions
Token questions
Feature activation+1.860
about
Token about
Feature activation+0.352
cat
Token cat
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
ers
Tokeners
Feature activation+4.669
?
Token?
Feature activation+0.311
Share
Token Share
Feature activation+0.000
them
Token them
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
harm
Token harm
Feature activation+0.724
in
Token in
Feature activation+0.000
telling
Token telling
Feature activation+0.073
her
Token her
Feature activation+3.290
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+4.665
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.339
It
TokenIt
Feature activation+0.000
game
Token game
Feature activation+3.023
we
Token we
Feature activation+0.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.181
re
Tokenre
Feature activation+0.961
covering
Token covering
Feature activation+4.627
that
Token that
Feature activation+0.444
you
Token you
Feature activation+0.061
âĢ
TokenâĢ
Feature activation+0.424
Ļ
TokenĻ
Feature activation+1.140
d
Tokend
Feature activation+0.687
inally
Tokeninally
Feature activation+0.000
(
Token (
Feature activation+0.000
is
Tokenis
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
word
Token word
Feature activation+4.613
?),
Token?),
Feature activation+0.000
they
Token they
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
audience
Token audience
Feature activation+0.000
and
Token and
Feature activation+0.372
diet
Token diet
Feature activation+2.373
to
Token to
Feature activation+0.000
save
Token save
Feature activation+0.835
their
Token their
Feature activation+0.000
health
Token health
Feature activation+4.574
?
Token?
Feature activation+0.554
Or
Token Or
Feature activation+0.332
will
Token will
Feature activation+0.000
they
Token they
Feature activation+1.113
carry
Token carry
Feature activation+0.000
spawned
Token spawned
Feature activation+0.669
of
Token of
Feature activation+0.000
unusually
Token unusually
Feature activation+0.000
warm
Token warm
Feature activation+0.040
ocean
Token ocean
Feature activation+2.956
waters
Token waters
Feature activation+4.572
?
Token?
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+2.568
in
Token in
Feature activation+0.000
real
Token real
Feature activation+0.000
-
Token-
Feature activation+0.000
life
Tokenlife
Feature activation+4.566
use
Token use
Feature activation+3.767
?
Token?
Feature activation+0.441
Let
Token Let
Feature activation+0.000
us
Token us
Feature activation+0.000
know
Token know
Feature activation+0.000
âĤ¬
TokenâĤ¬
Feature activation+0.000
Ëľ
TokenËľ
Feature activation+0.000
for
Tokenfor
Feature activation+0.244
loops
Token loops
Feature activation+3.462
âĢ
TokenâĢ
Feature activation+0.300
Ļ
TokenĻ
Feature activation+4.551
,
Token,
Feature activation+2.667
Ã
Token Ã
Feature activation+0.000
¢
Token¢
Feature activation+0.000
âĤ¬
TokenâĤ¬
Feature activation+0.000
Ëľ
TokenËľ
Feature activation+0.730
women
Token women
Feature activation+2.631
and
Token and
Feature activation+0.061
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
sex
Tokensex
Feature activation+0.407
groups
Token groups
Feature activation+4.550
?).
Token?).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mur
TokenMur
Feature activation+0.000
iel
Tokeniel
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.720
re
Tokenre
Feature activation+1.669
missing
Token missing
Feature activation+2.562
in
Token in
Feature activation+0.716
the
Token the
Feature activation+0.000
gallery
Token gallery
Feature activation+4.527
?
Token?
Feature activation+0.026
Let
Token Let
Feature activation+0.000
us
Token us
Feature activation+0.000
know
Token know
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.466
risks
Token risks
Feature activation+1.822
like
Token like
Feature activation+0.000
starting
Token starting
Feature activation+0.000
a
Token a
Feature activation+0.000
business
Token business
Feature activation+4.510
or
Token or
Feature activation+0.424
going
Token going
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
school
Token school
Feature activation+5.699

Top DFA by src position
MAX = 3.606

,
Token,
Feature activation+0.000
Top resid features:
do
Token do
Feature activation-0.001
Top resid features:
they
Token they
Feature activation+0.353
Top resid features:
take
Token take
Feature activation+0.567
Top resid features:
more
Token more
Feature activation+0.424
Top resid features:
risks
Token risks
Feature activation+2.443
Top resid features:
like
Token like
Feature activation+0.677
Top resid features:
starting
Token starting
Feature activation+0.181
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
business
Token business
Feature activation+0.264
Top resid features:
or
Token or
Feature activation+0.425
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
"
Token "
Feature activation-0.059
Top resid features:
What
TokenWhat
Feature activation+0.043
Top resid features:
is
Token is
Feature activation+0.279
Top resid features:
this
Token this
Feature activation+0.845
Top resid features:
,
Token,
Feature activation+3.215
Top resid features:
a
Token a
Feature activation+1.102
Top resid features:
first
Token first
Feature activation+0.167
Top resid features:
-
Token-
Feature activation+0.023
Top resid features:
person
Tokenperson
Feature activation+0.092
Top resid features:
shooter
Token shooter
Feature activation+0.139
Top resid features:
leave
Token leave
Feature activation+0.458
Top resid features:
me
Token me
Feature activation+0.146
Top resid features:
alone
Token alone
Feature activation+0.651
Top resid features:
personal
Token personal
Feature activation+0.146
Top resid features:
liberty
Token liberty
Feature activation+0.357
Top resid features:
thing
Token thing
Feature activation+1.158
Top resid features:
working
Token working
Feature activation+1.012
Top resid features:
out
Token out
Feature activation+0.443
Top resid features:
for
Token for
Feature activation+0.361
Top resid features:
you
Token you
Feature activation+0.191
Top resid features:
?"
Token?"
Feature activation+0.000
Top resid features:
interest
Tokeninterest
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
But
Token But
Feature activation+0.014
Top resid features:
are
Token are
Feature activation+0.068
Top resid features:
voters
Token voters
Feature activation+0.439
Top resid features:
really
Token really
Feature activation+3.606
Top resid features:
voting
Token voting
Feature activation+0.473
Top resid features:
against
Token against
Feature activation+0.760
Top resid features:
their
Token their
Feature activation+0.096
Top resid features:
self
Token self
Feature activation+0.071
Top resid features:
-
Token-
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+0.894
Top resid features:
bike
Token bike
Feature activation+0.119
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
friendly
Tokenfriendly
Feature activation+0.292
Top resid features:
public
Token public
Feature activation+0.072
Top resid features:
transport
Token transport
Feature activation+1.499
Top resid features:
where
Token where
Feature activation+0.315
Top resid features:
you
Token you
Feature activation+0.519
Top resid features:
live
Token live
Feature activation+0.284
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Tell
Token Tell
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
publish
Token publish
Feature activation+0.268
Top resid features:
an
Token an
Feature activation+0.266
Top resid features:
app
Token app
Feature activation+1.176
Top resid features:
like
Token like
Feature activation+0.238
Top resid features:
this
Token this
Feature activation+1.271
Top resid features:
for
Token for
Feature activation+0.310
Top resid features:
your
Token your
Feature activation+0.063
Top resid features:
friend
Token friend
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Well
Token Well
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.616
Top resid features:
attend
Token attend
Feature activation+0.710
Top resid features:
sports
Token sports
Feature activation+0.193
Top resid features:
as
Token as
Feature activation+0.202
Top resid features:
readily
Token readily
Feature activation+0.141
Top resid features:
as
Token as
Feature activation+2.271
Top resid features:
Mel
Token Mel
Feature activation+0.014
Top resid features:
burn
Tokenburn
Feature activation+0.104
Top resid features:
ians
Tokenians
Feature activation+0.599
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Why
Token Why
Feature activation+0.000
Top resid features:
school
Token school
Feature activation+0.003
Top resid features:
no
Token no
Feature activation+0.002
Top resid features:
less
Token less
Feature activation+0.004
Top resid features:
--
Token --
Feature activation+0.507
Top resid features:
be
Token be
Feature activation+0.599
Top resid features:
unable
Token unable
Feature activation+2.379
Top resid features:
to
Token to
Feature activation+1.053
Top resid features:
read
Token read
Feature activation+0.257
Top resid features:
her
Token her
Feature activation+0.096
Top resid features:
own
Token own
Feature activation+0.068
Top resid features:
words
Token words
Feature activation+0.149
Top resid features:
Sunday
Token Sunday
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Have
TokenHave
Feature activation-0.000
Top resid features:
you
Token you
Feature activation+2.367
Top resid features:
been
Token been
Feature activation+0.739
Top resid features:
involved
Token involved
Feature activation+0.716
Top resid features:
in
Token in
Feature activation+0.605
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
filming
Token filming
Feature activation+0.251
Top resid features:
?
Token?
Feature activation-0.002
Top resid features:
Do
Token Do
Feature activation+0.026
Top resid features:
you
Token you
Feature activation+0.832
Top resid features:
have
Token have
Feature activation+0.527
Top resid features:
any
Token any
Feature activation+0.800
Top resid features:
questions
Token questions
Feature activation+1.802
Top resid features:
about
Token about
Feature activation+0.241
Top resid features:
cat
Token cat
Feature activation+0.004
Top resid features:
whisk
Token whisk
Feature activation+0.004
Top resid features:
ers
Tokeners
Feature activation+0.051
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
What
Token What
Feature activation+0.016
Top resid features:
's
Token's
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
harm
Token harm
Feature activation+1.217
Top resid features:
in
Token in
Feature activation+2.769
Top resid features:
telling
Token telling
Feature activation+0.294
Top resid features:
her
Token her
Feature activation+0.295
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
truth
Token truth
Feature activation+0.085
Top resid features:
?"
Token?"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Do
TokenDo
Feature activation-0.027
Top resid features:
you
Token you
Feature activation+0.775
Top resid features:
have
Token have
Feature activation+0.911
Top resid features:
an
Token an
Feature activation+0.430
Top resid features:
opinion
Token opinion
Feature activation+1.375
Top resid features:
about
Token about
Feature activation+0.391
Top resid features:
a
Token a
Feature activation+0.249
Top resid features:
game
Token game
Feature activation+0.534
Top resid features:
we
Token we
Feature activation+0.121
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
sub
Token sub
Feature activation-0.001
Top resid features:
lim
Tokenlim
Feature activation-0.000
Top resid features:
inally
Tokeninally
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.025
Top resid features:
is
Tokenis
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+2.353
Top resid features:
a
Token a
Feature activation+2.290
Top resid features:
word
Token word
Feature activation+0.405
Top resid features:
?),
Token?),
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
help
Token help
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Will
Token Will
Feature activation+0.059
Top resid features:
they
Token they
Feature activation+0.824
Top resid features:
change
Token change
Feature activation+0.771
Top resid features:
tack
Token tack
Feature activation+1.079
Top resid features:
and
Token and
Feature activation+0.844
Top resid features:
diet
Token diet
Feature activation+0.051
Top resid features:
to
Token to
Feature activation+0.515
Top resid features:
save
Token save
Feature activation+0.575
Top resid features:
their
Token their
Feature activation+0.077
Top resid features:
Sandy
Token Sandy
Feature activation+0.347
Top resid features:
just
Token just
Feature activation+0.433
Top resid features:
a
Token a
Feature activation+0.392
Top resid features:
hurricane
Token hurricane
Feature activation+0.348
Top resid features:
,
Token,
Feature activation+0.387
Top resid features:
or
Token or
Feature activation+0.960
Top resid features:
an
Token an
Feature activation+0.382
Top resid features:
ang
Token ang
Feature activation+0.002
Top resid features:
rier
Tokenrier
Feature activation+0.326
Top resid features:
child
Token child
Feature activation+0.753
Top resid features:
spawned
Token spawned
Feature activation+0.145
Top resid features:
you
Token you
Feature activation+0.660
Top resid features:
see
Token see
Feature activation+0.986
Top resid features:
this
Token this
Feature activation+0.677
Top resid features:
as
Token as
Feature activation+0.507
Top resid features:
an
Token an
Feature activation+0.284
Top resid features:
issue
Token issue
Feature activation+1.180
Top resid features:
in
Token in
Feature activation+0.514
Top resid features:
real
Token real
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
life
Tokenlife
Feature activation+0.036
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
value
Token value
Feature activation-0.000
Top resid features:
).
Token).
Feature activation+0.051
Top resid features:
Did
Token Did
Feature activation+0.019
Top resid features:
you
Token you
Feature activation+0.654
Top resid features:
find
Token find
Feature activation+0.235
Top resid features:
yourself
Token yourself
Feature activation+1.320
Top resid features:
struggling
Token struggling
Feature activation+0.902
Top resid features:
to
Token to
Feature activation+0.909
Top resid features:
get
Token get
Feature activation+0.238
Top resid features:
back
Token back
Feature activation+0.201
Top resid features:
into
Token into
Feature activation+0.106
Top resid features:
is
Token is
Feature activation+0.031
Top resid features:
it
Token it
Feature activation+0.860
Top resid features:
something
Token something
Feature activation+0.386
Top resid features:
to
Token to
Feature activation+0.293
Top resid features:
do
Token do
Feature activation+0.252
Top resid features:
with
Token with
Feature activation+1.527
Top resid features:
women
Token women
Feature activation+0.488
Top resid features:
and
Token and
Feature activation+0.826
Top resid features:
single
Token single
Feature activation+0.027
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
sex
Tokensex
Feature activation+0.063
Top resid features:
city
Token city
Feature activation+0.392
Top resid features:
we
Token we
Feature activation+0.118
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
re
Tokenre
Feature activation+0.138
Top resid features:
missing
Token missing
Feature activation+2.694
Top resid features:
in
Token in
Feature activation+0.183
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
gallery
Token gallery
Feature activation+0.167
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Let
Token Let
Feature activation+0.000
Top resid features:
do
Token do
Feature activation-0.001
Top resid features:
they
Token they
Feature activation+0.184
Top resid features:
take
Token take
Feature activation+0.247
Top resid features:
more
Token more
Feature activation+0.742
Top resid features:
risks
Token risks
Feature activation+1.227
Top resid features:
like
Token like
Feature activation+1.567
Top resid features:
starting
Token starting
Feature activation+0.637
Top resid features:
a
Token a
Feature activation+0.095
Top resid features:
business
Token business
Feature activation+0.216
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.05

Head 3: 0.05

Head 4: 0.06

Head 5: 0.62

Head 6: 0.02

Head 7: 0.02

Head 8: 0.02

Head 9: 0.08

Head 10: 0.01

Head 11: 0.02

Positive logits

)?11.31

?10.84

?).10.55

?),10.31

?)10.15

?"9.96

?'9.85

?!9.85

??9.53

'?9.52

?」9.49

?9.48

?",9.43

?:9.42

???9.17

?".9.17

?,9.14

!?9.02

?'"9.01

?!"9.00

Negative logits

/​-3.01

iets-2.65

mast-2.60

���-2.54

��極-2.49

jong-2.48

];-2.41

senal-2.40

},"-2.30

atern-2.29

};-2.29

iors-2.27

anmar-2.27

.")-2.24

ouble-2.23

".[-2.22

CLUD-2.22

");-2.20

teness-2.19

achine-2.19

INTERVAL 5.129 - 5.699
CONTAINS 0.001%

friendly
Tokenfriendly
Feature activation+0.000
public
Token public
Feature activation+0.000
transport
Token transport
Feature activation+3.286
where
Token where
Feature activation+0.212
you
Token you
Feature activation+2.137
live
Token live
Feature activation+5.203
?
Token?
Feature activation+0.686
Tell
Token Tell
Feature activation+0.000
us
Token us
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
business
Token business
Feature activation+4.510
or
Token or
Feature activation+0.424
going
Token going
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
school
Token school
Feature activation+5.699
?
Token?
Feature activation+0.584
And
Token And
Feature activation+0.000
does
Token does
Feature activation+0.000
that
Token that
Feature activation+0.028
security
Token security
Feature activation+0.839
liberty
Token liberty
Feature activation+2.892
thing
Token thing
Feature activation+3.766
working
Token working
Feature activation+2.226
out
Token out
Feature activation+2.996
for
Token for
Feature activation+0.662
you
Token you
Feature activation+5.390
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
also
Token also
Feature activation+0.000
voting
Token voting
Feature activation+0.850
against
Token against
Feature activation+0.171
their
Token their
Feature activation+0.123
self
Token self
Feature activation+2.503
-
Token-
Feature activation+0.078
interest
Tokeninterest
Feature activation+5.231
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
Every
Token Every
Feature activation+0.000
Young
Token Young
Feature activation+0.000
Chef
Token Chef
Feature activation+0.000
,
Token,
Feature activation+0.319
a
Token a
Feature activation+0.000
first
Token first
Feature activation+0.176
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.462
shooter
Token shooter
Feature activation+5.401
?"
Token?"
Feature activation+0.000
Image
Token Image
Feature activation+0.000
courtesy
Token courtesy
Feature activation+0.000
Z
Token Z
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000

INTERVAL 4.559 - 5.129
CONTAINS 0.001%

an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+2.568
in
Token in
Feature activation+0.000
real
Token real
Feature activation+0.000
-
Token-
Feature activation+0.000
life
Tokenlife
Feature activation+4.566
use
Token use
Feature activation+3.767
?
Token?
Feature activation+0.441
Let
Token Let
Feature activation+0.000
us
Token us
Feature activation+0.000
know
Token know
Feature activation+0.000
spawned
Token spawned
Feature activation+0.669
of
Token of
Feature activation+0.000
unusually
Token unusually
Feature activation+0.000
warm
Token warm
Feature activation+0.040
ocean
Token ocean
Feature activation+2.956
waters
Token waters
Feature activation+4.572
?
Token?
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
any
Token any
Feature activation+0.000
questions
Token questions
Feature activation+1.860
about
Token about
Feature activation+0.352
cat
Token cat
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
ers
Tokeners
Feature activation+4.669
?
Token?
Feature activation+0.311
Share
Token Share
Feature activation+0.000
them
Token them
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+3.023
we
Token we
Feature activation+0.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.181
re
Tokenre
Feature activation+0.961
covering
Token covering
Feature activation+4.627
that
Token that
Feature activation+0.444
you
Token you
Feature activation+0.061
âĢ
TokenâĢ
Feature activation+0.424
Ļ
TokenĻ
Feature activation+1.140
d
Tokend
Feature activation+0.687
and
Token and
Feature activation+0.372
diet
Token diet
Feature activation+2.373
to
Token to
Feature activation+0.000
save
Token save
Feature activation+0.835
their
Token their
Feature activation+0.000
health
Token health
Feature activation+4.574
?
Token?
Feature activation+0.554
Or
Token Or
Feature activation+0.332
will
Token will
Feature activation+0.000
they
Token they
Feature activation+1.113
carry
Token carry
Feature activation+0.000

INTERVAL 3.989 - 4.559
CONTAINS 0.008%

âĤ¬
TokenâĤ¬
Feature activation+0.000
Ëľ
TokenËľ
Feature activation+0.730
if
Tokenif
Feature activation+0.000
statements
Token statements
Feature activation+2.934
âĢ
TokenâĢ
Feature activation+0.333
Ļ
TokenĻ
Feature activation+4.374
,
Token,
Feature activation+2.068
Ã
Token Ã
Feature activation+0.000
¢
Token¢
Feature activation+0.000
âĤ¬
TokenâĤ¬
Feature activation+0.000
Ëľ
TokenËľ
Feature activation+0.823
she
Token she
Feature activation+0.225
have
Token have
Feature activation+0.000
Albert
Token Albert
Feature activation+0.692
connect
Token connect
Feature activation+1.308
them
Token them
Feature activation+3.694
together
Token together
Feature activation+4.326
to
Token to
Feature activation+0.249
talk
Token talk
Feature activation+2.777
again
Token again
Feature activation+3.549
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
do
Token do
Feature activation+0.862
what
Token what
Feature activation+0.818
we
Token we
Feature activation+0.998
tell
Token tell
Feature activation+1.139
them
Token them
Feature activation+3.520
to
Token to
Feature activation+4.287
and
Token and
Feature activation+0.579
we
Token we
Feature activation+1.167
feed
Token feed
Feature activation+0.404
them
Token them
Feature activation+2.394
anyway
Token anyway
Feature activation+2.194
be
Token be
Feature activation+0.132
more
Token more
Feature activation+0.029
casual
Token casual
Feature activation+2.312
about
Token about
Feature activation+0.072
our
Token our
Feature activation+0.050
safety
Token safety
Feature activation+4.146
than
Token than
Feature activation+0.281
we
Token we
Feature activation+1.691
are
Token are
Feature activation+3.990
today
Token today
Feature activation+4.084
?
Token?
Feature activation+0.000
gain
Token gain
Feature activation+0.045
influence
Token influence
Feature activation+2.918
at
Token at
Feature activation+0.316
W
Token W
Feature activation+0.000
3
Token3
Feature activation+0.396
C
TokenC
Feature activation+4.106
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
your
Token your
Feature activation+0.000

INTERVAL 3.419 - 3.989
CONTAINS 0.019%

Did
Token Did
Feature activation+0.000
she
Token she
Feature activation+0.225
have
Token have
Feature activation+0.000
Albert
Token Albert
Feature activation+0.692
connect
Token connect
Feature activation+1.308
them
Token them
Feature activation+3.694
together
Token together
Feature activation+4.326
to
Token to
Feature activation+0.249
talk
Token talk
Feature activation+2.777
again
Token again
Feature activation+3.549
?
Token?
Feature activation+0.000
the
Token the
Feature activation+0.000
author
Token author
Feature activation+4.018
of
Token of
Feature activation+0.409
the
Token the
Feature activation+0.000
fake
Token fake
Feature activation+0.268
article
Token article
Feature activation+3.835
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.124
the
Token the
Feature activation+0.000
piece
Token piece
Feature activation+0.986
authenticity
Token authenticity
Feature activation+2.730
Ã
Token Ã
Feature activation+0.000
¢
Token¢
Feature activation+0.000
âĤ¬
TokenâĤ¬
Feature activation+0.000
Ëľ
TokenËľ
Feature activation+0.000
for
Tokenfor
Feature activation+0.244
loops
Token loops
Feature activation+3.462
âĢ
TokenâĢ
Feature activation+0.300
Ļ
TokenĻ
Feature activation+4.551
,
Token,
Feature activation+2.667
Ã
Token Ã
Feature activation+0.000
¢
Token¢
Feature activation+0.000
true
Token true
Feature activation+0.000
and
Token and
Feature activation+0.000
authoritative
Token authoritative
Feature activation+0.018
word
Token word
Feature activation+2.261
of
Token of
Feature activation+0.000
God
Token God
Feature activation+3.645
(
Token (
Feature activation+0.128
ie
Tokenie
Feature activation+0.378
factual
Token factual
Feature activation+0.705
,
Token,
Feature activation+0.604
where
Token where
Feature activation+0.728
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
beat
Token beat
Feature activation+0.000
back
Token back
Feature activation+0.000
Terry
Token Terry
Feature activation+0.000
Wilson
Token Wilson
Feature activation+3.531
and
Token and
Feature activation+0.157
Travis
Token Travis
Feature activation+0.000
J
Token J
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
en
Tokenen
Feature activation+4.051

INTERVAL 2.849 - 3.419
CONTAINS 0.030%

"
Token "
Feature activation+0.000
How
TokenHow
Feature activation+0.000
can
Token can
Feature activation+0.000
I
Token I
Feature activation+0.000
ask
Token ask
Feature activation+0.000
directions
Token directions
Feature activation+3.046
?",
Token?",
Feature activation+0.000
"
Token "
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.034
hit
Token hit
Feature activation+1.708
someone
Token someone
Feature activation+2.347
he
Token he
Feature activation+0.226
claims
Token claims
Feature activation+0.218
to
Token to
Feature activation+1.109
love
Token love
Feature activation+3.087
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
this
Token this
Feature activation+0.000
why
Token why
Feature activation+0.000
should
Token should
Feature activation+0.000
you
Token you
Feature activation+1.151
learn
Token learn
Feature activation+1.989
Egyptian
Token Egyptian
Feature activation+3.204
Arabic
Token Arabic
Feature activation+3.351
?
Token?
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
most
Token most
Feature activation+0.000
have
Token have
Feature activation+0.000
an
Token an
Feature activation+0.000
opinion
Token opinion
Feature activation+0.747
about
Token about
Feature activation+0.066
a
Token a
Feature activation+0.105
game
Token game
Feature activation+3.023
we
Token we
Feature activation+0.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.181
re
Tokenre
Feature activation+0.961
covering
Token covering
Feature activation+4.627
boy
Token boy
Feature activation+3.509
and
Token and
Feature activation+0.070
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
young
Token young
Feature activation+0.000
man
Token man
Feature activation+3.012
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
teens
Token teens
Feature activation+3.509
?
Token?
Feature activation+0.952
Abuse
Token Abuse
Feature activation+0.126

INTERVAL 2.280 - 2.849
CONTAINS 0.046%

he
Token he
Feature activation+0.074
ever
Token ever
Feature activation+0.083
want
Token want
Feature activation+0.591
to
Token to
Feature activation+0.838
do
Token do
Feature activation+0.666
anything
Token anything
Feature activation+2.328
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
is
Token is
Feature activation+0.000
art
Token art
Feature activation+1.854
,
Token,
Feature activation+0.976
"
Token "
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
this
Token this
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
normal
Token normal
Feature activation+2.350
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
city
Token city
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.348
t
Tokent
Feature activation+1.076
have
Token have
Feature activation+0.701
speakers
Token speakers
Feature activation+2.329
and
Token and
Feature activation+0.499
I
Token I
Feature activation+1.244
had
Token had
Feature activation+0.434
to
Token to
Feature activation+0.328
use
Token use
Feature activation+0.478
it
Token it
Feature activation+3.005
in
Token in
Feature activation+0.413
any
Token any
Feature activation+0.000
constructive
Token constructive
Feature activation+0.000
way
Token way
Feature activation+3.069
,
Token,
Feature activation+2.478
instead
Token instead
Feature activation+0.815
fe
Token fe
Feature activation+0.000
eb
Tokeneb
Feature activation+0.012
ly
Tokenly
Feature activation+0.544
adding
Token adding
Feature activation+0.205
its
Token its
Feature activation+0.000
exports
Token exports
Feature activation+3.309
beyond
Token beyond
Feature activation+0.129
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+2.394
,
Token,
Feature activation+2.556
largely
Token largely
Feature activation+1.461
under
Token under
Feature activation+0.000
such
Token such
Feature activation+0.000
rules
Token rules
Feature activation+3.394
?
Token?
Feature activation+0.296

INTERVAL 1.710 - 2.280
CONTAINS 0.061%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
I
Token I
Feature activation+0.354
get
Token get
Feature activation+0.124
stack
Token stack
Feature activation+0.000
traces
Token traces
Feature activation+2.179
?
Token?
Feature activation+0.123
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.256
presentation
Token presentation
Feature activation+0.654
).
Token).
Feature activation+0.000
who
Token who
Feature activation+0.000
cares
Token cares
Feature activation+0.720
about
Token about
Feature activation+0.000
fruit
Token fruit
Feature activation+0.104
fly
Token fly
Feature activation+0.305
sex
Token sex
Feature activation+2.059
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.773
t
Tokent
Feature activation+0.465
even
Token even
Feature activation+0.000
voted
Token voted
Feature activation+2.167
yet
Token yet
Feature activation+2.842
?
Token?
Feature activation+0.305
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
stand
Token stand
Feature activation+0.000
on
Token on
Feature activation+0.000
principle
Token principle
Feature activation+1.231
top
Token top
Feature activation+0.411
Republican
Token Republican
Feature activation+0.296
lawmakers
Token lawmakers
Feature activation+1.792
always
Token always
Feature activation+0.297
fold
Token fold
Feature activation+0.721
like
Token like
Feature activation+0.000
a
Token a
Feature activation+0.000
20
Token 20
Feature activation+0.000
what
Token what
Feature activation+0.012
do
Token do
Feature activation+0.000
they
Token they
Feature activation+0.785
expect
Token expect
Feature activation+1.520
to
Token to
Feature activation+0.000
find
Token find
Feature activation+1.980
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Content
TokenContent
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 1.140 - 1.710
CONTAINS 0.077%

Of
TokenOf
Feature activation+0.000
the
Token the
Feature activation+0.000
information
Token information
Feature activation+0.619
concerning
Token concerning
Feature activation+0.000
the
Token the
Feature activation+0.000
deaths
Token deaths
Feature activation+1.348
of
Token of
Feature activation+0.000
four
Token four
Feature activation+0.544
brave
Token brave
Feature activation+0.000
Americans
Token Americans
Feature activation+1.549
.
Token.
Feature activation+0.250
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
about
Token about
Feature activation+0.000
people
Token people
Feature activation+1.327
on
Token on
Feature activation+0.000
group
Token group
Feature activation+0.000
water
Token water
Feature activation+0.864
schemes
Token schemes
Feature activation+2.970
?
Token?
Feature activation+0.527
them
Token them
Feature activation+2.591
?
Token?
Feature activation+0.002
And
Token And
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.067
care
Token care
Feature activation+1.458
enough
Token enough
Feature activation+1.808
to
Token to
Feature activation+0.000
preserve
Token preserve
Feature activation+0.303
them
Token them
Feature activation+3.635
here
Token here
Feature activation+3.921
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
among
Token among
Feature activation+0.000
verte
Token verte
Feature activation+0.000
brates
Tokenbrates
Feature activation+2.011
,
Token,
Feature activation+1.673
can
Token can
Feature activation+0.000
fish
Token fish
Feature activation+1.677
,
Token,
Feature activation+0.146
reptiles
Token reptiles
Feature activation+0.867
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
billion
Token billion
Feature activation+0.000
dollars
Token dollars
Feature activation+0.743
required
Token required
Feature activation+1.508
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.159
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000

INTERVAL 0.570 - 1.140
CONTAINS 0.165%

ever
Token ever
Feature activation+0.000
stopped
Token stopped
Feature activation+0.357
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
beat
Token beat
Feature activation+2.332
and
Token and
Feature activation+0.896
wondered
Token wondered
Feature activation+0.630
what
Token what
Feature activation+0.198
if
Token if
Feature activation+1.018
these
Token these
Feature activation+0.719
crucial
Token crucial
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.379
after
Token after
Feature activation+0.000
that
Token that
Feature activation+0.677
?
Token?
Feature activation+0.274
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
za
Tokenza
Feature activation+0.000
a
Token a
Feature activation+0.000
crack
Token crack
Feature activation+0.216
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Cyber
Token Cyber
Feature activation+0.000
men
Tokenmen
Feature activation+0.870
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Chris
TokenChris
Feature activation+0.000
did
Token did
Feature activation+0.000
a
Token a
Feature activation+0.000
beat
Token beat
Feature activation+2.332
and
Token and
Feature activation+0.896
wondered
Token wondered
Feature activation+0.630
what
Token what
Feature activation+0.198
if
Token if
Feature activation+1.018
these
Token these
Feature activation+0.719
crucial
Token crucial
Feature activation+0.000
data
Token data
Feature activation+2.814
were
Token were
Feature activation+0.747
easily
Token easily
Feature activation+0.114
,
Token,
Feature activation+1.327
opposed
Token opposed
Feature activation+0.417
by
Token by
Feature activation+0.360
many
Token many
Feature activation+2.202
voters
Token voters
Feature activation+2.810
?
Token?
Feature activation+0.976
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Politico
Token Politico
Feature activation+0.000

INTERVAL 0.000 - 0.570
CONTAINS 99.593%

to
Token to
Feature activation+0.000
experience
Token experience
Feature activation+0.000
severe
Token severe
Feature activation+0.000
pain
Token pain
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
vomit
Token vomit
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
sheriff
Token sheriff
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
incumbent
Token incumbent
Feature activation+0.000
land
Token land
Feature activation+0.000
owners
Token owners
Feature activation+0.000
gain
Token gain
Feature activation+0.390
or
Token or
Feature activation+0.062
lose
Token lose
Feature activation+1.242
?
Token?
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
family
Token family
Feature activation+0.000
in
Token in
Feature activation+0.000
Kenya
Token Kenya
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
received
Token received
Feature activation+0.000
some
Token some
Feature activation+0.000
're
Token're
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
into
Token into
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
figure
Token figure
Feature activation+0.000
it
Token it
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
art
Token art
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
or
Token or
Feature activation+0.000
coy
Token coy
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
music
Token music
Feature activation+0.000
:
Token:
Feature activation+0.000
If
Token If
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 H10.5: (feature 15210)

TOP ACTIVATIONS
MAX = 5.895

and
Token and
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
perpetuate
Token perpetuate
Feature activation+0.453
the
Token the
Feature activation+0.000
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
for
Token for
Feature activation+0.300
many
Token many
Feature activation+0.131
years
Token years
Feature activation+1.233
afterward
Token afterward
Feature activation+2.323
,
Token,
Feature activation+1.266
to
Token to
Feature activation+0.000
perpetuate
Token perpetuate
Feature activation+0.453
the
Token the
Feature activation+0.000
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
for
Token for
Feature activation+0.300
many
Token many
Feature activation+0.131
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
him
Token him
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
that
Token that
Feature activation+1.242
hobby
Token hobby
Feature activation+4.257
during
Token during
Feature activation+0.000
his
Token his
Feature activation+0.000
service
Token service
Feature activation+0.518
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
The
TokenThe
Feature activation+0.000
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+4.161
kissing
Token kissing
Feature activation+3.540
each
Token each
Feature activation+0.000
other
Token other
Feature activation+4.097
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+3.081
1950
Token 1950
Feature activation+0.000
that
Token that
Feature activation+0.000
remained
Token remained
Feature activation+0.000
on
Token on
Feature activation+0.396
the
Token the
Feature activation+0.000
books
Token books
Feature activation+4.110
even
Token even
Feature activation+1.001
though
Token though
Feature activation+0.000
they
Token they
Feature activation+0.000
violated
Token violated
Feature activation+0.000
state
Token state
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
siege
Token siege
Feature activation+0.668
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
strip
Token strip
Feature activation+4.110
,
Token,
Feature activation+0.693
while
Token while
Feature activation+0.000
indiscrim
Token indiscrim
Feature activation+0.000
inately
Tokeninately
Feature activation+0.000
harassing
Token harassing
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+4.161
kissing
Token kissing
Feature activation+3.540
each
Token each
Feature activation+0.000
other
Token other
Feature activation+4.097
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+3.081
and
Token and
Feature activation+0.000
hugging
Token hugging
Feature activation+1.788
,
Token,
Feature activation+1.772
rules
Token rules
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
stays
Token stays
Feature activation+0.000
frozen
Token frozen
Feature activation+1.888
in
Token in
Feature activation+0.000
place
Token place
Feature activation+4.065
for
Token for
Feature activation+0.048
now
Token now
Feature activation+2.235
.
Token.
Feature activation+0.100
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
schemes
Token schemes
Feature activation+0.000
would
Token would
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
so
Token so
Feature activation+4.061
.
Token.
Feature activation+0.000
Commercial
Token Commercial
Feature activation+0.000
water
Token water
Feature activation+0.000
customers
Token customers
Feature activation+0.000
would
Token would
Feature activation+0.000
retail
Token retail
Feature activation+0.000
sites
Token sites
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
operate
Token operate
Feature activation+2.423
separately
Token separately
Feature activation+3.981
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Tokena
Feature activation+0.000
role
Token role
Feature activation+0.000
she
Token she
Feature activation+0.000
continued
Token continued
Feature activation+1.584
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+3.827
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
first
Token first
Feature activation+0.000
registered
Token registered
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.458
his
Token his
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
abilities
Token abilities
Feature activation+3.716
at
Token at
Feature activation+0.316
each
Token each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
Grand
Token Grand
Feature activation+0.000
had
Token had
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.471
u
Token u
Feature activation+0.000
u
Tokenu
Feature activation+3.638
,
Token,
Feature activation+1.193
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
usage
Token usage
Feature activation+0.000
returned
Token returned
Feature activation+0.225
his
Token his
Feature activation+0.000
Upper
Token Upper
Feature activation+0.000
East
Token East
Feature activation+0.000
Side
Token Side
Feature activation+0.000
town
Token town
Feature activation+0.000
house
Token house
Feature activation+3.629
despite
Token despite
Feature activation+0.000
its
Token its
Feature activation+0.000
recent
Token recent
Feature activation+0.000
drop
Token drop
Feature activation+0.000
from
Token from
Feature activation+0.000
they
Token they
Feature activation+0.000
persisted
Token persisted
Feature activation+0.128
in
Token in
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
the
Token the
Feature activation+0.000
tradition
Token tradition
Feature activation+3.621
until
Token until
Feature activation+0.000
the
Token the
Feature activation+0.000
queen
Token queen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
stick
Token stick
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.236
story
Token story
Feature activation+3.591
.
Token.
Feature activation+0.000
Actually
Token Actually
Feature activation+0.000
,
Token,
Feature activation+0.000
elements
Token elements
Feature activation+0.000
of
Token of
Feature activation+0.000
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+4.161
kissing
Token kissing
Feature activation+3.540
each
Token each
Feature activation+0.000
other
Token other
Feature activation+4.097
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+3.081
and
Token and
Feature activation+0.000
vol
Tokenvol
Feature activation+0.000
va
Tokenva
Feature activation+2.375
and
Token and
Feature activation+0.000
Priv
Token Priv
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
va
Tokenva
Feature activation+3.511
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
details
Token details
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.000
an
Token an
Feature activation+0.000
active
Token active
Feature activation+0.000
band
Token band
Feature activation+3.462
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
being
Token being
Feature activation+1.830
.
Token.
Feature activation+0.166

Top DFA by src position
MAX = 4.827

much
Token much
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
2011
Token 2011
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
continued
Token continued
Feature activation+4.827
Top resid features:
to
Token to
Feature activation+1.099
Top resid features:
perpetuate
Token perpetuate
Feature activation+0.456
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
movement
Token movement
Feature activation+0.086
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
2011
Token 2011
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
continued
Token continued
Feature activation+3.752
Top resid features:
to
Token to
Feature activation+1.522
Top resid features:
perpetuate
Token perpetuate
Feature activation+0.490
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
movement
Token movement
Feature activation+0.122
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
much
Token much
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
2011
Token 2011
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
continued
Token continued
Feature activation+2.959
Top resid features:
to
Token to
Feature activation+0.651
Top resid features:
perpetuate
Token perpetuate
Feature activation+0.782
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
movement
Token movement
Feature activation+0.377
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
result
Token result
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
him
Token him
Feature activation+0.071
Top resid features:
continuing
Token continuing
Feature activation+4.382
Top resid features:
that
Token that
Feature activation+0.258
Top resid features:
hobby
Token hobby
Feature activation+0.082
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
service
Token service
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
The
TokenThe
Feature activation-0.004
Top resid features:
couple
Token couple
Feature activation-0.021
Top resid features:
remained
Token remained
Feature activation+4.314
Top resid features:
at
Token at
Feature activation+0.286
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
bar
Token bar
Feature activation+0.010
Top resid features:
kissing
Token kissing
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
ordinances
Token ordinances
Feature activation+0.008
Top resid features:
dating
Token dating
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.006
Top resid features:
1950
Token 1950
Feature activation-0.013
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
remained
Token remained
Feature activation+4.347
Top resid features:
on
Token on
Feature activation+0.298
Top resid features:
the
Token the
Feature activation+0.072
Top resid features:
books
Token books
Feature activation+0.100
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.002
Top resid features:
practice
Token practice
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
Israel
Token Israel
Feature activation-0.005
Top resid features:
has
Token has
Feature activation+0.037
Top resid features:
continued
Token continued
Feature activation+4.239
Top resid features:
its
Token its
Feature activation+0.100
Top resid features:
illegal
Token illegal
Feature activation+0.053
Top resid features:
siege
Token siege
Feature activation+0.306
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
couple
Token couple
Feature activation-0.017
Top resid features:
remained
Token remained
Feature activation+4.348
Top resid features:
at
Token at
Feature activation+0.069
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
bar
Token bar
Feature activation+0.053
Top resid features:
kissing
Token kissing
Feature activation+0.142
Top resid features:
each
Token each
Feature activation+0.024
Top resid features:
certain
Token certain
Feature activation+0.003
Top resid features:
set
Token set
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
rules
Token rules
Feature activation-0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.169
Top resid features:
stays
Token stays
Feature activation+3.364
Top resid features:
frozen
Token frozen
Feature activation+1.041
Top resid features:
in
Token in
Feature activation+0.199
Top resid features:
place
Token place
Feature activation+0.231
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.007
Top resid features:
on
Token on
Feature activation+0.021
Top resid features:
these
Token these
Feature activation+0.004
Top resid features:
schemes
Token schemes
Feature activation-0.005
Top resid features:
would
Token would
Feature activation-0.007
Top resid features:
continue
Token continue
Feature activation+3.689
Top resid features:
to
Token to
Feature activation+0.531
Top resid features:
do
Token do
Feature activation+0.168
Top resid features:
so
Token so
Feature activation+0.135
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Commercial
Token Commercial
Feature activation+0.000
Top resid features:
although
Token although
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
two
Token two
Feature activation-0.005
Top resid features:
retail
Token retail
Feature activation+0.002
Top resid features:
sites
Token sites
Feature activation-0.000
Top resid features:
continued
Token continued
Feature activation+3.649
Top resid features:
to
Token to
Feature activation+0.688
Top resid features:
operate
Token operate
Feature activation+0.447
Top resid features:
separately
Token separately
Feature activation+0.070
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
1935
Token 1935
Feature activation-0.050
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.097
Top resid features:
a
Tokena
Feature activation-0.000
Top resid features:
role
Token role
Feature activation-0.002
Top resid features:
she
Token she
Feature activation+0.048
Top resid features:
continued
Token continued
Feature activation+3.298
Top resid features:
to
Token to
Feature activation+0.919
Top resid features:
serve
Token serve
Feature activation+0.236
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
great
Token great
Feature activation+0.005
Top resid features:
driver
Token driver
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
he
Token he
Feature activation+0.018
Top resid features:
continues
Token continues
Feature activation+2.576
Top resid features:
to
Token to
Feature activation+1.009
Top resid features:
show
Token show
Feature activation+0.388
Top resid features:
his
Token his
Feature activation+0.054
Top resid features:
extraordinary
Token extraordinary
Feature activation+0.034
Top resid features:
abilities
Token abilities
Feature activation+0.039
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
European
Token European
Feature activation+0.003
Top resid features:
sc
Token sc
Feature activation+0.001
Top resid features:
ribes
Tokenribes
Feature activation-0.000
Top resid features:
had
Token had
Feature activation-0.071
Top resid features:
continued
Token continued
Feature activation+3.408
Top resid features:
to
Token to
Feature activation+0.675
Top resid features:
write
Token write
Feature activation+0.223
Top resid features:
u
Token u
Feature activation+0.030
Top resid features:
u
Tokenu
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.010
Top resid features:
he
Token he
Feature activation-0.008
Top resid features:
said
Token said
Feature activation-0.002
Top resid features:
he
Token he
Feature activation-0.004
Top resid features:
had
Token had
Feature activation-0.141
Top resid features:
continued
Token continued
Feature activation+4.173
Top resid features:
patron
Token patron
Feature activation+0.008
Top resid features:
izing
Tokenizing
Feature activation+0.126
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
coffee
Token coffee
Feature activation-0.003
Top resid features:
shop
Token shop
Feature activation+0.125
Top resid features:
Albert
Token Albert
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
they
Token they
Feature activation+0.008
Top resid features:
persisted
Token persisted
Feature activation+0.911
Top resid features:
in
Token in
Feature activation+0.945
Top resid features:
continuing
Token continuing
Feature activation+1.692
Top resid features:
the
Token the
Feature activation+0.214
Top resid features:
tradition
Token tradition
Feature activation+0.341
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
queen
Token queen
Feature activation+0.000
Top resid features:
operation
Token operation
Feature activation+0.000
Top resid features:
surprised
Token surprised
Feature activation+0.002
Top resid features:
them
Token them
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.074
Top resid features:
Many
Token Many
Feature activation+0.006
Top resid features:
continue
Token continue
Feature activation+2.500
Top resid features:
to
Token to
Feature activation+0.919
Top resid features:
stick
Token stick
Feature activation+0.468
Top resid features:
to
Token to
Feature activation+0.122
Top resid features:
that
Token that
Feature activation+0.094
Top resid features:
story
Token story
Feature activation+0.080
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
couple
Token couple
Feature activation-0.023
Top resid features:
remained
Token remained
Feature activation+3.729
Top resid features:
at
Token at
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.039
Top resid features:
bar
Token bar
Feature activation+0.070
Top resid features:
kissing
Token kissing
Feature activation+0.109
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
daemon
Token daemon
Feature activation+0.006
Top resid features:
continues
Token continues
Feature activation+3.757
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
descriptions
Token descriptions
Feature activation+0.373
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Sub
Token Sub
Feature activation+0.004
Top resid features:
vol
Tokenvol
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.089
Top resid features:
Canadian
Token Canadian
Feature activation+0.003
Top resid features:
tour
Token tour
Feature activation-0.023
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
will
Token will
Feature activation-0.025
Top resid features:
remain
Token remain
Feature activation+3.577
Top resid features:
an
Token an
Feature activation+0.262
Top resid features:
active
Token active
Feature activation+0.168
Top resid features:
band
Token band
Feature activation+0.111
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.04

Head 4: 0.04

Head 5: 0.62

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.10

Head 10: 0.01

Head 11: 0.04

Positive logits

until5.73

despite5.62

till5.23

until5.00

indefinitely4.96

despite4.86

even4.39

notwithstanding4.37

throughout4.31

regardless4.25

unchanged4.07

unab3.90

withstanding3.90

irrespective3.88

while3.67

intact3.50

uninterrupted3.49

unless3.36

remains3.33

even3.33

Negative logits

yip-3.73

utenant-3.07

��-2.76

suddenly-2.74

rupture-2.64

azo-2.64

ワン-2.61

romancer-2.60

THEN-2.56

urgently-2.46

quickShipAvailable-2.45

panic-2.40

collided-2.38

furt-2.37

bringer-2.37

found-2.36

leigh-2.36

announced-2.35

eco-2.35

Thumbnail-2.35

INTERVAL 5.306 - 5.895
CONTAINS 0.000%

and
Token and
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
perpetuate
Token perpetuate
Feature activation+0.453
the
Token the
Feature activation+0.000
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
for
Token for
Feature activation+0.300
many
Token many
Feature activation+0.131
years
Token years
Feature activation+1.233
afterward
Token afterward
Feature activation+2.323
,
Token,
Feature activation+1.266

INTERVAL 4.716 - 5.306
CONTAINS 0.000%

INTERVAL 4.127 - 4.716
CONTAINS 0.000%

The
TokenThe
Feature activation+0.000
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+4.161
kissing
Token kissing
Feature activation+3.540
each
Token each
Feature activation+0.000
other
Token other
Feature activation+4.097
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+3.081
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
him
Token him
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
that
Token that
Feature activation+1.242
hobby
Token hobby
Feature activation+4.257
during
Token during
Feature activation+0.000
his
Token his
Feature activation+0.000
service
Token service
Feature activation+0.518
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
to
Token to
Feature activation+0.000
perpetuate
Token perpetuate
Feature activation+0.453
the
Token the
Feature activation+0.000
movement
Token movement
Feature activation+5.895
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.270
s
Tokens
Feature activation+0.398
debunked
Token debunked
Feature activation+0.039
nonsense
Token nonsense
Feature activation+5.512
for
Token for
Feature activation+0.300
many
Token many
Feature activation+0.131

INTERVAL 3.537 - 4.127
CONTAINS 0.001%

couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+4.161
kissing
Token kissing
Feature activation+3.540
each
Token each
Feature activation+0.000
other
Token other
Feature activation+4.097
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+3.081
and
Token and
Feature activation+0.000
a
Tokena
Feature activation+0.000
role
Token role
Feature activation+0.000
she
Token she
Feature activation+0.000
continued
Token continued
Feature activation+1.584
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+3.827
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
first
Token first
Feature activation+0.000
registered
Token registered
Feature activation+0.000
schemes
Token schemes
Feature activation+0.000
would
Token would
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
so
Token so
Feature activation+4.061
.
Token.
Feature activation+0.000
Commercial
Token Commercial
Feature activation+0.000
water
Token water
Feature activation+0.000
customers
Token customers
Feature activation+0.000
would
Token would
Feature activation+0.000
had
Token had
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.471
u
Token u
Feature activation+0.000
u
Tokenu
Feature activation+3.638
,
Token,
Feature activation+1.193
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
usage
Token usage
Feature activation+0.000
returned
Token returned
Feature activation+0.225
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.458
his
Token his
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
abilities
Token abilities
Feature activation+3.716
at
Token at
Feature activation+0.316
each
Token each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
Grand
Token Grand
Feature activation+0.000

INTERVAL 2.948 - 3.537
CONTAINS 0.003%

the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
shrink
Token shrink
Feature activation+3.222
next
Token next
Feature activation+0.000
year
Token year
Feature activation+1.460
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.052
report
Token report
Feature activation+0.490
on
Token on
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+1.182
and
Token and
Feature activation+0.000
blockchain
Token blockchain
Feature activation+1.136
regulation
Token regulation
Feature activation+3.129
as
Token as
Feature activation+0.000
information
Token information
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
available
Token available
Feature activation+0.233
.
Token.
Feature activation+0.000
guys
Token guys
Feature activation+0.000
he
Token he
Feature activation+0.000
remained
Token remained
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
motion
Token motion
Feature activation+0.000
less
Tokenless
Feature activation+3.428
and
Token and
Feature activation+0.000
spoke
Token spoke
Feature activation+0.276
in
Token in
Feature activation+0.000
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
s
Tokens
Feature activation+2.183
and
Token and
Feature activation+0.000
1960
Token 1960
Feature activation+0.000
s
Tokens
Feature activation+3.112
.
Token.
Feature activation+0.000
Economic
Token Economic
Feature activation+0.000
historians
Token historians
Feature activation+0.000
Claudia
Token Claudia
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.057
do
Token do
Feature activation+0.487
so
Token so
Feature activation+3.012
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
lost
Token lost
Feature activation+0.000

INTERVAL 2.358 - 2.948
CONTAINS 0.007%

say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.003
safe
Token safe
Feature activation+2.418
from
Token from
Feature activation+0.000
Iran
Token Iran
Feature activation+1.359
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
ambitions
Token ambitions
Feature activation+2.438
and
Token and
Feature activation+0.000
Missouri
Token Missouri
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.506
sightings
Token sightings
Feature activation+2.548
increase
Token increase
Feature activation+0.933
in
Token in
Feature activation+0.000
frequency
Token frequency
Feature activation+2.444
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fire
Token fire
Feature activation+2.377
the
Token the
Feature activation+0.000
Target
Token Target
Feature activation+1.279
Loc
Token Loc
Feature activation+0.000
ator
Tokenator
Feature activation+2.817
and
Token and
Feature activation+0.000
continued
Token continued
Feature activation+0.000
to
Token to
Feature activation+0.000
selectively
Token selectively
Feature activation+0.000
dictate
Token dictate
Feature activation+0.108
government
Token government
Feature activation+1.532
policies
Token policies
Feature activation+2.726
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
instance
Token instance
Feature activation+0.000
King
Token King
Feature activation+0.000
George
Token George
Feature activation+0.000
The
Token The
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
creep
Token creep
Feature activation+0.254
along
Token along
Feature activation+2.720
on
Token on
Feature activation+0.022
campuses
Token campuses
Feature activation+2.744
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
marginalized
Token marginalized
Feature activation+0.000

INTERVAL 1.769 - 2.358
CONTAINS 0.014%

the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
statements
Token statements
Feature activation+0.000
remain
Token remain
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
accurate
Token accurate
Feature activation+1.871
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Pat
TokenPat
Feature activation+0.000
stay
Token stay
Feature activation+0.000
up
Token up
Feature activation+0.512
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
date
Tokendate
Feature activation+2.194
and
Token and
Feature activation+0.000
reflect
Token reflect
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
law
Token law
Feature activation+0.103
the
Token the
Feature activation+0.000
Conc
Token Conc
Feature activation+0.000
orde
Tokenorde
Feature activation+0.000
continued
Token continued
Feature activation+0.014
to
Token to
Feature activation+0.000
fly
Token fly
Feature activation+2.313
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
years
Token years
Feature activation+1.467
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
it
Token it
Feature activation+0.435
stay
Token stay
Feature activation+0.000
confidential
Token confidential
Feature activation+1.819
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
various
Token various
Feature activation+0.000
partners
Token partners
Feature activation+1.565
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
poor
Token poor
Feature activation+0.943
in
Token in
Feature activation+0.000
place
Token place
Feature activation+1.965
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
have
Token have
Feature activation+0.000
blocked
Token blocked
Feature activation+0.000

INTERVAL 1.179 - 1.769
CONTAINS 0.029%

not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+1.377
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
firm
Token firm
Feature activation+1.228
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
kept
Token kept
Feature activation+0.000
things
Token things
Feature activation+0.000
quiet
Token quiet
Feature activation+1.715
until
Token until
Feature activation+0.000
that
Token that
Feature activation+0.000
interview
Token interview
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
exhibit
Token exhibit
Feature activation+0.325
enormous
Token enormous
Feature activation+0.000
love
Token love
Feature activation+1.263
,
Token,
Feature activation+0.237
resilience
Token resilience
Feature activation+0.000
and
Token and
Feature activation+0.000
optimism
Token optimism
Feature activation+2.050
in
Token in
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
stop
Token stop
Feature activation+0.000
developing
Token developing
Feature activation+0.244
the
Token the
Feature activation+0.000
game
Token game
Feature activation+1.538
or
Token or
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
new
Token new
Feature activation+0.000
features
Token features
Feature activation+0.724
in
Token in
Feature activation+0.695
Rox
Token Rox
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
Street
Token Street
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.000
open
Token open
Feature activation+1.666
and
Token and
Feature activation+0.000
access
Token access
Feature activation+0.351
provided
Token provided
Feature activation+1.407
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 0.590 - 1.179
CONTAINS 0.091%

scrutiny
Token scrutiny
Feature activation+0.352
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
lives
Token lives
Feature activation+0.000
of
Token of
Feature activation+0.000
ants
Token ants
Feature activation+0.798
provides
Token provides
Feature activation+0.000
insights
Token insights
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
web
Token web
Feature activation+0.000
H
Token H
Feature activation+0.000
wang
Tokenwang
Feature activation+0.000
K
Token K
Feature activation+0.000
yo
Tokenyo
Feature activation+0.000
-
Token-
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.619
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
with
Token with
Feature activation+0.000
whoever
Token whoever
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
protesting
Token protesting
Feature activation+1.916
this
Token this
Feature activation+0.000
coming
Token coming
Feature activation+0.000
weekend
Token weekend
Feature activation+0.829
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
stood
Token stood
Feature activation+0.000
in
Token in
Feature activation+0.000
solidarity
Token solidarity
Feature activation+0.075
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
still
Token still
Feature activation+0.000
help
Token help
Feature activation+0.084
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.716
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
get
Token get
Feature activation+0.000
caught
Token caught
Feature activation+0.000
face
Token face
Feature activation+0.000
have
Token have
Feature activation+0.000
continued
Token continued
Feature activation+1.550
to
Token to
Feature activation+0.000
claim
Token claim
Feature activation+0.044
lives
Token lives
Feature activation+2.504
,
Token,
Feature activation+1.049
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.096
Ban
Token Ban
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.000 - 0.590
CONTAINS 99.856%

O
TokenO
Feature activation+0.000
tto
Tokentto
Feature activation+0.000
also
Token also
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Parker
Token Parker
Feature activation+0.000
's
Token's
Feature activation+0.000
lot
Token lot
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
Thank
TokenThank
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
little
Token little
Feature activation+0.000
s
Token s
Feature activation+0.000
is
Tokenis
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
.
Token.
Feature activation+0.000
centre
Token centre
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
of
Token of
Feature activation+0.000
Science
Token Science
Feature activation+0.000
,
Token,
Feature activation+0.000
Technology
Token Technology
Feature activation+0.000
and
Token and
Feature activation+0.000
Industry
Token Industry
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
horny
Token horny
Feature activation+0.000
person
Token person
Feature activation+0.000
dressed
Token dressed
Feature activation+0.000
up
Token up
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
grape
Token grape
Feature activation+0.000
pin
Token pin
Feature activation+0.000
ched
Tokenched
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 H10.5: (feature 4925)

TOP ACTIVATIONS
MAX = 6.529

Ļ
TokenĻ
Feature activation+4.789
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Fighting
Token Fighting
Feature activation+0.000
Group
Token Group
Feature activation+6.529
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
IF
TokenIF
Feature activation+0.000
G
TokenG
Feature activation+0.000
)
Token)
Feature activation+6.412
Group
Token Group
Feature activation+6.529
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
IF
TokenIF
Feature activation+0.000
G
TokenG
Feature activation+0.000
)
Token)
Feature activation+6.412
have
Token have
Feature activation+1.096
armed
Token armed
Feature activation+0.000
sectarian
Token sectarian
Feature activation+0.000
extremists
Token extremists
Feature activation+0.298
across
Token across
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
orks
Tokenorks
Feature activation+6.148
have
Token have
Feature activation+1.252
taken
Token taken
Feature activation+0.037
just
Token just
Feature activation+0.000
4
Token 4
Feature activation+0.000
points
Token points
Feature activation+0.047
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fract
Token fract
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+5.891
have
Token have
Feature activation+0.966
so
Token so
Feature activation+0.113
many
Token many
Feature activation+0.162
nations
Token nations
Feature activation+1.960
lined
Token lined
Feature activation+0.161
here
Token here
Feature activation+1.353
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Brew
Token Brew
Feature activation+0.029
Review
Token Review
Feature activation+5.130
Crew
Token Crew
Feature activation+5.692
have
Token have
Feature activation+0.622
been
Token been
Feature activation+0.067
spreading
Token spreading
Feature activation+0.000
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
Bell
Token Bell
Feature activation+0.769
Labs
Token Labs
Feature activation+5.521
was
Token was
Feature activation+0.339
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.150
where
Token where
Feature activation+0.000
such
Token such
Feature activation+0.000
"
Token"
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
Great
Token Great
Feature activation+0.000
Depression
Token Depression
Feature activation+5.399
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.102
seen
Token seen
Feature activation+1.362
an
Token an
Feature activation+0.000
economic
Token economic
Feature activation+0.000
we
Token we
Feature activation+2.339
here
Token here
Feature activation+1.353
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Brew
Token Brew
Feature activation+0.029
Review
Token Review
Feature activation+5.130
Crew
Token Crew
Feature activation+5.692
have
Token have
Feature activation+0.622
been
Token been
Feature activation+0.067
spreading
Token spreading
Feature activation+0.000
the
Token the
Feature activation+0.000
led
Token led
Feature activation+0.167
by
Token by
Feature activation+0.000
commanders
Token commanders
Feature activation+1.178
of
Token of
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+4.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.789
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+2.192
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
allies
Token allies
Feature activation+4.964
have
Token have
Feature activation+1.275
built
Token built
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
and
Token and
Feature activation+0.000
commanders
Token commanders
Feature activation+1.178
of
Token of
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+4.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.789
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Fighting
Token Fighting
Feature activation+0.000
Group
Token Group
Feature activation+6.529
like
Token like
Feature activation+0.000
Kickstarter
Token Kickstarter
Feature activation+4.274
and
Token and
Feature activation+0.000
Ind
Token Ind
Feature activation+0.000
ieg
Tokenieg
Feature activation+0.000
ogo
Tokenogo
Feature activation+4.716
have
Token have
Feature activation+0.686
revolution
Token revolution
Feature activation+0.190
ized
Tokenized
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
,
Token,
Feature activation+0.000
mental
Token mental
Feature activation+0.000
health
Token health
Feature activation+0.681
professionals
Token professionals
Feature activation+4.660
were
Token were
Feature activation+0.661
taught
Token taught
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
,
Token,
Feature activation+0.000
relations
Token relations
Feature activation+1.806
between
Token between
Feature activation+0.000
Tokyo
Token Tokyo
Feature activation+0.402
and
Token and
Feature activation+0.000
Seoul
Token Seoul
Feature activation+4.618
have
Token have
Feature activation+0.532
been
Token been
Feature activation+0.614
m
Token m
Feature activation+0.000
ired
Tokenired
Feature activation+0.566
in
Token in
Feature activation+0.000
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.509
,
Token,
Feature activation+0.461
the
Token the
Feature activation+0.000
damn
Token damn
Feature activation+0.012
thing
Token thing
Feature activation+4.582
was
Token was
Feature activation+0.828
breaking
Token breaking
Feature activation+0.002
and
Token and
Feature activation+0.176
facing
Token facing
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
Over
TokenOver
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
many
Token many
Feature activation+0.370
Americans
Token Americans
Feature activation+4.542
have
Token have
Feature activation+1.330
likely
Token likely
Feature activation+1.631
heard
Token heard
Feature activation+0.225
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
while
Token while
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.249
the
Token the
Feature activation+0.000
Ruby
Token Ruby
Feature activation+0.000
community
Token community
Feature activation+4.516
has
Token has
Feature activation+2.483
become
Token become
Feature activation+0.402
en
Token en
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ored
Tokenored
Feature activation+0.231
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+0.009
and
Token and
Feature activation+0.000
libertarian
Token libertarian
Feature activation+0.000
movement
Token movement
Feature activation+4.490
has
Token has
Feature activation+1.213
grown
Token grown
Feature activation+0.041
exponentially
Token exponentially
Feature activation+0.501
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
s
Tokens
Feature activation+0.367
very
Token very
Feature activation+0.000
influential
Token influential
Feature activation+0.000
members
Token members
Feature activation+4.027
in
Token in
Feature activation+0.000
government
Token government
Feature activation+4.418
,
Token,
Feature activation+0.934
the
Token the
Feature activation+0.000
media
Token media
Feature activation+1.165
,
Token,
Feature activation+0.607
and
Token and
Feature activation+0.025
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+0.162
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
CFR
Token CFR
Feature activation+4.416
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.400
s
Tokens
Feature activation+0.367
very
Token very
Feature activation+0.000
influential
Token influential
Feature activation+0.000

Top DFA by src position
MAX = 5.914

North
Token North
Feature activation+0.000
Top resid features:
African
Token African
Feature activation+0.000
Top resid features:
nation
Token nation
Feature activation-0.000
Top resid features:
.
Token .
Feature activation+0.032
Top resid features:
Since
Token Since
Feature activation+0.691
Top resid features:
then
Token then
Feature activation+3.182
Top resid features:
,
Token,
Feature activation+2.424
Top resid features:
Libya
Token Libya
Feature activation+0.186
Top resid features:
âĢ
TokenâĢ
Feature activation+0.062
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
African
Token African
Feature activation+0.001
Top resid features:
nation
Token nation
Feature activation-0.002
Top resid features:
.
Token .
Feature activation+0.030
Top resid features:
Since
Token Since
Feature activation+0.976
Top resid features:
then
Token then
Feature activation+3.036
Top resid features:
,
Token,
Feature activation+2.034
Top resid features:
Libya
Token Libya
Feature activation+0.166
Top resid features:
âĢ
TokenâĢ
Feature activation+0.048
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
San
Token San
Feature activation+0.001
Top resid features:
Jose
Token Jose
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Since
Token Since
Feature activation+1.046
Top resid features:
that
Token that
Feature activation+0.129
Top resid features:
time
Token time
Feature activation+2.668
Top resid features:
,
Token,
Feature activation+2.238
Top resid features:
the
Token the
Feature activation+0.467
Top resid features:
Sp
Token Sp
Feature activation+0.007
Top resid features:
orks
Tokenorks
Feature activation+0.028
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation-0.010
Top resid features:
rarely
Token rarely
Feature activation+0.170
Top resid features:
in
Token in
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
recent
Token recent
Feature activation+0.097
Top resid features:
history
Token history
Feature activation+5.860
Top resid features:
of
Token of
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
fract
Token fract
Feature activation-0.010
Top resid features:
ious
Tokenious
Feature activation+0.005
Top resid features:
Middle
Token Middle
Feature activation+0.004
Top resid features:
website
Token website
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.037
Top resid features:
Over
TokenOver
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.068
Top resid features:
year
Token year
Feature activation+4.574
Top resid features:
,
Token,
Feature activation+1.120
Top resid features:
we
Token we
Feature activation+0.225
Top resid features:
here
Token here
Feature activation+0.090
Top resid features:
at
Token at
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
."
Token."
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
In
TokenIn
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
past
Token past
Feature activation+5.914
Top resid features:
Bell
Token Bell
Feature activation+0.007
Top resid features:
Labs
Token Labs
Feature activation+0.066
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
"
Token"
Feature activation-0.021
Top resid features:
Not
TokenNot
Feature activation+0.004
Top resid features:
since
Token since
Feature activation+5.846
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Great
Token Great
Feature activation+0.000
Top resid features:
Depression
Token Depression
Feature activation+0.068
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
website
Token website
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.014
Top resid features:
Over
TokenOver
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
past
Token past
Feature activation+0.027
Top resid features:
year
Token year
Feature activation+4.127
Top resid features:
,
Token,
Feature activation+1.190
Top resid features:
we
Token we
Feature activation+0.149
Top resid features:
here
Token here
Feature activation+0.166
Top resid features:
at
Token at
Feature activation-0.036
Top resid features:
the
Token the
Feature activation-0.032
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
African
Token African
Feature activation+0.001
Top resid features:
nation
Token nation
Feature activation-0.001
Top resid features:
.
Token .
Feature activation+0.039
Top resid features:
Since
Token Since
Feature activation+0.682
Top resid features:
then
Token then
Feature activation+2.229
Top resid features:
,
Token,
Feature activation+1.600
Top resid features:
Libya
Token Libya
Feature activation+0.129
Top resid features:
âĢ
TokenâĢ
Feature activation+0.074
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
donors
Token donors
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
2003
Token 2003
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Since
Token Since
Feature activation+1.852
Top resid features:
then
Token then
Feature activation+2.834
Top resid features:
,
Token,
Feature activation+0.699
Top resid features:
he
Token he
Feature activation+0.047
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
his
Token his
Feature activation-0.039
Top resid features:
allies
Token allies
Feature activation+0.072
Top resid features:
North
Token North
Feature activation+0.001
Top resid features:
African
Token African
Feature activation+0.001
Top resid features:
nation
Token nation
Feature activation-0.001
Top resid features:
.
Token .
Feature activation+0.011
Top resid features:
Since
Token Since
Feature activation+0.636
Top resid features:
then
Token then
Feature activation+1.584
Top resid features:
,
Token,
Feature activation+1.330
Top resid features:
Libya
Token Libya
Feature activation+0.162
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.033
Top resid features:
In
TokenIn
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
last
Token last
Feature activation+0.005
Top resid features:
few
Token few
Feature activation+0.066
Top resid features:
years
Token years
Feature activation+2.925
Top resid features:
,
Token,
Feature activation+2.020
Top resid features:
sites
Token sites
Feature activation+0.179
Top resid features:
like
Token like
Feature activation-0.004
Top resid features:
Kickstarter
Token Kickstarter
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
voices
Token voices
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
In
Token In
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
past
Token past
Feature activation+4.427
Top resid features:
,
Token,
Feature activation+0.595
Top resid features:
mental
Token mental
Feature activation+0.001
Top resid features:
health
Token health
Feature activation-0.003
Top resid features:
professionals
Token professionals
Feature activation+0.131
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
reass
Token reass
Feature activation-0.000
Top resid features:
umed
Tokenumed
Feature activation-0.014
Top resid features:
power
Token power
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
2012
Token 2012
Feature activation+0.227
Top resid features:
,
Token,
Feature activation+3.743
Top resid features:
relations
Token relations
Feature activation+0.860
Top resid features:
between
Token between
Feature activation+0.005
Top resid features:
Tokyo
Token Tokyo
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
Seoul
Token Seoul
Feature activation+0.017
Top resid features:
its
Token its
Feature activation-0.002
Top resid features:
start
Token start
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
since
Token since
Feature activation+0.558
Top resid features:
then
Token then
Feature activation+2.347
Top resid features:
,
Token,
Feature activation+1.351
Top resid features:
the
Token the
Feature activation+0.337
Top resid features:
damn
Token damn
Feature activation+0.073
Top resid features:
thing
Token thing
Feature activation+0.060
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Over
TokenOver
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
last
Token last
Feature activation+0.046
Top resid features:
year
Token year
Feature activation+4.096
Top resid features:
many
Token many
Feature activation+0.627
Top resid features:
Americans
Token Americans
Feature activation+0.225
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
heard
Token heard
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.020
Top resid features:
For
TokenFor
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
while
Token while
Feature activation+0.442
Top resid features:
now
Token now
Feature activation+3.084
Top resid features:
,
Token,
Feature activation+1.287
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
Ruby
Token Ruby
Feature activation+0.015
Top resid features:
community
Token community
Feature activation+0.048
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Since
Token Since
Feature activation+0.249
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
1980
Token 1980
Feature activation+0.222
Top resid features:
s
Tokens
Feature activation+1.873
Top resid features:
,
Token,
Feature activation+2.477
Top resid features:
the
Token the
Feature activation+0.184
Top resid features:
institutional
Token institutional
Feature activation-0.011
Top resid features:
infrastructure
Token infrastructure
Feature activation-0.041
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
decades
Token decades
Feature activation+0.060
Top resid features:
since
Token since
Feature activation+0.519
Top resid features:
World
Token World
Feature activation-0.000
Top resid features:
War
Token War
Feature activation+0.001
Top resid features:
II
Token II
Feature activation+0.355
Top resid features:
,
Token,
Feature activation+2.761
Top resid features:
the
Token the
Feature activation+0.249
Top resid features:
CFR
Token CFR
Feature activation+0.062
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.043
Top resid features:
decades
Token decades
Feature activation+0.179
Top resid features:
since
Token since
Feature activation+1.171
Top resid features:
World
Token World
Feature activation+0.000
Top resid features:
War
Token War
Feature activation+0.012
Top resid features:
II
Token II
Feature activation+0.751
Top resid features:
,
Token,
Feature activation+2.309
Top resid features:
the
Token the
Feature activation+0.344
Top resid features:
CFR
Token CFR
Feature activation+0.039
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.04

Head 4: 0.06

Head 5: 0.61

Head 6: 0.03

Head 7: 0.03

Head 8: 0.02

Head 9: 0.10

Head 10: 0.01

Head 11: 0.03

Positive logits

has5.23

have5.21

have5.07

has4.71

've4.68

hath4.23

Have4.09

hasn4.08

haven4.00

HAS3.92

been3.89

Has3.82

HAVE3.60

Have3.59

Has3.54

pmwiki3.34

been3.24

haven3.00

reviewed2.96

had2.82

Negative logits

someday-3.25

=$-3.11

))))-3.05

"},{"-2.99

ASAP-2.99

uble-2.82

":"/-2.79

anyways-2.73

tomorrow-2.71

"],"-2.70

abus-2.65

htt-2.64

secondly-2.63

/>-2.60

"}],"-2.57

Adds-2.56

>.-2.54

2020-2.54

Shutterstock-2.49

\":-2.48

INTERVAL 5.876 - 6.529
CONTAINS 0.000%

that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
orks
Tokenorks
Feature activation+6.148
have
Token have
Feature activation+1.252
taken
Token taken
Feature activation+0.037
just
Token just
Feature activation+0.000
4
Token 4
Feature activation+0.000
points
Token points
Feature activation+0.047
Ļ
TokenĻ
Feature activation+4.789
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Fighting
Token Fighting
Feature activation+0.000
Group
Token Group
Feature activation+6.529
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
IF
TokenIF
Feature activation+0.000
G
TokenG
Feature activation+0.000
)
Token)
Feature activation+6.412
Group
Token Group
Feature activation+6.529
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
IF
TokenIF
Feature activation+0.000
G
TokenG
Feature activation+0.000
)
Token)
Feature activation+6.412
have
Token have
Feature activation+1.096
armed
Token armed
Feature activation+0.000
sectarian
Token sectarian
Feature activation+0.000
extremists
Token extremists
Feature activation+0.298
across
Token across
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fract
Token fract
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+5.891
have
Token have
Feature activation+0.966
so
Token so
Feature activation+0.113
many
Token many
Feature activation+0.162
nations
Token nations
Feature activation+1.960
lined
Token lined
Feature activation+0.161

INTERVAL 5.223 - 5.876
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
Bell
Token Bell
Feature activation+0.769
Labs
Token Labs
Feature activation+5.521
was
Token was
Feature activation+0.339
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.150
where
Token where
Feature activation+0.000
such
Token such
Feature activation+0.000
here
Token here
Feature activation+1.353
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Brew
Token Brew
Feature activation+0.029
Review
Token Review
Feature activation+5.130
Crew
Token Crew
Feature activation+5.692
have
Token have
Feature activation+0.622
been
Token been
Feature activation+0.067
spreading
Token spreading
Feature activation+0.000
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.000
"
Token"
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
Great
Token Great
Feature activation+0.000
Depression
Token Depression
Feature activation+5.399
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.102
seen
Token seen
Feature activation+1.362
an
Token an
Feature activation+0.000
economic
Token economic
Feature activation+0.000

INTERVAL 4.571 - 5.223
CONTAINS 0.001%

the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
,
Token,
Feature activation+0.000
mental
Token mental
Feature activation+0.000
health
Token health
Feature activation+0.681
professionals
Token professionals
Feature activation+4.660
were
Token were
Feature activation+0.661
taught
Token taught
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
like
Token like
Feature activation+0.000
Kickstarter
Token Kickstarter
Feature activation+4.274
and
Token and
Feature activation+0.000
Ind
Token Ind
Feature activation+0.000
ieg
Tokenieg
Feature activation+0.000
ogo
Tokenogo
Feature activation+4.716
have
Token have
Feature activation+0.686
revolution
Token revolution
Feature activation+0.190
ized
Tokenized
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
we
Token we
Feature activation+2.339
here
Token here
Feature activation+1.353
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Brew
Token Brew
Feature activation+0.029
Review
Token Review
Feature activation+5.130
Crew
Token Crew
Feature activation+5.692
have
Token have
Feature activation+0.622
been
Token been
Feature activation+0.067
spreading
Token spreading
Feature activation+0.000
the
Token the
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+2.192
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
allies
Token allies
Feature activation+4.964
have
Token have
Feature activation+1.275
built
Token built
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
and
Token and
Feature activation+0.000
led
Token led
Feature activation+0.167
by
Token by
Feature activation+0.000
commanders
Token commanders
Feature activation+1.178
of
Token of
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+4.966
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.789
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000

INTERVAL 3.918 - 4.571
CONTAINS 0.002%

talk
Token talk
Feature activation+2.534
of
Token of
Feature activation+0.000
drafting
Token drafting
Feature activation+0.000
articles
Token articles
Feature activation+0.556
of
Token of
Feature activation+0.000
impeachment
Token impeachment
Feature activation+4.287
has
Token has
Feature activation+1.289
remained
Token remained
Feature activation+0.000
limited
Token limited
Feature activation+0.468
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
later
Token later
Feature activation+0.000
,
Token,
Feature activation+0.000
written
Token written
Feature activation+0.000
versions
Token versions
Feature activation+3.987
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
agreement
Token agreement
Feature activation+3.377
have
Token have
Feature activation+0.238
been
Token been
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Since
TokenSince
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
Jay
Token Jay
Feature activation+4.127
has
Token has
Feature activation+0.940
been
Token been
Feature activation+0.177
trying
Token trying
Feature activation+0.239
to
Token to
Feature activation+0.000
gear
Token gear
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+1.165
,
Token,
Feature activation+0.607
and
Token and
Feature activation+0.025
academ
Token academ
Feature activation+0.000
e
Tokene
Feature activation+4.416
have
Token have
Feature activation+1.722
been
Token been
Feature activation+0.599
in
Token in
Feature activation+0.249
the
Token the
Feature activation+0.000
forefront
Token forefront
Feature activation+0.373
,
Token,
Feature activation+0.000
Libya
Token Libya
Feature activation+3.575
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.606
s
Tokens
Feature activation+0.000
militants
Token militants
Feature activation+4.401
led
Token led
Feature activation+0.167
by
Token by
Feature activation+0.000
commanders
Token commanders
Feature activation+1.178
of
Token of
Feature activation+0.000
Al
Token Al
Feature activation+0.000

INTERVAL 3.265 - 3.918
CONTAINS 0.004%

-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+3.781
has
Token has
Feature activation+0.948
been
Token been
Feature activation+0.101
considered
Token considered
Feature activation+0.000
a
Token a
Feature activation+0.000
hallmark
Token hallmark
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
im
Tokenim
Feature activation+0.000
aa
Tokenaa
Feature activation+1.553
community
Token community
Feature activation+3.831
has
Token has
Feature activation+0.735
held
Token held
Feature activation+0.000
three
Token three
Feature activation+0.000
annual
Token annual
Feature activation+0.000
tournaments
Token tournaments
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
slave
Token slave
Feature activation+0.000
man
Token man
Feature activation+0.501
um
Tokenum
Feature activation+0.000
ission
Tokenission
Feature activation+3.341
produced
Token produced
Feature activation+0.000
a
Token a
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
population
Token population
Feature activation+0.000
of
Token of
Feature activation+0.000
II
Token II
Feature activation+0.162
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
CFR
Token CFR
Feature activation+4.416
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.400
s
Tokens
Feature activation+0.367
very
Token very
Feature activation+0.000
influential
Token influential
Feature activation+0.000
members
Token members
Feature activation+4.027
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
decades
Token decades
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+3.282
relied
Token relied
Feature activation+0.000
on
Token on
Feature activation+0.000
country
Token country
Feature activation+0.000
music
Token music
Feature activation+0.197
to
Token to
Feature activation+0.000

INTERVAL 2.612 - 3.265
CONTAINS 0.006%

results
Token results
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
he
Token he
Feature activation+3.056
has
Token has
Feature activation+1.396
also
Token also
Feature activation+1.009
taken
Token taken
Feature activation+0.163
sensible
Token sensible
Feature activation+0.000
positions
Token positions
Feature activation+0.390
.
Token.
Feature activation+0.000
Since
Token Since
Feature activation+0.000
December
Token December
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
,
Token,
Feature activation+0.000
Google
Token Google
Feature activation+2.732
has
Token has
Feature activation+0.957
offered
Token offered
Feature activation+0.079
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
version
Token version
Feature activation+0.053
and
Token and
Feature activation+0.000
David
Token David
Feature activation+0.000
Beckham
Token Beckham
Feature activation+0.608
,
Token,
Feature activation+0.395
the
Token the
Feature activation+0.000
club
Token club
Feature activation+2.897
has
Token has
Feature activation+0.392
been
Token been
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
re
Token re
Feature activation+0.000
branded
Tokenbranded
Feature activation+0.083
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
And
Token And
Feature activation+0.000
for
Token for
Feature activation+0.000
decades
Token decades
Feature activation+0.000
psychologists
Token psychologists
Feature activation+2.685
have
Token have
Feature activation+1.283
known
Token known
Feature activation+0.153
that
Token that
Feature activation+0.000
context
Token context
Feature activation+0.459
matters
Token matters
Feature activation+0.000
,
Token,
Feature activation+0.000
organizations
Token organizations
Feature activation+2.092
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Cross
Token Cross
Feature activation+3.111
have
Token have
Feature activation+0.493
mobilized
Token mobilized
Feature activation+0.126
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000

INTERVAL 1.959 - 2.612
CONTAINS 0.012%

centuries
Token centuries
Feature activation+0.000
our
Token our
Feature activation+0.000
brave
Token brave
Feature activation+0.071
men
Token men
Feature activation+2.689
and
Token and
Feature activation+0.227
women
Token women
Feature activation+2.113
in
Token in
Feature activation+0.000
uniform
Token uniform
Feature activation+4.257
have
Token have
Feature activation+1.518
overcome
Token overcome
Feature activation+0.276
tyranny
Token tyranny
Feature activation+0.884
says
Token says
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
conditions
Token conditions
Feature activation+1.966
have
Token have
Feature activation+0.166
gotten
Token gotten
Feature activation+0.000
more
Token more
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
here
Token here
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
prevalence
Token prevalence
Feature activation+2.151
was
Token was
Feature activation+0.452
estimated
Token estimated
Feature activation+0.019
by
Token by
Feature activation+0.000
sampling
Token sampling
Feature activation+0.071
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
draw
Token draw
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+2.225
have
Token have
Feature activation+0.397
scored
Token scored
Feature activation+0.008
one
Token one
Feature activation+0.000
goal
Token goal
Feature activation+0.364
(
Token (
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
.
Token.
Feature activation+0.000
Trad
Token Trad
Feature activation+0.000
itionally
Tokenitionally
Feature activation+0.000
,
Token,
Feature activation+0.030
leaders
Token leaders
Feature activation+2.583
of
Token of
Feature activation+0.000
mult
Token mult
Feature activation+0.000
ilateral
Tokenilateral
Feature activation+0.000
institutions
Token institutions
Feature activation+2.715
are
Token are
Feature activation+0.849

INTERVAL 1.306 - 1.959
CONTAINS 0.023%

since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.384
and
Token and
Feature activation+0.000
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
students
Token students
Feature activation+1.484
,
Token,
Feature activation+0.608
just
Token just
Feature activation+0.167
like
Token like
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
,
Token,
Feature activation+2.182
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
imposed
Tokenimposed
Feature activation+0.000
rule
Token rule
Feature activation+1.519
,
Token,
Feature activation+0.082
I
Token I
Feature activation+1.350
âĢ
TokenâĢ
Feature activation+0.924
Ļ
TokenĻ
Feature activation+3.125
ve
Tokenve
Feature activation+1.131
also
Token also
Feature activation+0.469
developed
Token developed
Feature activation+0.000
men
Token men
Feature activation+2.689
and
Token and
Feature activation+0.227
women
Token women
Feature activation+2.113
in
Token in
Feature activation+0.000
uniform
Token uniform
Feature activation+4.257
have
Token have
Feature activation+1.518
overcome
Token overcome
Feature activation+0.276
tyranny
Token tyranny
Feature activation+0.884
,
Token,
Feature activation+0.040
fascism
Token fascism
Feature activation+0.908
,
Token,
Feature activation+0.000
stakes
Token stakes
Feature activation+1.456
in
Token in
Feature activation+0.000
talks
Token talks
Feature activation+1.489
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.342
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
due
Token due
Feature activation+0.000
goal
Token goal
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+0.561
has
Token has
Feature activation+1.219
always
Token always
Feature activation+1.369
been
Token been
Feature activation+0.244
Formula
Token Formula
Feature activation+0.000
1
Token 1
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.666

INTERVAL 0.653 - 1.306
CONTAINS 0.092%

lot
Token lot
Feature activation+0.000
stranger
Token stranger
Feature activation+0.000
now
Token now
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
son
Token son
Feature activation+1.140
allegedly
Token allegedly
Feature activation+0.594
revealed
Token revealed
Feature activation+0.000
his
Token his
Feature activation+0.000
whereabouts
Token whereabouts
Feature activation+0.000
online
Token online
Feature activation+0.000
few
Token few
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.152
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.629
she
Token she
Feature activation+0.943
said
Token said
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
event
Token event
Feature activation+0.000
has
Token has
Feature activation+0.000
it
Token it
Feature activation+0.030
helped
Token helped
Feature activation+0.000
your
Token your
Feature activation+0.000
sleeping
Token sleeping
Feature activation+0.338
patterns
Token patterns
Feature activation+1.006
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Source
TokenSource
Feature activation+0.000
:
Token:
Feature activation+0.000
never
Token never
Feature activation+0.000
shared
Token shared
Feature activation+0.158
water
Token water
Feature activation+0.980
with
Token with
Feature activation+0.310
a
Token a
Feature activation+0.000
male
Token male
Feature activation+0.691
.
Token.
Feature activation+0.040
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
pup
Token pup
Feature activation+0.175
to
Token to
Feature activation+0.000
assign
Token assign
Feature activation+0.000
a
Token a
Feature activation+0.000
date
Token date
Feature activation+0.491
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.958
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.525
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.653
CONTAINS 99.859%

few
Token few
Feature activation+0.000
copies
Token copies
Feature activation+0.000
for
Token for
Feature activation+0.000
retailers
Token retailers
Feature activation+0.000
,
Token,
Feature activation+0.000
chiefly
Token chiefly
Feature activation+0.000
for
Token for
Feature activation+0.000
Water
Token Water
Feature activation+0.000
stones
Tokenstones
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
spouses
Token spouses
Feature activation+0.000
and
Token and
Feature activation+0.000
partners
Token partners
Feature activation+0.000
being
Token being
Feature activation+0.000
detained
Token detained
Feature activation+0.000
and
Token and
Feature activation+0.000
interrogated
Token interrogated
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
there
Token there
Feature activation+0.000
House
Token House
Feature activation+0.000
Counsel
Token Counsel
Feature activation+0.000
Neil
Token Neil
Feature activation+0.000
Egg
Token Egg
Feature activation+0.000
l
Tokenl
Feature activation+0.000
eston
Tokeneston
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
point
Token point
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
now
Token now
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
John
Token John
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
seriousness
Token seriousness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
charge
Token charge
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 H10.5: (feature 1287)

TOP ACTIVATIONS
MAX = 5.844

Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
D
Token D
Feature activation+0.000
annel
Tokenannel
Feature activation+0.000
Mall
Token Mall
Feature activation+0.000
oy
Tokenoy
Feature activation+5.844
is
Token is
Feature activation+3.151
joining
Token joining
Feature activation+0.004
in
Token in
Feature activation+1.520
,
Token,
Feature activation+0.725
too
Token too
Feature activation+1.062
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+4.268
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+1.351
countries
Token countries
Feature activation+5.035
has
Token has
Feature activation+1.113
become
Token become
Feature activation+0.099
primarily
Token primarily
Feature activation+0.907
economic
Token economic
Feature activation+2.170
,
Token,
Feature activation+0.525
case
Token case
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.132
they
Token they
Feature activation+4.999
are
Token are
Feature activation+4.583
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
organizations
Token organizations
Feature activation+4.641
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+4.897
are
Token are
Feature activation+2.246
beginning
Token beginning
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.560
with
Token with
Feature activation+0.000
make
Token make
Feature activation+0.000
Par
Token Par
Feature activation+0.000
se
Tokense
Feature activation+0.081
code
Token code
Feature activation+0.000
open
Token open
Feature activation+0.963
source
Token source
Feature activation+4.871
adds
Token adds
Feature activation+0.000
more
Token more
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
to
Token to
Feature activation+0.000
these
Token these
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.057
,
Token,
Feature activation+0.500
the
Token the
Feature activation+0.000
team
Token team
Feature activation+4.733
has
Token has
Feature activation+1.852
made
Token made
Feature activation+0.000
some
Token some
Feature activation+0.000
brilliant
Token brilliant
Feature activation+0.000
roster
Token roster
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.183
governments
Token governments
Feature activation+3.584
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
organizations
Token organizations
Feature activation+4.641
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+4.897
are
Token are
Feature activation+2.246
beginning
Token beginning
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.132
they
Token they
Feature activation+4.999
are
Token are
Feature activation+4.583
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
empt
Tokenempt
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
W
Token W
Feature activation+0.000
ren
Tokenren
Feature activation+4.351
works
Token works
Feature activation+0.000
for
Token for
Feature activation+0.000
D
Token D
Feature activation+0.000
omb
Tokenomb
Feature activation+0.000
rows
Tokenrows
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
attorneys
Token attorneys
Feature activation+1.844
and
Token and
Feature activation+0.000
city
Token city
Feature activation+0.013
managers
Token managers
Feature activation+4.306
grapple
Token grapple
Feature activation+0.242
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.117
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+4.268
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+1.351
countries
Token countries
Feature activation+5.035
has
Token has
Feature activation+1.113
for
Token for
Feature activation+0.000
riders
Token riders
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
now
Token now
Feature activation+0.000
they
Token they
Feature activation+4.239
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.872
could
Token could
Feature activation+0.120
back
Token back
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+1.008
player
Token player
Feature activation+1.744
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+4.216
has
Token has
Feature activation+0.000
broken
Token broken
Feature activation+0.000
it
Token it
Feature activation+1.563
,
Token,
Feature activation+0.637
and
Token and
Feature activation+0.130
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
Sn
Token Sn
Feature activation+0.000
opes
Tokenopes
Feature activation+4.202
has
Token has
Feature activation+1.366
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
posting
Token posting
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.352
they
Token they
Feature activation+4.063
have
Token have
Feature activation+0.868
resumed
Token resumed
Feature activation+0.000
their
Token their
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000
strike
Token strike
Feature activation+2.924
S
Token S
Feature activation+0.000
MI
TokenMI
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
Westbrook
Token Westbrook
Feature activation+4.060
is
Token is
Feature activation+1.094
30
Token 30
Feature activation+1.505
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
'll
Token'll
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
the
Token the
Feature activation+0.000
NRA
Token NRA
Feature activation+4.046
wants
Token wants
Feature activation+0.301
to
Token to
Feature activation+0.004
up
Token up
Feature activation+0.000
end
Tokenend
Feature activation+0.278
those
Token those
Feature activation+0.000
Unity
Token Unity
Feature activation+0.129
5
Token 5
Feature activation+0.288
version
Token version
Feature activation+2.211
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+3.859
is
Token is
Feature activation+0.849
a
Token a
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
match
Token match
Feature activation+0.087
will
Token will
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
a
Token a
Feature activation+0.000
trial
Token trial
Feature activation+2.793
judge
Token judge
Feature activation+3.732
will
Token will
Feature activation+0.941
attempt
Token attempt
Feature activation+0.020
to
Token to
Feature activation+0.000
ascertain
Token ascertain
Feature activation+0.000
the
Token the
Feature activation+0.000
Christopher
Token Christopher
Feature activation+0.000
Markus
Token Markus
Feature activation+0.000
and
Token and
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
McF
Token McF
Feature activation+0.000
eely
Tokeneely
Feature activation+3.670
recently
Token recently
Feature activation+1.436
talked
Token talked
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
possibility
Token possibility
Feature activation+0.111

Top DFA by src position
MAX = 6.011

:
Token:
Feature activation+0.003
Top resid features:
"
Token "
Feature activation-0.006
Top resid features:
global
Tokenglobal
Feature activation-0.000
Top resid features:
warming
Token warming
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+0.050
Top resid features:
Now
Token Now
Feature activation+6.011
Top resid features:
Connecticut
Token Connecticut
Feature activation+0.045
Top resid features:
Gov
Token Gov
Feature activation+0.039
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
D
Token D
Feature activation+0.001
Top resid features:
annel
Tokenannel
Feature activation+0.002
Top resid features:
radar
Token radar
Feature activation-0.003
Top resid features:
system
Token system
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Now
TokenNow
Feature activation+3.833
Top resid features:
,
Token,
Feature activation+1.046
Top resid features:
the
Token the
Feature activation+0.232
Top resid features:
relationship
Token relationship
Feature activation+0.629
Top resid features:
between
Token between
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Now
TokenNow
Feature activation+5.137
Top resid features:
they
Token they
Feature activation+0.149
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pre
Token pre
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Enterprise
Token Enterprise
Feature activation+0.001
Top resid features:
Ethereum
Token Ethereum
Feature activation-0.001
Top resid features:
Alliance
Token Alliance
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Now
Token Now
Feature activation+4.080
Top resid features:
,
Token,
Feature activation+0.781
Top resid features:
governments
Token governments
Feature activation+0.302
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
international
Token international
Feature activation-0.018
Top resid features:
organizations
Token organizations
Feature activation+0.197
Top resid features:
aa
Tokenaa
Feature activation-0.003
Top resid features:
S
TokenS
Feature activation+0.001
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
platforms
Token platforms
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Now
Token Now
Feature activation+4.989
Top resid features:
Facebook
Token Facebook
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation-0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
decision
Token decision
Feature activation+0.138
Top resid features:
players
Token players
Feature activation-0.002
Top resid features:
alike
Token alike
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
Now
TokenNow
Feature activation+3.620
Top resid features:
,
Token,
Feature activation+1.527
Top resid features:
the
Token the
Feature activation+0.222
Top resid features:
team
Token team
Feature activation+0.026
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Enterprise
Token Enterprise
Feature activation+0.000
Top resid features:
Ethereum
Token Ethereum
Feature activation-0.005
Top resid features:
Alliance
Token Alliance
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Now
Token Now
Feature activation+3.882
Top resid features:
,
Token,
Feature activation+1.027
Top resid features:
governments
Token governments
Feature activation+0.238
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
international
Token international
Feature activation-0.046
Top resid features:
organizations
Token organizations
Feature activation+0.178
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Now
TokenNow
Feature activation+4.080
Top resid features:
they
Token they
Feature activation+0.517
Top resid features:
are
Token are
Feature activation+0.225
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pre
Token pre
Feature activation+0.000
Top resid features:
following
Token following
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
2014
Token 2014
Feature activation-0.009
Top resid features:
season
Token season
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Now
Token Now
Feature activation+4.626
Top resid features:
W
Token W
Feature activation+0.025
Top resid features:
ren
Tokenren
Feature activation+0.079
Top resid features:
works
Token works
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.185
Top resid features:
cameras
Token cameras
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Now
Token Now
Feature activation+4.375
Top resid features:
attorneys
Token attorneys
Feature activation+0.241
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
city
Token city
Feature activation+0.013
Top resid features:
managers
Token managers
Feature activation+0.254
Top resid features:
grapple
Token grapple
Feature activation+0.000
Top resid features:
radar
Token radar
Feature activation-0.001
Top resid features:
system
Token system
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Now
TokenNow
Feature activation+3.157
Top resid features:
,
Token,
Feature activation+1.200
Top resid features:
the
Token the
Feature activation+0.292
Top resid features:
relationship
Token relationship
Feature activation+0.288
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
safe
Token safe
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
riders
Token riders
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
But
Token But
Feature activation+0.026
Top resid features:
now
Token now
Feature activation+4.369
Top resid features:
they
Token they
Feature activation+0.322
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
60
Token 60
Feature activation+0.000
Top resid features:
games
Token games
Feature activation-0.002
Top resid features:
-
Token -
Feature activation+0.030
Top resid features:
and
Token and
Feature activation-0.056
Top resid features:
now
Token now
Feature activation+3.918
Top resid features:
the
Token the
Feature activation+0.386
Top resid features:
best
Token best
Feature activation+0.074
Top resid features:
player
Token player
Feature activation+0.249
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
really
Token really
Feature activation-0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Now
TokenNow
Feature activation+4.634
Top resid features:
Sn
Token Sn
Feature activation+0.010
Top resid features:
opes
Tokenopes
Feature activation+0.025
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
themselves
Token themselves
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
one
Token one
Feature activation-0.005
Top resid features:
another
Token another
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Now
Token Now
Feature activation+4.070
Top resid features:
they
Token they
Feature activation+0.401
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
resumed
Token resumed
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
hunger
Token hunger
Feature activation+0.000
Top resid features:
Icon
TokenIcon
Feature activation-0.000
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
MI
TokenMI
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
Now
TokenNow
Feature activation+4.467
Top resid features:
Westbrook
Token Westbrook
Feature activation+0.130
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
he
Tokenhe
Feature activation+0.000
Top resid features:
concealed
Token concealed
Feature activation+0.002
Top resid features:
weapon
Token weapon
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.025
Top resid features:
Now
TokenNow
Feature activation+4.003
Top resid features:
the
Token the
Feature activation+0.430
Top resid features:
NRA
Token NRA
Feature activation+0.059
Top resid features:
wants
Token wants
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
fixing
Token fixing
Feature activation+0.015
Top resid features:
those
Token those
Feature activation-0.003
Top resid features:
bugs
Token bugs
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.038
Top resid features:
now
Token now
Feature activation+4.042
Top resid features:
the
Token the
Feature activation+0.226
Top resid features:
Unity
Token Unity
Feature activation+0.010
Top resid features:
5
Token 5
Feature activation+0.014
Top resid features:
version
Token version
Feature activation+0.126
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Now
Token Now
Feature activation+3.464
Top resid features:
a
Token a
Feature activation+0.516
Top resid features:
trial
Token trial
Feature activation+0.033
Top resid features:
judge
Token judge
Feature activation+0.220
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
attempt
Token attempt
Feature activation+0.000
Top resid features:
event
Token event
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
epic
Token epic
Feature activation-0.000
Top resid features:
proportions
Token proportions
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Now
Token Now
Feature activation+3.446
Top resid features:
that
Token that
Feature activation+0.124
Top resid features:
Captain
Token Captain
Feature activation-0.001
Top resid features:
America
Token America
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
Civil
Token Civil
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.03

Head 3: 0.04

Head 4: 0.07

Head 5: 0.61

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.09

Head 10: 0.02

Head 11: 0.03

Positive logits

thanks3.57

can3.16

are3.03

feels3.00

is2.98

realizes2.92

seems2.88

has2.86

appears2.82

refers2.79

wants2.79

awaits2.73

looks2.61

?!2.61

esters2.59

sporting2.51

!!2.47

recogn2.47

smells2.46

wonder2.44

Negative logits

THEN-3.75

Then-3.52

then-3.47

went-3.40

tended-3.38

stayed-3.38

BEFORE-3.20

icipated-3.18

stood-3.18

acted-3.18

Didn-3.17

then-3.17

remained-3.13

puted-3.12

Eventually-3.10

continued-3.10

Eventually-3.07

Ended-3.07

proceeded-3.06

sequently-3.04

INTERVAL 5.260 - 5.844
CONTAINS 0.000%

Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
D
Token D
Feature activation+0.000
annel
Tokenannel
Feature activation+0.000
Mall
Token Mall
Feature activation+0.000
oy
Tokenoy
Feature activation+5.844
is
Token is
Feature activation+3.151
joining
Token joining
Feature activation+0.004
in
Token in
Feature activation+1.520
,
Token,
Feature activation+0.725
too
Token too
Feature activation+1.062

INTERVAL 4.676 - 5.260
CONTAINS 0.001%

the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+4.268
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+1.351
countries
Token countries
Feature activation+5.035
has
Token has
Feature activation+1.113
become
Token become
Feature activation+0.099
primarily
Token primarily
Feature activation+0.907
economic
Token economic
Feature activation+2.170
,
Token,
Feature activation+0.525
case
Token case
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.132
they
Token they
Feature activation+4.999
are
Token are
Feature activation+4.583
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
organizations
Token organizations
Feature activation+4.641
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+4.897
are
Token are
Feature activation+2.246
beginning
Token beginning
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.560
with
Token with
Feature activation+0.000
make
Token make
Feature activation+0.000
Par
Token Par
Feature activation+0.000
se
Tokense
Feature activation+0.081
code
Token code
Feature activation+0.000
open
Token open
Feature activation+0.963
source
Token source
Feature activation+4.871
adds
Token adds
Feature activation+0.000
more
Token more
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
to
Token to
Feature activation+0.000
these
Token these
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.057
,
Token,
Feature activation+0.500
the
Token the
Feature activation+0.000
team
Token team
Feature activation+4.733
has
Token has
Feature activation+1.852
made
Token made
Feature activation+0.000
some
Token some
Feature activation+0.000
brilliant
Token brilliant
Feature activation+0.000
roster
Token roster
Feature activation+0.000

INTERVAL 4.091 - 4.676
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
Sn
Token Sn
Feature activation+0.000
opes
Tokenopes
Feature activation+4.202
has
Token has
Feature activation+1.366
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
posting
Token posting
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.117
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+4.268
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+1.351
countries
Token countries
Feature activation+5.035
has
Token has
Feature activation+1.113
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
attorneys
Token attorneys
Feature activation+1.844
and
Token and
Feature activation+0.000
city
Token city
Feature activation+0.013
managers
Token managers
Feature activation+4.306
grapple
Token grapple
Feature activation+0.242
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.132
they
Token they
Feature activation+4.999
are
Token are
Feature activation+4.583
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
empt
Tokenempt
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.183
governments
Token governments
Feature activation+3.584
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
organizations
Token organizations
Feature activation+4.641
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+4.897
are
Token are
Feature activation+2.246
beginning
Token beginning
Feature activation+0.000

INTERVAL 3.507 - 4.091
CONTAINS 0.001%

and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.352
they
Token they
Feature activation+4.063
have
Token have
Feature activation+0.868
resumed
Token resumed
Feature activation+0.000
their
Token their
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000
strike
Token strike
Feature activation+2.924
ate
Tokenate
Feature activation+2.647
and
Token and
Feature activation+0.524
Mew
Token Mew
Feature activation+0.408
two
Tokentwo
Feature activation+2.649
and
Token and
Feature activation+0.000
Pikachu
Token Pikachu
Feature activation+3.535
are
Token are
Feature activation+1.462
once
Token once
Feature activation+0.126
again
Token again
Feature activation+1.159
laps
Token laps
Feature activation+0.032
ed
Tokened
Feature activation+0.487
Unity
Token Unity
Feature activation+0.129
5
Token 5
Feature activation+0.288
version
Token version
Feature activation+2.211
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+3.859
is
Token is
Feature activation+0.849
a
Token a
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
match
Token match
Feature activation+0.087
will
Token will
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
a
Token a
Feature activation+0.000
trial
Token trial
Feature activation+2.793
judge
Token judge
Feature activation+3.732
will
Token will
Feature activation+0.941
attempt
Token attempt
Feature activation+0.020
to
Token to
Feature activation+0.000
ascertain
Token ascertain
Feature activation+0.000
the
Token the
Feature activation+0.000
led
Tokenled
Feature activation+0.000
hysteria
Token hysteria
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.479
they
Token they
Feature activation+3.636
do
Token do
Feature activation+1.181
admit
Token admit
Feature activation+0.000
,
Token,
Feature activation+0.258
like
Token like
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000

INTERVAL 2.922 - 3.507
CONTAINS 0.002%

pur
Token pur
Feature activation+0.000
vey
Tokenvey
Feature activation+0.000
ors
Tokenors
Feature activation+1.789
of
Token of
Feature activation+0.000
Hudson
Token Hudson
Feature activation+0.000
politics
Token politics
Feature activation+2.984
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
praise
Token praise
Feature activation+0.000
PATH
Token PATH
Feature activation+0.000
and
Token and
Feature activation+0.212
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
adays
Tokenadays
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
countries
Token countries
Feature activation+3.148
typically
Token typically
Feature activation+1.558
have
Token have
Feature activation+0.176
sizable
Token sizable
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
reserves
Token reserves
Feature activation+0.000
,
Token,
Feature activation+0.653
though
Token though
Feature activation+0.244
,
Token,
Feature activation+1.116
the
Token the
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+3.497
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.771
s
Tokens
Feature activation+0.394
Robert
Token Robert
Feature activation+0.000
Costa
Token Costa
Feature activation+2.369
)
Token )
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
now
Token now
Feature activation+0.000
Aleppo
Token Aleppo
Feature activation+3.256
has
Token has
Feature activation+0.767
fallen
Token fallen
Feature activation+0.474
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
flames
Token flames
Feature activation+1.305
stream
Tokenstream
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.953
it
Token it
Feature activation+2.961
reads
Token reads
Feature activation+0.093
"
Token "
Feature activation+0.000
Pal
TokenPal
Feature activation+0.000
estine
Tokenestine
Feature activation+0.000
".
Token".
Feature activation+0.694

INTERVAL 2.338 - 2.922
CONTAINS 0.005%

about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.876
I
Token I
Feature activation+2.343
am
Token am
Feature activation+0.704
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.014
much
Token much
Feature activation+0.000
sense
Token sense
Feature activation+0.000
).
Token).
Feature activation+0.000
So
Token So
Feature activation+0.000
now
Token now
Feature activation+0.000
Amazon
Token Amazon
Feature activation+2.726
has
Token has
Feature activation+0.440
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
even
Token even
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
now
Token now
Feature activation+0.109
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
election
Token election
Feature activation+2.574
's
Token's
Feature activation+0.537
over
Token over
Feature activation+1.640
,
Token,
Feature activation+0.679
he
Token he
Feature activation+2.551
's
Token's
Feature activation+1.936
the
Token the
Feature activation+0.000
election
Token election
Feature activation+2.574
's
Token's
Feature activation+0.537
over
Token over
Feature activation+1.640
,
Token,
Feature activation+0.679
he
Token he
Feature activation+2.551
's
Token's
Feature activation+1.936
having
Token having
Feature activation+0.278
trouble
Token trouble
Feature activation+0.000
identifying
Token identifying
Feature activation+0.000
any
Token any
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.073
he
Token he
Feature activation+2.843
was
Token was
Feature activation+0.460
suddenly
Token suddenly
Feature activation+0.376
the
Token the
Feature activation+0.000
49
Token 49
Feature activation+0.000
ers
Tokeners
Feature activation+0.000

INTERVAL 1.753 - 2.338
CONTAINS 0.007%

election
Token election
Feature activation+2.574
's
Token's
Feature activation+0.537
over
Token over
Feature activation+1.640
,
Token,
Feature activation+0.679
he
Token he
Feature activation+2.551
's
Token's
Feature activation+1.936
having
Token having
Feature activation+0.278
trouble
Token trouble
Feature activation+0.000
identifying
Token identifying
Feature activation+0.000
any
Token any
Feature activation+0.000
actual
Token actual
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
books
Token books
Feature activation+0.000
hel
Tokenhel
Feature activation+0.000
ves
Tokenves
Feature activation+2.024
in
Token in
Feature activation+0.000
America
Token America
Feature activation+1.304
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
available
Token available
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
it
Token it
Feature activation+1.057
âĢ
TokenâĢ
Feature activation+0.350
Ļ
TokenĻ
Feature activation+2.178
s
Tokens
Feature activation+1.452
a
Token a
Feature activation+0.000
Kickstarter
Token Kickstarter
Feature activation+1.844
Project
Token Project
Feature activation+2.382
.
Token.
Feature activation+0.033
he
Token he
Feature activation+2.219
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.272
s
Tokens
Feature activation+1.153
an
Token an
Feature activation+0.000
adult
Token adult
Feature activation+1.906
who
Token who
Feature activation+0.491
just
Token just
Feature activation+0.270
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.172
it
Token it
Feature activation+2.257
appears
Token appears
Feature activation+0.328
that
Token that
Feature activation+0.000
CB
Token CB
Feature activation+0.000
SA
TokenSA
Feature activation+1.823
intended
Token intended
Feature activation+0.000

INTERVAL 1.169 - 1.753
CONTAINS 0.022%

returns
Token returns
Feature activation+0.002
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
screen
Token screen
Feature activation+0.000
near
Token near
Feature activation+0.000
you
Token you
Feature activation+1.342
for
Token for
Feature activation+0.000
another
Token another
Feature activation+0.000
installment
Token installment
Feature activation+0.000
of
Token of
Feature activation+0.000
Liberty
Token Liberty
Feature activation+0.000
has
Token has
Feature activation+1.852
made
Token made
Feature activation+0.000
some
Token some
Feature activation+0.000
brilliant
Token brilliant
Feature activation+0.000
roster
Token roster
Feature activation+0.000
moves
Token moves
Feature activation+1.411
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.457
moved
Token moved
Feature activation+0.000
Ken
Token Ken
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
Today
Token Today
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
symb
Token symb
Feature activation+0.000
iotic
Tokeniotic
Feature activation+0.000
technologies
Token technologies
Feature activation+1.460
have
Token have
Feature activation+0.044
earned
Token earned
Feature activation+0.000
them
Token them
Feature activation+0.000
rightful
Token rightful
Feature activation+0.000
places
Token places
Feature activation+0.012
whole
Token whole
Feature activation+0.000
world
Token world
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+1.292
s
Tokens
Feature activation+0.448
a
Token a
Feature activation+0.000
move
Token move
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
tech
Token tech
Feature activation+0.000
talent
Token talent
Feature activation+0.000
is
Token is
Feature activation+0.000
already
Token already
Feature activation+0.000
well
Token well
Feature activation+0.000
documented
Token documented
Feature activation+1.482
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000

INTERVAL 0.584 - 1.169
CONTAINS 0.076%

are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+0.241
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.815
yet
Tokenyet
Feature activation+0.000
)
Token)
Feature activation+0.378
people
Token people
Feature activation+0.720
are
Token are
Feature activation+0.558
getting
Token getting
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+0.000
popular
Token popular
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
in
Token in
Feature activation+0.000
cities
Token cities
Feature activation+0.679
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.993
.
Token.
Feature activation+0.000
Bar
Token Bar
Feature activation+0.000
ring
Tokenring
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.191
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.657
s
Tokens
Feature activation+0.000
done
Token done
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
destruct
Tokendestruct
Feature activation+0.204
different
Token different
Feature activation+0.000
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
,
Token,
Feature activation+0.000
Obama
Token Obama
Feature activation+2.726
has
Token has
Feature activation+0.865
been
Token been
Feature activation+0.221
labelled
Token labelled
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+0.000
popular
Token popular
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+0.024
with
Token with
Feature activation+0.000
Caesar
Token Caesar
Feature activation+0.000
seemingly
Token seemingly
Feature activation+0.447
clumsy
Token clumsy
Feature activation+0.706
-
Token-
Feature activation+0.000
footed
Tokenfooted
Feature activation+1.221
on
Token on
Feature activation+0.000
another
Token another
Feature activation+0.000
issue
Token issue
Feature activation+0.983

INTERVAL 0.000 - 0.584
CONTAINS 99.887%

Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
?
Token?
Feature activation+0.000
Take
Token Take
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
RO
Token RO
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
executive
Token executive
Feature activation+0.000
network
Token network
Feature activation+0.000
and
Token and
Feature activation+0.000
DM
Token DM
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
the
Token the
Feature activation+0.000
fee
Token fee
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
fee
Token fee
Feature activation+0.000
of
Token of
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
college
Token college
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
that
Token that
Feature activation+0.000
should
Token should
Feature activation+0.000
pay
Token pay
Feature activation+0.000
between
Token between
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
occur
Token occur
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Law
TokenLaw
Feature activation+0.000
makers
Tokenmakers
Feature activation+0.000
are
Token are
Feature activation+0.000
trying
Token trying
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