H4.1 top features

Top feature 0 in H4.1: (feature 21785)

TOP ACTIVATIONS
MAX = 5.214

as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000
find
Token find
Feature activation+0.688
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.[
Token.[
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
about
Token about
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.000
you
Token you
Feature activation+2.507
get
Token get
Feature activation+2.864
to
Token to
Feature activation+3.144
the
Token the
Feature activation+1.035
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
or
Token or
Feature activation+0.000
contact
Token contact
Feature activation+0.000
s
Tokens
Feature activation+0.000
about
Token about
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
AR
Token AR
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.000
you
Token you
Feature activation+2.507
get
Token get
Feature activation+2.864
to
Token to
Feature activation+3.144
the
Token the
Feature activation+1.035
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
or
Token or
Feature activation+0.000
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000
find
Token find
Feature activation+0.688
on
Token on
Feature activation+0.000
god
Token god
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000
touches
Token touches
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.398
what
Token what
Feature activation+2.554
the
Token the
Feature activation+0.292
groups
Token groups
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.[
Token.[
Feature activation+0.000
d
Tokend
Feature activation+0.000
on
Token on
Feature activation+0.000
AR
Token AR
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.000
you
Token you
Feature activation+2.507
get
Token get
Feature activation+2.864
to
Token to
Feature activation+3.144
the
Token the
Feature activation+1.035
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
re
Tokenre
Feature activation+0.000
still
Token still
Feature activation+0.000
not
Token not
Feature activation+0.000
close
Token close
Feature activation+0.411
to
Token to
Feature activation+1.198
using
Token using
Feature activation+2.214
terms
Token terms
Feature activation+0.227
like
Token like
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
healthy
Tokenhealthy
Feature activation+0.000
's
Token's
Feature activation+0.000
coming
Token coming
Feature activation+0.000
dangerously
Token dangerously
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.306
being
Token being
Feature activation+2.170
a
Token a
Feature activation+0.800
new
Token new
Feature activation+0.000
low
Token low
Feature activation+0.000
including
Token including
Feature activation+0.000
holidays
Token holidays
Feature activation+0.000
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000
touches
Token touches
Feature activation+0.000
are
Token are
Feature activation+0.000

Top DFA by src position
MAX = 6.076

âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.023
Top resid features:
s
Tokens
Feature activation+0.092
Top resid features:
about
Token about
Feature activation-0.025
Top resid features:
as
Token as
Feature activation+0.082
Top resid features:
close
Token close
Feature activation+6.076
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
heaven
Token heaven
Feature activation+0.023
Top resid features:
as
Token as
Feature activation-0.143
Top resid features:
you
Token you
Feature activation+0.158
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
texture
Token texture
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
as
Token as
Feature activation-0.005
Top resid features:
close
Token close
Feature activation+5.412
Top resid features:
as
Token as
Feature activation+0.100
Top resid features:
you
Token you
Feature activation+0.058
Top resid features:
can
Token can
Feature activation+0.006
Top resid features:
get
Token get
Feature activation+0.237
Top resid features:
to
Token to
Feature activation+0.134
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
texture
Token texture
Feature activation+0.059
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
is
Token is
Feature activation-0.013
Top resid features:
as
Token as
Feature activation+0.007
Top resid features:
close
Token close
Feature activation+5.526
Top resid features:
as
Token as
Feature activation+0.099
Top resid features:
you
Token you
Feature activation+0.045
Top resid features:
can
Token can
Feature activation+0.032
Top resid features:
get
Token get
Feature activation+0.197
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
texture
Token texture
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
as
Token as
Feature activation-0.046
Top resid features:
close
Token close
Feature activation+5.015
Top resid features:
as
Token as
Feature activation+0.107
Top resid features:
you
Token you
Feature activation+0.078
Top resid features:
can
Token can
Feature activation-0.005
Top resid features:
get
Token get
Feature activation+0.053
Top resid features:
to
Token to
Feature activation-0.121
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
texture
Token texture
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
close
Token close
Feature activation+5.086
Top resid features:
as
Token as
Feature activation+0.092
Top resid features:
you
Token you
Feature activation+0.148
Top resid features:
can
Token can
Feature activation+0.054
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.035
Top resid features:
texture
Token texture
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
as
Token as
Feature activation-0.022
Top resid features:
close
Token close
Feature activation+5.240
Top resid features:
as
Token as
Feature activation-0.197
Top resid features:
you
Token you
Feature activation+0.121
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.186
Top resid features:
?
Token?
Feature activation+0.060
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation-0.018
Top resid features:
As
TokenAs
Feature activation-0.053
Top resid features:
close
Token close
Feature activation+4.616
Top resid features:
as
Token as
Feature activation+0.181
Top resid features:
you
Token you
Feature activation+0.083
Top resid features:
can
Token can
Feature activation+0.069
Top resid features:
stand
Token stand
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.139
Top resid features:
?
Token?
Feature activation+0.092
Top resid features:
âĢ
Token âĢ
Feature activation+0.003
Top resid features:
ľ
Tokenľ
Feature activation-0.026
Top resid features:
As
TokenAs
Feature activation-0.047
Top resid features:
close
Token close
Feature activation+5.138
Top resid features:
as
Token as
Feature activation-0.322
Top resid features:
you
Token you
Feature activation+0.163
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
stand
Token stand
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.027
Top resid features:
s
Tokens
Feature activation+0.054
Top resid features:
about
Token about
Feature activation+0.009
Top resid features:
as
Token as
Feature activation-0.053
Top resid features:
close
Token close
Feature activation+3.910
Top resid features:
to
Token to
Feature activation+0.138
Top resid features:
heaven
Token heaven
Feature activation+0.128
Top resid features:
as
Token as
Feature activation+0.171
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
working
Token working
Feature activation-0.010
Top resid features:
on
Token on
Feature activation-0.027
Top resid features:
AR
Token AR
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.021
Top resid features:
closer
Token closer
Feature activation+4.371
Top resid features:
you
Token you
Feature activation+0.110
Top resid features:
get
Token get
Feature activation-0.120
Top resid features:
to
Token to
Feature activation-0.116
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wearable
Token wearable
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
about
Token about
Feature activation+0.023
Top resid features:
as
Token as
Feature activation-0.214
Top resid features:
close
Token close
Feature activation+4.912
Top resid features:
to
Token to
Feature activation-0.736
Top resid features:
heaven
Token heaven
Feature activation+0.153
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
working
Token working
Feature activation-0.033
Top resid features:
on
Token on
Feature activation-0.021
Top resid features:
AR
Token AR
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
The
Token The
Feature activation+0.035
Top resid features:
closer
Token closer
Feature activation+4.507
Top resid features:
you
Token you
Feature activation-0.125
Top resid features:
get
Token get
Feature activation-0.316
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wearable
Token wearable
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.070
Top resid features:
Ļ
TokenĻ
Feature activation-0.044
Top resid features:
s
Tokens
Feature activation-0.062
Top resid features:
about
Token about
Feature activation-0.025
Top resid features:
as
Token as
Feature activation+0.082
Top resid features:
close
Token close
Feature activation+3.794
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
heaven
Token heaven
Feature activation+0.022
Top resid features:
as
Token as
Feature activation+0.109
Top resid features:
you
Token you
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
texture
Token texture
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
as
Token as
Feature activation-0.022
Top resid features:
close
Token close
Feature activation+2.957
Top resid features:
as
Token as
Feature activation+0.111
Top resid features:
you
Token you
Feature activation+0.069
Top resid features:
can
Token can
Feature activation-0.020
Top resid features:
get
Token get
Feature activation+0.033
Top resid features:
to
Token to
Feature activation-0.055
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.116
Top resid features:
was
Token was
Feature activation-0.063
Top resid features:
very
Token very
Feature activation+0.066
Top resid features:
close
Token close
Feature activation+4.146
Top resid features:
to
Token to
Feature activation-0.608
Top resid features:
what
Token what
Feature activation+0.158
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
groups
Token groups
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.226
Top resid features:
?
Token?
Feature activation+0.022
Top resid features:
âĢ
Token âĢ
Feature activation+0.010
Top resid features:
ľ
Tokenľ
Feature activation-0.009
Top resid features:
As
TokenAs
Feature activation-0.046
Top resid features:
close
Token close
Feature activation+2.746
Top resid features:
as
Token as
Feature activation+0.309
Top resid features:
you
Token you
Feature activation+0.161
Top resid features:
can
Token can
Feature activation-0.094
Top resid features:
stand
Token stand
Feature activation+0.324
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
working
Token working
Feature activation-0.019
Top resid features:
on
Token on
Feature activation-0.025
Top resid features:
AR
Token AR
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
The
Token The
Feature activation+0.012
Top resid features:
closer
Token closer
Feature activation+3.967
Top resid features:
you
Token you
Feature activation-0.302
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wearable
Token wearable
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
re
Tokenre
Feature activation+0.002
Top resid features:
still
Token still
Feature activation+0.039
Top resid features:
not
Token not
Feature activation+0.023
Top resid features:
close
Token close
Feature activation+3.608
Top resid features:
to
Token to
Feature activation-0.368
Top resid features:
using
Token using
Feature activation+0.128
Top resid features:
terms
Token terms
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
it
Token it
Feature activation+0.282
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
coming
Token coming
Feature activation-0.034
Top resid features:
dangerously
Token dangerously
Feature activation+0.110
Top resid features:
close
Token close
Feature activation+2.959
Top resid features:
to
Token to
Feature activation-0.299
Top resid features:
being
Token being
Feature activation+0.131
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
low
Token low
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
texture
Token texture
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.010
Top resid features:
close
Token close
Feature activation+2.119
Top resid features:
as
Token as
Feature activation+0.095
Top resid features:
you
Token you
Feature activation+0.059
Top resid features:
can
Token can
Feature activation-0.025
Top resid features:
get
Token get
Feature activation+0.037
Top resid features:
to
Token to
Feature activation-0.042
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.50

Head 2: 0.05

Head 3: 0.04

Head 4: 0.03

Head 5: 0.03

Head 6: 0.04

Head 7: 0.08

Head 8: 0.02

Head 9: 0.06

Head 10: 0.02

Head 11: 0.07

Positive logits

vernment1.40

heed1.40

ossible1.25

allowable1.22

ans1.16

reckoning1.15

ceivable1.15

orthy1.14

achievable1.13

permissible1.13

vable1.13

ropri1.12

apon1.12

enough1.11

isman1.11

imation1.10

hn1.10

isable1.10

lihood1.10

vin1.10

Negative logits

-1.61

Coffin-1.51

PLA-1.49

folios-1.31

oys-1.30

-1.27

Shutterstock-1.26

-1.25

UFF-1.23

Offline-1.20

-1.19

Reviewer-1.19

":["-1.19

?????--1.19

の�-1.18

();-1.16

LA-1.16

();-1.15

Blend-1.15

の魔-1.14

INTERVAL 4.692 - 5.214
CONTAINS 0.000%

as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000
find
Token find
Feature activation+0.688
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000

INTERVAL 4.171 - 4.692
CONTAINS 0.001%

that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.653
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
as
Token as
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000

INTERVAL 3.650 - 4.171
CONTAINS 0.000%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.[
Token.[
Feature activation+0.000

INTERVAL 3.128 - 3.650
CONTAINS 0.000%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.000
you
Token you
Feature activation+2.507
get
Token get
Feature activation+2.864
to
Token to
Feature activation+3.144
the
Token the
Feature activation+1.035
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
or
Token or
Feature activation+0.000
contact
Token contact
Feature activation+0.000
about
Token about
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000

INTERVAL 2.607 - 3.128
CONTAINS 0.001%

AR
Token AR
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.000
you
Token you
Feature activation+2.507
get
Token get
Feature activation+2.864
to
Token to
Feature activation+3.144
the
Token the
Feature activation+1.035
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
or
Token or
Feature activation+0.000
s
Tokens
Feature activation+0.000
about
Token about
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+2.816
likely
Token likely
Feature activation+0.000
find
Token find
Feature activation+0.688
on
Token on
Feature activation+0.000
god
Token god
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
you
Token you
Feature activation+4.177
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000
touches
Token touches
Feature activation+0.000

INTERVAL 2.085 - 2.607
CONTAINS 0.001%

re
Tokenre
Feature activation+0.000
still
Token still
Feature activation+0.000
not
Token not
Feature activation+0.000
close
Token close
Feature activation+0.411
to
Token to
Feature activation+1.198
using
Token using
Feature activation+2.214
terms
Token terms
Feature activation+0.227
like
Token like
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
healthy
Tokenhealthy
Feature activation+0.000
's
Token's
Feature activation+0.000
coming
Token coming
Feature activation+0.000
dangerously
Token dangerously
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.306
being
Token being
Feature activation+2.170
a
Token a
Feature activation+0.800
new
Token new
Feature activation+0.000
low
Token low
Feature activation+0.000
including
Token including
Feature activation+0.000
holidays
Token holidays
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.550
you
Token you
Feature activation+3.919
can
Token can
Feature activation+3.930
stand
Token stand
Feature activation+2.516
it
Token it
Feature activation+0.433
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.[
Token.[
Feature activation+0.000
d
Tokend
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.398
what
Token what
Feature activation+2.554
the
Token the
Feature activation+0.292
groups
Token groups
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
can
Token can
Feature activation+4.365
get
Token get
Feature activation+4.910
to
Token to
Feature activation+4.911
a
Token a
Feature activation+4.393
real
Token real
Feature activation+2.738
bill
Token bill
Feature activation+2.125
.
Token.
Feature activation+0.257
The
Token The
Feature activation+0.000
finishing
Token finishing
Feature activation+0.000
touches
Token touches
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 1.564 - 2.085
CONTAINS 0.001%

giving
Token giving
Feature activation+0.000
up
Token up
Feature activation+0.000
set
Token set
Feature activation+0.000
pieces
Token pieces
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+2.079
goal
Token goal
Feature activation+0.375
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
is
Token is
Feature activation+0.000
much
Token much
Feature activation+0.000
closer
Token closer
Feature activation+0.000
to
Token to
Feature activation+0.397
the
Token the
Feature activation+0.530
truth
Token truth
Feature activation+1.652
.
Token.
Feature activation+0.012
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
started
Token started
Feature activation+0.000
have
Token have
Feature activation+0.000
inform
Token inform
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.059
the
Token the
Feature activation+1.616
regime
Token regime
Feature activation+0.418
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
counties
Token counties
Feature activation+0.000
are
Token are
Feature activation+0.000
dangerously
Token dangerously
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
being
Token being
Feature activation+1.596
declared
Token declared
Feature activation+0.337
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
compliance
Token compliance
Feature activation+0.000
with
Token with
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
closest
Token closest
Feature activation+0.000
thing
Token thing
Feature activation+0.000
you
Token you
Feature activation+0.824
can
Token can
Feature activation+1.625
imagine
Token imagine
Feature activation+1.041
to
Token to
Feature activation+1.059
Al
Token Al
Feature activation+0.000
Cap
Token Cap
Feature activation+0.000
one
Tokenone
Feature activation+0.000

INTERVAL 1.043 - 1.564
CONTAINS 0.002%

are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
closest
Token closest
Feature activation+0.000
I
Token I
Feature activation+0.148
've
Token've
Feature activation+1.598
come
Token come
Feature activation+1.070
to
Token to
Feature activation+0.986
a
Token a
Feature activation+1.059
game
Token game
Feature activation+1.258
induced
Token induced
Feature activation+0.000
heart
Token heart
Feature activation+0.000
vote
Token vote
Feature activation+0.000
shy
Token shy
Feature activation+0.000
of
Token of
Feature activation+0.624
passing
Token passing
Feature activation+0.624
a
Token a
Feature activation+0.570
bill
Token bill
Feature activation+1.420
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
about
Token about
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+1.417
heaven
Token heaven
Feature activation+3.073
as
Token as
Feature activation+3.241
you
Token you
Feature activation+5.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
even
Token even
Feature activation+0.000
close
Token close
Feature activation+0.280
to
Token to
Feature activation+1.431
Century
Token Century
Feature activation+0.536
Link
TokenLink
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
U
Token U
Feature activation+0.309
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.526
.
Token.
Feature activation+0.416
government
Token government
Feature activation+0.043
examines
Token examines
Feature activation+1.220
the
Token the
Feature activation+0.671
background
Token background
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000

INTERVAL 0.521 - 1.043
CONTAINS 0.006%

At
TokenAt
Feature activation+0.000
issue
Token issue
Feature activation+0.000
is
Token is
Feature activation+0.000
how
Token how
Feature activation+0.000
closely
Token closely
Feature activation+0.000
the
Token the
Feature activation+0.599
U
Token U
Feature activation+0.309
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.526
.
Token.
Feature activation+0.416
government
Token government
Feature activation+0.043
a
Token a
Feature activation+0.000
roaring
Token roaring
Feature activation+0.000
business
Token business
Feature activation+0.000
with
Token with
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.865
4
Token 4
Feature activation+1.110
,
Token,
Feature activation+0.219
000
Token000
Feature activation+0.000
stores
Token stores
Feature activation+0.000
in
Token in
Feature activation+0.000
s
Tokens
Feature activation+0.000
potential
Token potential
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
close
Token close
Feature activation+0.000
that
Token that
Feature activation+0.859
potential
Token potential
Feature activation+0.000
was
Token was
Feature activation+3.926
to
Token to
Feature activation+4.280
being
Token being
Feature activation+3.154
realized
Token realized
Feature activation+2.990
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
come
Token come
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
close
Token close
Feature activation+1.386
to
Token to
Feature activation+0.638
rival
Token rival
Feature activation+0.253
ing
Tokening
Feature activation+1.082
its
Token its
Feature activation+0.041
mobile
Token mobile
Feature activation+0.000
counterparts
Token counterparts
Feature activation+0.000
fuck
Tokenfuck
Feature activation+0.000
is
Token is
Feature activation+0.000
much
Token much
Feature activation+0.000
closer
Token closer
Feature activation+0.000
to
Token to
Feature activation+0.397
the
Token the
Feature activation+0.530
truth
Token truth
Feature activation+1.652
.
Token.
Feature activation+0.012
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000

INTERVAL 0.000 - 0.521
CONTAINS 99.988%

He
Token He
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
moved
Token moved
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
lane
Token lane
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
room
Token room
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
,
Token,
Feature activation+0.000
looking
Token looking
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
direction
Token direction
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Gandhi
Token Gandhi
Feature activation+0.000
dynasty
Token dynasty
Feature activation+0.000
still
Token still
Feature activation+0.000
holds
Token holds
Feature activation+0.000
together
Token together
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
(
Token (
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
Parenthood
Token Parenthood
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
also
Token also
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
spike
Token spike
Feature activation+0.000
in
Token in
Feature activation+0.000
people
Token people
Feature activation+0.000
making
Token making
Feature activation+0.000
appointments
Token appointments
Feature activation+0.000
them
Token them
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
important
Token important
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
,
Token,
Feature activation+0.000
Muscle
Token Muscle
Feature activation+0.000
Soldier
Token Soldier
Feature activation+0.000
âĢ
TokenâĢ
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 H4.1: (feature 22990)

TOP ACTIVATIONS
MAX = 4.330

how
Token how
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+0.762
felt
Token felt
Feature activation+3.013
so
Token so
Feature activation+4.330
damn
Token damn
Feature activation+0.283
good
Token good
Feature activation+2.676
to
Token to
Feature activation+0.452
read
Token read
Feature activation+0.179
.
Token.
Feature activation+0.000
out
Token out
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.039
prince
Token prince
Feature activation+0.000
generated
Token generated
Feature activation+3.070
so
Token so
Feature activation+4.276
much
Token much
Feature activation+4.160
interest
Token interest
Feature activation+2.474
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.039
prince
Token prince
Feature activation+0.000
generated
Token generated
Feature activation+3.070
so
Token so
Feature activation+4.276
much
Token much
Feature activation+4.160
interest
Token interest
Feature activation+2.474
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
ing
Tokening
Feature activation+0.000
facility
Token facility
Feature activation+0.000
in
Token in
Feature activation+0.000
Edmonton
Token Edmonton
Feature activation+0.000
had
Token had
Feature activation+2.262
such
Token such
Feature activation+4.119
structural
Token structural
Feature activation+0.000
damage
Token damage
Feature activation+0.728
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
about
Token about
Feature activation+0.000
why
Token why
Feature activation+0.000
an
Token an
Feature activation+0.000
error
Token error
Feature activation+0.000
is
Token is
Feature activation+3.666
occurring
Token occurring
Feature activation+4.065
to
Token to
Feature activation+1.062
you
Token you
Feature activation+0.118
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
developer
Token developer
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
your
Token your
Feature activation+0.000
backing
Token backing
Feature activation+0.433
is
Token is
Feature activation+3.391
needed
Token needed
Feature activation+4.031
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
seen
Token seen
Feature activation+0.000
further
Token further
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Nikki
Token Nikki
Feature activation+0.000
Haley
Token Haley
Feature activation+0.000
,
Token,
Feature activation+0.000
chooses
Token chooses
Feature activation+3.999
to
Token to
Feature activation+1.093
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
know
Token know
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.727
topic
Token topic
Feature activation+0.380
is
Token is
Feature activation+3.925
important
Token important
Feature activation+3.966
to
Token to
Feature activation+0.824
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.727
topic
Token topic
Feature activation+0.380
is
Token is
Feature activation+3.925
important
Token important
Feature activation+3.966
to
Token to
Feature activation+0.824
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
presenting
Token presenting
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.251
subject
Token subject
Feature activation+0.063
is
Token is
Feature activation+3.746
important
Token important
Feature activation+3.888
to
Token to
Feature activation+0.579
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
Why
Token Why
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.399
t
Tokent
Feature activation+3.820
baff
Token baff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
version
Token version
Feature activation+0.000
infring
Token infring
Feature activation+0.640
es
Tokenes
Feature activation+3.751
its
Token its
Feature activation+0.978
patents
Token patents
Feature activation+0.000
.
Token.
Feature activation+0.000
Samsung
Token Samsung
Feature activation+0.000
planned
Token planned
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
presenting
Token presenting
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.251
subject
Token subject
Feature activation+0.063
is
Token is
Feature activation+3.746
important
Token important
Feature activation+3.888
to
Token to
Feature activation+0.579
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
ve
Tokenve
Feature activation+3.461
seen
Token seen
Feature activation+3.297
this
Token this
Feature activation+0.935
severe
Token severe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
so
Token so
Feature activation+3.736
early
Token early
Feature activation+1.576
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
weather
Token weather
Feature activation+0.000
we
Token we
Feature activation+0.000
ask
Token ask
Feature activation+0.000
why
Token why
Feature activation+0.000
an
Token an
Feature activation+0.000
artist
Token artist
Feature activation+0.696
shows
Token shows
Feature activation+3.732
life
Token life
Feature activation+1.047
at
Token at
Feature activation+0.781
a
Token a
Feature activation+0.121
remove
Token remove
Feature activation+0.000
and
Token and
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
is
Token is
Feature activation+1.360
the
Token the
Feature activation+0.981
NFL
Token NFL
Feature activation+0.000
taking
Token taking
Feature activation+1.807
so
Token so
Feature activation+3.715
long
Token long
Feature activation+3.708
to
Token to
Feature activation+0.000
announce
Token announce
Feature activation+0.000
its
Token its
Feature activation+0.000
decision
Token decision
Feature activation+0.000
is
Token is
Feature activation+1.360
the
Token the
Feature activation+0.981
NFL
Token NFL
Feature activation+0.000
taking
Token taking
Feature activation+1.807
so
Token so
Feature activation+3.715
long
Token long
Feature activation+3.708
to
Token to
Feature activation+0.000
announce
Token announce
Feature activation+0.000
its
Token its
Feature activation+0.000
decision
Token decision
Feature activation+0.000
?
Token?
Feature activation+0.000
Email
Token Email
Feature activation+0.005
Fil
Token Fil
Feature activation+0.000
ters
Tokenters
Feature activation+1.552
are
Token are
Feature activation+2.673
required
Token required
Feature activation+3.346
in
Token in
Feature activation+3.671
the
Token the
Feature activation+3.319
First
Token First
Feature activation+0.383
Place
Token Place
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
about
Token about
Feature activation+0.000
why
Token why
Feature activation+0.000
an
Token an
Feature activation+0.000
error
Token error
Feature activation+0.000
is
Token is
Feature activation+3.666
occurring
Token occurring
Feature activation+4.065
to
Token to
Feature activation+1.062
you
Token you
Feature activation+0.118
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
know
Token know
Feature activation+0.000
was
Token was
Feature activation+0.000
why
Token why
Feature activation+0.000
it
Token it
Feature activation+0.803
was
Token was
Feature activation+2.251
such
Token such
Feature activation+3.615
a
Token a
Feature activation+3.026
big
Token big
Feature activation+1.526
deal
Token deal
Feature activation+2.760
in
Token in
Feature activation+0.479
Saudi
Token Saudi
Feature activation+0.000

Top DFA by src position
MAX = 5.155

flow
Token flow
Feature activation+0.013
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
how
Token how
Feature activation-0.059
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
why
Token why
Feature activation+5.116
Top resid features:
they
Token they
Feature activation+0.128
Top resid features:
felt
Token felt
Feature activation+0.403
Top resid features:
so
Token so
Feature activation+0.201
Top resid features:
damn
Token damn
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
island
Token island
Feature activation+0.002
Top resid features:
nation
Token nation
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
find
Token find
Feature activation-0.005
Top resid features:
out
Token out
Feature activation+0.042
Top resid features:
why
Token why
Feature activation+5.002
Top resid features:
the
Token the
Feature activation+0.112
Top resid features:
prince
Token prince
Feature activation+0.044
Top resid features:
generated
Token generated
Feature activation+0.340
Top resid features:
so
Token so
Feature activation+0.265
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
island
Token island
Feature activation-0.001
Top resid features:
nation
Token nation
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
find
Token find
Feature activation-0.003
Top resid features:
out
Token out
Feature activation+0.010
Top resid features:
why
Token why
Feature activation+5.155
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
prince
Token prince
Feature activation+0.027
Top resid features:
generated
Token generated
Feature activation-0.015
Top resid features:
so
Token so
Feature activation+0.377
Top resid features:
much
Token much
Feature activation+0.140
Top resid features:
councillors
Token councillors
Feature activation-0.009
Top resid features:
are
Token are
Feature activation-0.017
Top resid features:
demanding
Token demanding
Feature activation+0.012
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
know
Token know
Feature activation+0.047
Top resid features:
why
Token why
Feature activation+4.718
Top resid features:
a
Token a
Feature activation+0.055
Top resid features:
key
Token key
Feature activation+0.058
Top resid features:
compost
Token compost
Feature activation+0.009
Top resid features:
ing
Tokening
Feature activation+0.009
Top resid features:
facility
Token facility
Feature activation+0.105
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
internal
Token internal
Feature activation+0.004
Top resid features:
knowledge
Token knowledge
Feature activation+0.054
Top resid features:
about
Token about
Feature activation+0.021
Top resid features:
why
Token why
Feature activation+4.919
Top resid features:
an
Token an
Feature activation+0.019
Top resid features:
error
Token error
Feature activation+0.160
Top resid features:
is
Token is
Feature activation+0.359
Top resid features:
occurring
Token occurring
Feature activation+0.086
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
A
Token A
Feature activation-0.010
Top resid features:
full
Token full
Feature activation-0.000
Top resid features:
breakdown
Token breakdown
Feature activation+0.023
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
why
Token why
Feature activation+4.564
Top resid features:
your
Token your
Feature activation+0.034
Top resid features:
backing
Token backing
Feature activation+0.219
Top resid features:
is
Token is
Feature activation+0.460
Top resid features:
needed
Token needed
Feature activation+0.316
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
I
TokenI
Feature activation-0.021
Top resid features:
often
Token often
Feature activation+0.014
Top resid features:
wonder
Token wonder
Feature activation-0.021
Top resid features:
why
Token why
Feature activation+4.343
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
person
Token person
Feature activation+0.118
Top resid features:
of
Token of
Feature activation+0.135
Top resid features:
color
Token color
Feature activation+0.050
Top resid features:
,
Token,
Feature activation+0.206
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
hearing
Token hearing
Feature activation-0.102
Top resid features:
you
Token you
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
know
Token know
Feature activation+0.073
Top resid features:
why
Token why
Feature activation+4.615
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
topic
Token topic
Feature activation+0.315
Top resid features:
is
Token is
Feature activation+0.386
Top resid features:
important
Token important
Feature activation+0.172
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.001
Top resid features:
hearing
Token hearing
Feature activation-0.081
Top resid features:
you
Token you
Feature activation-0.022
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
know
Token know
Feature activation+0.020
Top resid features:
why
Token why
Feature activation+4.873
Top resid features:
the
Token the
Feature activation+0.134
Top resid features:
topic
Token topic
Feature activation+0.534
Top resid features:
is
Token is
Feature activation+0.055
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
authority
Token authority
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
After
TokenAfter
Feature activation+0.019
Top resid features:
presenting
Token presenting
Feature activation+0.005
Top resid features:
why
Token why
Feature activation+4.296
Top resid features:
the
Token the
Feature activation+0.135
Top resid features:
subject
Token subject
Feature activation+0.243
Top resid features:
is
Token is
Feature activation+0.497
Top resid features:
important
Token important
Feature activation+0.200
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
just
Token just
Feature activation-0.001
Top resid features:
about
Token about
Feature activation+0.011
Top resid features:
any
Token any
Feature activation-0.006
Top resid features:
reason
Token reason
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Why
Token Why
Feature activation+4.543
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
don
Token don
Feature activation+0.142
Top resid features:
âĢ
TokenâĢ
Feature activation+0.047
Top resid features:
Ļ
TokenĻ
Feature activation+0.455
Top resid features:
t
Tokent
Feature activation+0.196
Top resid features:
presented
Token presented
Feature activation+0.021
Top resid features:
no
Token no
Feature activation-0.009
Top resid features:
new
Token new
Feature activation-0.032
Top resid features:
evidence
Token evidence
Feature activation+0.035
Top resid features:
detailing
Token detailing
Feature activation+0.037
Top resid features:
why
Token why
Feature activation+4.179
Top resid features:
the
Token the
Feature activation+0.174
Top resid features:
new
Token new
Feature activation+0.098
Top resid features:
version
Token version
Feature activation+0.173
Top resid features:
infring
Token infring
Feature activation+0.507
Top resid features:
es
Tokenes
Feature activation+0.188
Top resid features:
authority
Token authority
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
After
TokenAfter
Feature activation+0.013
Top resid features:
presenting
Token presenting
Feature activation+0.018
Top resid features:
why
Token why
Feature activation+4.724
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
subject
Token subject
Feature activation+0.391
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.009
Top resid features:
ľ
Tokenľ
Feature activation-0.013
Top resid features:
Why
TokenWhy
Feature activation+4.691
Top resid features:
we
Token we
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.030
Top resid features:
Ļ
TokenĻ
Feature activation+0.035
Top resid features:
ve
Tokenve
Feature activation+0.047
Top resid features:
seen
Token seen
Feature activation-0.071
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.317
Top resid features:
ism
Tokenism
Feature activation+0.012
Top resid features:
can
Token can
Feature activation-0.022
Top resid features:
we
Token we
Feature activation-0.103
Top resid features:
ask
Token ask
Feature activation-0.021
Top resid features:
why
Token why
Feature activation+4.623
Top resid features:
an
Token an
Feature activation+0.048
Top resid features:
artist
Token artist
Feature activation+0.669
Top resid features:
shows
Token shows
Feature activation+0.025
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.283
Top resid features:
.
Token.
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Why
TokenWhy
Feature activation+4.288
Top resid features:
is
Token is
Feature activation+0.127
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
NFL
Token NFL
Feature activation+0.011
Top resid features:
taking
Token taking
Feature activation+0.509
Top resid features:
so
Token so
Feature activation+0.280
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.294
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Why
TokenWhy
Feature activation+4.407
Top resid features:
is
Token is
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
NFL
Token NFL
Feature activation+0.026
Top resid features:
taking
Token taking
Feature activation+0.135
Top resid features:
so
Token so
Feature activation+0.028
Top resid features:
providers
Token providers
Feature activation+0.000
Top resid features:
too
Token too
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Why
TokenWhy
Feature activation+4.125
Top resid features:
Email
Token Email
Feature activation+0.078
Top resid features:
Fil
Token Fil
Feature activation+0.005
Top resid features:
ters
Tokenters
Feature activation+0.126
Top resid features:
are
Token are
Feature activation+0.081
Top resid features:
required
Token required
Feature activation+0.586
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
internal
Token internal
Feature activation+0.007
Top resid features:
knowledge
Token knowledge
Feature activation+0.017
Top resid features:
about
Token about
Feature activation+0.017
Top resid features:
why
Token why
Feature activation+4.737
Top resid features:
an
Token an
Feature activation+0.003
Top resid features:
error
Token error
Feature activation+0.489
Top resid features:
is
Token is
Feature activation-0.022
Top resid features:
occurring
Token occurring
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.006
Top resid features:
wanted
Token wanted
Feature activation-0.036
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
know
Token know
Feature activation+0.091
Top resid features:
was
Token was
Feature activation-0.032
Top resid features:
why
Token why
Feature activation+4.648
Top resid features:
it
Token it
Feature activation+0.084
Top resid features:
was
Token was
Feature activation+0.415
Top resid features:
such
Token such
Feature activation+0.261
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.49

Head 2: 0.04

Head 3: 0.07

Head 4: 0.02

Head 5: 0.03

Head 6: 0.05

Head 7: 0.10

Head 8: 0.02

Head 9: 0.07

Head 10: 0.01

Head 11: 0.07

Positive logits

prematurely1.42

differently1.39

ependent1.39

incorrectly1.35

wrongly1.29

vs1.29

rush1.28

Matters1.27

owa1.25

iky1.24

so1.24

Canaver1.23

disproportionately1.23

Hebdo1.22

stru1.21

chester1.20

hiatus1.20

blindly1.19

rush1.19

?,1.18

Negative logits

��-1.73

OLOGY-1.63

ATER-1.47

ydia-1.36

Disk-1.32

ailability-1.27

ATING-1.24

ANC-1.24

consolation-1.23

ICA-1.20

OURCE-1.18

srfAttach-1.18

feasibility-1.17

acer-1.17

ntil-1.17

ILCS-1.16

CLASSIFIED-1.16

ylan-1.15

\\\\\\\\\\\\\\\\-1.14

OTO-1.14

INTERVAL 3.897 - 4.330
CONTAINS 0.001%

ing
Tokening
Feature activation+0.000
facility
Token facility
Feature activation+0.000
in
Token in
Feature activation+0.000
Edmonton
Token Edmonton
Feature activation+0.000
had
Token had
Feature activation+2.262
such
Token such
Feature activation+4.119
structural
Token structural
Feature activation+0.000
damage
Token damage
Feature activation+0.728
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
your
Token your
Feature activation+0.000
backing
Token backing
Feature activation+0.433
is
Token is
Feature activation+3.391
needed
Token needed
Feature activation+4.031
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
seen
Token seen
Feature activation+0.000
further
Token further
Feature activation+0.000
down
Token down
Feature activation+0.000
out
Token out
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.039
prince
Token prince
Feature activation+0.000
generated
Token generated
Feature activation+3.070
so
Token so
Feature activation+4.276
much
Token much
Feature activation+4.160
interest
Token interest
Feature activation+2.474
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
about
Token about
Feature activation+0.000
why
Token why
Feature activation+0.000
an
Token an
Feature activation+0.000
error
Token error
Feature activation+0.000
is
Token is
Feature activation+3.666
occurring
Token occurring
Feature activation+4.065
to
Token to
Feature activation+1.062
you
Token you
Feature activation+0.118
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
developer
Token developer
Feature activation+0.000
how
Token how
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+0.762
felt
Token felt
Feature activation+3.013
so
Token so
Feature activation+4.330
damn
Token damn
Feature activation+0.283
good
Token good
Feature activation+2.676
to
Token to
Feature activation+0.452
read
Token read
Feature activation+0.179
.
Token.
Feature activation+0.000

INTERVAL 3.464 - 3.897
CONTAINS 0.002%

know
Token know
Feature activation+0.000
was
Token was
Feature activation+0.000
why
Token why
Feature activation+0.000
it
Token it
Feature activation+0.803
was
Token was
Feature activation+2.251
such
Token such
Feature activation+3.615
a
Token a
Feature activation+3.026
big
Token big
Feature activation+1.526
deal
Token deal
Feature activation+2.760
in
Token in
Feature activation+0.479
Saudi
Token Saudi
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
video
Token video
Feature activation+0.000
was
Token was
Feature activation+2.434
so
Token so
Feature activation+3.242
popular
Token popular
Feature activation+3.575
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
we
Token we
Feature activation+0.000
we
Token we
Feature activation+0.000
ask
Token ask
Feature activation+0.000
why
Token why
Feature activation+0.000
an
Token an
Feature activation+0.000
artist
Token artist
Feature activation+0.696
shows
Token shows
Feature activation+3.732
life
Token life
Feature activation+1.047
at
Token at
Feature activation+0.781
a
Token a
Feature activation+0.121
remove
Token remove
Feature activation+0.000
and
Token and
Feature activation+0.000
Why
Token Why
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.399
t
Tokent
Feature activation+3.820
baff
Token baff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Email
Token Email
Feature activation+0.005
Fil
Token Fil
Feature activation+0.000
ters
Tokenters
Feature activation+1.552
are
Token are
Feature activation+2.673
required
Token required
Feature activation+3.346
in
Token in
Feature activation+3.671
the
Token the
Feature activation+3.319
First
Token First
Feature activation+0.383
Place
Token Place
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.031 - 3.464
CONTAINS 0.003%

why
Token why
Feature activation+0.000
a
Token a
Feature activation+0.000
previous
Token previous
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
didn
Token didn
Feature activation+2.083
't
Token't
Feature activation+3.228
detect
Token detect
Feature activation+0.320
problems
Token problems
Feature activation+0.000
sooner
Token sooner
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
understand
Token understand
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
video
Token video
Feature activation+0.000
was
Token was
Feature activation+2.434
so
Token so
Feature activation+3.242
popular
Token popular
Feature activation+3.575
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.561
ve
Tokenve
Feature activation+3.461
seen
Token seen
Feature activation+3.297
this
Token this
Feature activation+0.935
severe
Token severe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
so
Token so
Feature activation+3.736
early
Token early
Feature activation+1.576
breakdown
Token breakdown
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
your
Token your
Feature activation+0.000
backing
Token backing
Feature activation+0.433
is
Token is
Feature activation+3.391
needed
Token needed
Feature activation+4.031
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
seen
Token seen
Feature activation+0.000
further
Token further
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.561
ve
Tokenve
Feature activation+3.461
seen
Token seen
Feature activation+3.297
this
Token this
Feature activation+0.935
severe
Token severe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
so
Token so
Feature activation+3.736

INTERVAL 2.598 - 3.031
CONTAINS 0.007%

wonder
Token wonder
Feature activation+0.000
why
Token why
Feature activation+0.000
people
Token people
Feature activation+1.253
seem
Token seem
Feature activation+2.515
to
Token to
Feature activation+1.413
think
Token think
Feature activation+2.872
that
Token that
Feature activation+1.446
symbolic
Token symbolic
Feature activation+0.000
gestures
Token gestures
Feature activation+0.000
translate
Token translate
Feature activation+0.103
into
Token into
Feature activation+0.163
reasons
Token reasons
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
talk
Token talk
Feature activation+1.434
so
Token so
Feature activation+2.313
much
Token much
Feature activation+2.814
,
Token,
Feature activation+0.179
talk
Token talk
Feature activation+0.000
so
Token so
Feature activation+0.000
loud
Token loud
Feature activation+0.000
when
Token when
Feature activation+0.253
of
Token of
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
why
Tokenwhy
Feature activation+0.000
things
Token things
Feature activation+0.216
tend
Token tend
Feature activation+2.193
to
Token to
Feature activation+2.631
be
Token be
Feature activation+2.165
much
Token much
Feature activation+1.583
less
Token less
Feature activation+0.502
lively
Token lively
Feature activation+0.022
on
Token on
Feature activation+0.087
the
Token the
Feature activation+0.000
how
Token how
Feature activation+0.000
of
Token of
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+0.762
felt
Token felt
Feature activation+3.013
so
Token so
Feature activation+4.330
damn
Token damn
Feature activation+0.283
good
Token good
Feature activation+2.676
to
Token to
Feature activation+0.452
read
Token read
Feature activation+0.179
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
State
Token State
Feature activation+0.000
Government
Token Government
Feature activation+0.000
made
Token made
Feature activation+2.652
fluor
Token fluor
Feature activation+0.117
idation
Tokenidation
Feature activation+0.870
mandatory
Token mandatory
Feature activation+2.152
if
Token if
Feature activation+1.129
there
Token there
Feature activation+0.000

INTERVAL 2.165 - 2.598
CONTAINS 0.007%

mean
Token mean
Feature activation+0.000
,
Token,
Feature activation+0.000
why
Token why
Feature activation+0.000
do
Token do
Feature activation+0.174
we
Token we
Feature activation+1.872
need
Token need
Feature activation+2.217
to
Token to
Feature activation+1.556
make
Token make
Feature activation+0.000
Santa
Token Santa
Feature activation+0.000
Claus
Token Claus
Feature activation+0.000
gay
Token gay
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
questioned
Token questioned
Feature activation+0.000
why
Token why
Feature activation+0.000
he
Token he
Feature activation+0.666
was
Token was
Feature activation+2.255
being
Token being
Feature activation+2.526
detained
Token detained
Feature activation+2.979
,
Token,
Feature activation+0.613
at
Token at
Feature activation+0.143
one
Token one
Feature activation+0.000
congress
Token congress
Feature activation+0.000
-
Token-
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+0.994
weren
Token weren
Feature activation+2.203
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.946
t
Tokent
Feature activation+2.537
reflecting
Token reflecting
Feature activation+0.907
the
Token the
Feature activation+0.000
can
Token can
Feature activation+0.000
understand
Token understand
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
video
Token video
Feature activation+0.000
was
Token was
Feature activation+2.434
so
Token so
Feature activation+3.242
popular
Token popular
Feature activation+3.575
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
it
Token it
Feature activation+0.000
Doesn
Token Doesn
Feature activation+0.659
't
Token't
Feature activation+2.386
Make
Token Make
Feature activation+0.000
Sense
Token Sense
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.732 - 2.165
CONTAINS 0.010%

Dash
Token Dash
Feature activation+0.747
upgraded
Token upgraded
Feature activation+1.719
its
Token its
Feature activation+1.223
software
Token software
Feature activation+0.061
in
Token in
Feature activation+1.285
order
Token order
Feature activation+1.835
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.000
network
Token network
Feature activation+0.000
with
Token with
Feature activation+0.000
why
Token why
Feature activation+0.000
she
Token she
Feature activation+0.551
decided
Token decided
Feature activation+3.110
to
Token to
Feature activation+2.481
focus
Token focus
Feature activation+1.911
on
Token on
Feature activation+1.845
the
Token the
Feature activation+0.749
sexual
Token sexual
Feature activation+0.000
behaviors
Token behaviors
Feature activation+0.135
of
Token of
Feature activation+0.000
daughters
Token daughters
Feature activation+0.000
out
Token out
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+1.156
will
Token will
Feature activation+1.860
be
Token be
Feature activation+1.318
taking
Token taking
Feature activation+2.103
part
Token part
Feature activation+1.641
in
Token in
Feature activation+1.125
the
Token the
Feature activation+1.543
cent
Token cent
Feature activation+0.000
enary
Tokenenary
Feature activation+0.000
tax
Token tax
Feature activation+0.000
reform
Token reform
Feature activation+0.000
and
Token and
Feature activation+0.000
tax
Token tax
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
are
Token are
Feature activation+2.097
not
Token not
Feature activation+2.034
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
explain
Token explain
Feature activation+0.000
why
Token why
Feature activation+0.000
big
Token big
Feature activation+0.000
banks
Token banks
Feature activation+0.212
shouldn
Token shouldn
Feature activation+2.392
't
Token't
Feature activation+1.941
be
Token be
Feature activation+0.138
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.299 - 1.732
CONTAINS 0.013%

continues
Token continues
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
do
Token do
Feature activation+1.327
you
Token you
Feature activation+2.065
feel
Token feel
Feature activation+2.988
that
Token that
Feature activation+1.839
we
Token we
Feature activation+0.268
are
Token are
Feature activation+0.454
this
Token this
Feature activation+0.760
late
Token late
Feature activation+0.000
into
Token into
Feature activation+0.000
bracket
Token bracket
Feature activation+0.000
is
Token is
Feature activation+0.892
different
Token different
Feature activation+1.441
from
Token from
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
why
Tokenwhy
Feature activation+0.000
-
Token-
Feature activation+0.000
don
Tokendon
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.113
t
Tokent
Feature activation+1.521
-
Token-
Feature activation+0.000
we
Tokenwe
Feature activation+0.513
-
Token-
Feature activation+0.000
have
Tokenhave
Feature activation+1.065
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.399
t
Tokent
Feature activation+3.820
baff
Token baff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
DOES
Token DOES
Feature activation+0.653
H
Token H
Feature activation+0.203
ILL
TokenILL
Feature activation+0.502
ARY
TokenARY
Feature activation+1.005
CL
Token CL
Feature activation+1.080
INTON
TokenINTON
Feature activation+1.677
ALWAYS
Token ALWAYS
Feature activation+0.532
C
Token C
Feature activation+0.401
ACK
TokenACK
Feature activation+0.000
LE
TokenLE
Feature activation+0.000
WITH
Token WITH
Feature activation+0.472

INTERVAL 0.866 - 1.299
CONTAINS 0.018%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
talk
Token talk
Feature activation+1.359
about
Token about
Feature activation+1.111
sustainable
Token sustainable
Feature activation+0.000
growth
Token growth
Feature activation+0.150
right
Token right
Feature activation+0.628
now
Token now
Feature activation+0.645
?
Token?
Feature activation+0.000
why
Token why
Feature activation+0.000
rape
Token rape
Feature activation+0.000
is
Token is
Feature activation+0.973
so
Token so
Feature activation+3.175
widely
Token widely
Feature activation+2.026
accepted
Token accepted
Feature activation+1.265
.
Token.
Feature activation+0.000
Un
Token Un
Feature activation+0.000
acceptable
Tokenacceptable
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
election
Token election
Feature activation+0.000
are
Token are
Feature activation+0.000
finding
Token finding
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.463
stay
Token stay
Feature activation+1.205
home
Token home
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Who
Token Who
Feature activation+0.000
's
Token's
Feature activation+0.000
why
Token why
Feature activation+0.000
we
Token we
Feature activation+0.000
made
Token made
Feature activation+0.121
the
Token the
Feature activation+0.435
decision
Token decision
Feature activation+1.089
to
Token to
Feature activation+0.000
suspend
Token suspend
Feature activation+0.000
processing
Token processing
Feature activation+0.000
organ
Token organ
Feature activation+0.000
ics
Tokenics
Feature activation+0.000
this
Token this
Feature activation+0.196
item
Token item
Feature activation+0.079
might
Token might
Feature activation+2.050
not
Token not
Feature activation+1.312
work
Token work
Feature activation+0.799
within
Token within
Feature activation+1.149
Overwatch
Token Overwatch
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Current
TokenCurrent
Feature activation+0.000

INTERVAL 0.433 - 0.866
CONTAINS 0.028%

the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.328
is
Token is
Feature activation+0.849
now
Token now
Feature activation+1.356
hearing
Token hearing
Feature activation+0.000
about
Token about
Feature activation+0.596
this
Token this
Feature activation+0.000
change
Token change
Feature activation+0.000
of
Token of
Feature activation+0.000
heart
Token heart
Feature activation+0.000
is
Token is
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.653
hired
Token hired
Feature activation+0.033
us
Token us
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
the
Token the
Feature activation+0.000
ISPs
Token ISPs
Feature activation+0.000
filter
Token filter
Feature activation+0.441
emails
Token emails
Feature activation+0.027
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ca
TokenCa
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
why
Token why
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.313
encouraged
Token encouraged
Feature activation+0.439
to
Token to
Feature activation+0.000
only
Token only
Feature activation+0.000
speak
Token speak
Feature activation+0.000
once
Token once
Feature activation+0.000
you
Token you
Feature activation+0.000
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
questioned
Token questioned
Feature activation+0.000
why
Token why
Feature activation+0.000
he
Token he
Feature activation+0.666
was
Token was
Feature activation+2.255
being
Token being
Feature activation+2.526
detained
Token detained
Feature activation+2.979
,
Token,
Feature activation+0.613
at
Token at
Feature activation+0.143

INTERVAL 0.000 - 0.433
CONTAINS 99.912%

journal
Token journal
Feature activation+0.000
Nature
Token Nature
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
asteroid
Token asteroid
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
Se
Token Se
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
sofa
Token sofa
Feature activation+0.000
across
Token across
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
he
Token he
Feature activation+0.000
believed
Token believed
Feature activation+0.000
A
TokenA
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
how
Token how
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
shaved
Token shaved
Feature activation+0.000
while
Token while
Feature activation+0.000
striking
Token striking
Feature activation+0.000
a
Token a
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
security
Token security
Feature activation+0.000
barric
Token barric
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
drove
Token drove
Feature activation+0.000
through
Token through
Feature activation+0.000
an
Token an
Feature activation+0.000
't
Token't
Feature activation+0.000
really
Token really
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
strike
Tokenstrike
Feature activation+0.000
"
Token"
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
taking
Token taking
Feature activation+0.000
an
Token an
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H4.1: (feature 6897)

TOP ACTIVATIONS
MAX = 4.124

most
Token most
Feature activation+0.000
brutal
Token brutal
Feature activation+0.000
K
Token K
Feature activation+1.767
ombat
Tokenombat
Feature activation+0.898
experience
Token experience
Feature activation+2.427
ever
Token ever
Feature activation+4.105
,
Token,
Feature activation+0.000
offering
Token offering
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
fully
Token fully
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
he
Token he
Feature activation+1.918
ist
Tokenist
Feature activation+0.310
in
Token in
Feature activation+3.407
the
Token the
Feature activation+1.999
history
Token history
Feature activation+3.958
of
Token of
Feature activation+0.000
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
insane
Token insane
Feature activation+0.000
months
Token months
Feature activation+1.640
EVER
Token EVER
Feature activation+3.893
that
Token that
Feature activation+1.671
has
Token has
Feature activation+3.895
been
Token been
Feature activation+1.604
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
crazy
Token crazy
Feature activation+0.000
and
Token and
Feature activation+0.000
insane
Token insane
Feature activation+0.000
months
Token months
Feature activation+1.640
EVER
Token EVER
Feature activation+3.893
that
Token that
Feature activation+1.671
has
Token has
Feature activation+3.895
been
Token been
Feature activation+1.604
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
celebrated
Token celebrated
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
to
Token to
Feature activation+2.150
ever
Token ever
Feature activation+3.823
work
Token work
Feature activation+2.841
in
Token in
Feature activation+0.116
the
Token the
Feature activation+0.000
medium
Token medium
Feature activation+1.792
,
Token,
Feature activation+0.000
gest
Tokengest
Feature activation+0.000
act
Token act
Feature activation+2.209
of
Token of
Feature activation+1.523
privat
Token privat
Feature activation+0.753
isation
Tokenisation
Feature activation+1.542
ever
Token ever
Feature activation+3.806
seen
Token seen
Feature activation+3.374
in
Token in
Feature activation+2.126
the
Token the
Feature activation+0.708
NHS
Token NHS
Feature activation+0.000
",
Token",
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
GSL
Token GSL
Feature activation+1.577
finals
Token finals
Feature activation+1.262
ever
Token ever
Feature activation+3.804
has
Token has
Feature activation+0.666
bitten
Token bitten
Feature activation+0.066
the
Token the
Feature activation+0.000
dust
Token dust
Feature activation+0.000
.
Token.
Feature activation+0.000
paid
Token paid
Feature activation+0.000
Pac
Token Pac
Feature activation+0.285
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.151
assistant
Token assistant
Feature activation+0.470
EVER
Token EVER
Feature activation+3.745
by
Token by
Feature activation+2.369
around
Token around
Feature activation+0.618
500
Token 500
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
The
Token The
Feature activation+0.000
Most
Token Most
Feature activation+0.000
Meta
Token Meta
Feature activation+0.562
Sn
Token Sn
Feature activation+0.426
ack
Tokenack
Feature activation+2.482
Ever
Token Ever
Feature activation+3.738
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
honest
Token honest
Feature activation+0.000
statement
Token statement
Feature activation+2.987
I
Token I
Feature activation+3.118
can
Token can
Feature activation+3.728
muster
Token muster
Feature activation+2.492
about
Token about
Feature activation+1.964
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Creat
TokenCreat
Feature activation+0.000
akings
Tokenakings
Feature activation+1.342
you
Token you
Feature activation+1.052
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.039
ever
Token ever
Feature activation+3.713
face
Token face
Feature activation+0.475
in
Token in
Feature activation+0.140
a
Token a
Feature activation+0.000
PC
Token PC
Feature activation+0.000
flight
Token flight
Feature activation+0.000
sweeping
Token sweeping
Feature activation+0.246
voter
Token voter
Feature activation+0.047
-
Token-
Feature activation+0.000
supp
Tokensupp
Feature activation+0.000
ression
Tokenression
Feature activation+0.621
law
Token law
Feature activation+3.686
in
Token in
Feature activation+2.669
the
Token the
Feature activation+2.625
nation
Token nation
Feature activation+3.451
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
single
Token single
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
tweet
Token tweet
Feature activation+0.106
in
Token in
Feature activation+1.713
the
Token the
Feature activation+2.203
history
Token history
Feature activation+3.680
of
Token of
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
.
Token.
Feature activation+0.006
Do
Token Do
Feature activation+0.000
you
Token you
Feature activation+0.000
-
Token-
Feature activation+0.000
written
Tokenwritten
Feature activation+1.279
shows
Token shows
Feature activation+0.000
in
Token in
Feature activation+1.179
television
Token television
Feature activation+0.740
history
Token history
Feature activation+3.657
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
wards
Tokenwards
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
strike
Token strike
Feature activation+0.407
in
Token in
Feature activation+2.991
the
Token the
Feature activation+2.227
history
Token history
Feature activation+3.611
of
Token of
Feature activation+0.064
the
Token the
Feature activation+0.000
fast
Token fast
Feature activation+0.000
-
Token-
Feature activation+0.000
food
Tokenfood
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ils
Tokenils
Feature activation+0.189
the
Token the
Feature activation+1.766
world
Token world
Feature activation+1.380
has
Token has
Feature activation+2.933
ever
Token ever
Feature activation+3.603
seen
Token seen
Feature activation+1.691
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
turnout
Token turnout
Feature activation+0.154
of
Token of
Feature activation+1.955
Latinos
Token Latinos
Feature activation+0.153
in
Token in
Feature activation+1.371
electoral
Token electoral
Feature activation+0.364
history
Token history
Feature activation+3.595
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
gru
Token gru
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
est
Tokenest
Feature activation+0.000
voice
Token voice
Feature activation+1.447
you
Token you
Feature activation+1.715
can
Token can
Feature activation+3.523
.
Token.
Feature activation+0.000
SC
Token SC
Feature activation+0.000
OTT
TokenOTT
Feature activation+0.000
CHAR
Token CHAR
Feature activation+0.000
LES
TokenLES
Feature activation+0.000
offered
Token offered
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.190
lease
Token lease
Feature activation+0.776
sale
Token sale
Feature activation+1.543
ever
Token ever
Feature activation+3.508
in
Token in
Feature activation+1.356
the
Token the
Feature activation+0.705
National
Token National
Feature activation+0.000
Petroleum
Token Petroleum
Feature activation+0.000
Reserve
Token Reserve
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
international
Token international
Feature activation+0.448
operations
Token operations
Feature activation+0.000
to
Token to
Feature activation+2.491
date
Token date
Feature activation+3.469
against
Token against
Feature activation+0.613
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.045
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 4.784

new
Token new
Feature activation+0.017
Top resid features:
gameplay
Token gameplay
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
deliver
Token deliver
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
most
Token most
Feature activation+4.447
Top resid features:
brutal
Token brutal
Feature activation+0.062
Top resid features:
K
Token K
Feature activation+0.020
Top resid features:
ombat
Tokenombat
Feature activation+0.012
Top resid features:
experience
Token experience
Feature activation+0.176
Top resid features:
ever
Token ever
Feature activation-0.014
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.004
Top resid features:
had
Tokenhad
Feature activation+0.014
Top resid features:
just
Token just
Feature activation+0.008
Top resid features:
committed
Token committed
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
biggest
Token biggest
Feature activation+4.784
Top resid features:
he
Token he
Feature activation+0.009
Top resid features:
ist
Tokenist
Feature activation-0.013
Top resid features:
in
Token in
Feature activation-0.131
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
history
Token history
Feature activation-0.114
Top resid features:
just
Token just
Feature activation+0.006
Top resid features:
finished
Token finished
Feature activation-0.001
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+4.216
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
ctic
Tokenctic
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
crazy
Token crazy
Feature activation+0.034
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
just
Token just
Feature activation+0.007
Top resid features:
finished
Token finished
Feature activation-0.039
Top resid features:
one
Token one
Feature activation+0.007
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
most
Token most
Feature activation+4.502
Top resid features:
he
Token he
Feature activation+0.015
Top resid features:
ctic
Tokenctic
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
crazy
Token crazy
Feature activation+0.040
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
movie
Token movie
Feature activation-0.003
Top resid features:
from
Token from
Feature activation+0.022
Top resid features:
one
Token one
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+4.219
Top resid features:
celebrated
Token celebrated
Feature activation+0.078
Top resid features:
filmmakers
Token filmmakers
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.161
Top resid features:
ever
Token ever
Feature activation-0.038
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
resulting
Token resulting
Feature activation+0.003
Top resid features:
in
Token in
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
"
Token "
Feature activation+0.109
Top resid features:
big
Tokenbig
Feature activation+0.029
Top resid features:
gest
Tokengest
Feature activation+4.194
Top resid features:
act
Token act
Feature activation+0.028
Top resid features:
of
Token of
Feature activation-0.013
Top resid features:
privat
Token privat
Feature activation+0.037
Top resid features:
isation
Tokenisation
Feature activation+0.151
Top resid features:
ever
Token ever
Feature activation-0.096
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
both
Token both
Feature activation+0.026
Top resid features:
players
Token players
Feature activation-0.010
Top resid features:
from
Token from
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
greatest
Token greatest
Feature activation+4.357
Top resid features:
GSL
Token GSL
Feature activation+0.007
Top resid features:
finals
Token finals
Feature activation+0.036
Top resid features:
ever
Token ever
Feature activation-0.036
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
bitten
Token bitten
Feature activation+0.000
Top resid features:
supp
Tokensupp
Feature activation+0.000
Top resid features:
osed
Tokenosed
Feature activation+0.005
Top resid features:
ly
Tokenly
Feature activation+0.004
Top resid features:
)
Token)
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
most
Token most
Feature activation+4.268
Top resid features:
paid
Token paid
Feature activation+0.037
Top resid features:
Pac
Token Pac
Feature activation+0.007
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
12
Token12
Feature activation+0.007
Top resid features:
assistant
Token assistant
Feature activation+0.097
Top resid features:
reme
Tokenreme
Feature activation+0.008
Top resid features:
Ore
Token Ore
Feature activation-0.006
Top resid features:
os
Tokenos
Feature activation+0.011
Top resid features:
:
Token:
Feature activation-0.041
Top resid features:
The
Token The
Feature activation+0.059
Top resid features:
Most
Token Most
Feature activation+4.096
Top resid features:
Meta
Token Meta
Feature activation+0.059
Top resid features:
Sn
Token Sn
Feature activation+0.047
Top resid features:
ack
Tokenack
Feature activation+0.194
Top resid features:
Ever
Token Ever
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+4.150
Top resid features:
honest
Token honest
Feature activation+0.147
Top resid features:
statement
Token statement
Feature activation+0.039
Top resid features:
I
Token I
Feature activation+0.031
Top resid features:
can
Token can
Feature activation-0.048
Top resid features:
muster
Token muster
Feature activation+0.000
Top resid features:
platform
Token platform
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
most
Token most
Feature activation+3.714
Top resid features:
challenging
Token challenging
Feature activation+0.069
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.009
Top resid features:
and
Tokenand
Feature activation+0.019
Top resid features:
intensely
Token intensely
Feature activation-0.002
Top resid features:
satisfying
Token satisfying
Feature activation+0.002
Top resid features:
Carolina
Token Carolina
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
approved
Token approved
Feature activation-0.043
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
most
Token most
Feature activation+3.979
Top resid features:
sweeping
Token sweeping
Feature activation+0.080
Top resid features:
voter
Token voter
Feature activation+0.035
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
supp
Tokensupp
Feature activation+0.025
Top resid features:
ression
Tokenression
Feature activation+0.267
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
anniversary
Token anniversary
Feature activation+0.014
Top resid features:
of
Token of
Feature activation-0.026
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
single
Token single
Feature activation+0.035
Top resid features:
greatest
Token greatest
Feature activation+4.528
Top resid features:
tweet
Token tweet
Feature activation+0.059
Top resid features:
in
Token in
Feature activation-0.232
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
history
Token history
Feature activation-0.079
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ending
Token ending
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
one
Token one
Feature activation+0.009
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
most
Token most
Feature activation+4.392
Top resid features:
well
Token well
Feature activation+0.052
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
written
Tokenwritten
Feature activation+0.015
Top resid features:
shows
Token shows
Feature activation+0.022
Top resid features:
in
Token in
Feature activation-0.277
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
they
Token they
Feature activation-0.003
Top resid features:
'd
Token'd
Feature activation+0.034
Top resid features:
launched
Token launched
Feature activation-0.042
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
largest
Token largest
Feature activation+4.521
Top resid features:
strike
Token strike
Feature activation+0.053
Top resid features:
in
Token in
Feature activation-0.164
Top resid features:
the
Token the
Feature activation-0.046
Top resid features:
history
Token history
Feature activation-0.125
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
some
Token some
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
most
Token most
Feature activation+4.311
Top resid features:
innovative
Token innovative
Feature activation+0.033
Top resid features:
dared
Token dared
Feature activation+0.003
Top resid features:
ev
Tokenev
Feature activation-0.001
Top resid features:
ils
Tokenils
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
track
Token track
Feature activation-0.014
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
have
Token have
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
biggest
Token biggest
Feature activation+4.114
Top resid features:
turnout
Token turnout
Feature activation+0.037
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
Latinos
Token Latinos
Feature activation-0.015
Top resid features:
in
Token in
Feature activation-0.143
Top resid features:
electoral
Token electoral
Feature activation+0.296
Top resid features:
you
Token you
Feature activation-0.005
Top resid features:
find
Token find
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
gru
Token gru
Feature activation+0.001
Top resid features:
ff
Tokenff
Feature activation-0.001
Top resid features:
est
Tokenest
Feature activation+4.049
Top resid features:
voice
Token voice
Feature activation-0.032
Top resid features:
you
Token you
Feature activation+0.095
Top resid features:
can
Token can
Feature activation-0.061
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
SC
Token SC
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
administration
Token administration
Feature activation+0.004
Top resid features:
offered
Token offered
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
largest
Token largest
Feature activation+4.186
Top resid features:
lease
Token lease
Feature activation+0.020
Top resid features:
sale
Token sale
Feature activation+0.028
Top resid features:
ever
Token ever
Feature activation-0.062
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.014
Top resid features:
one
Token one
Feature activation-0.027
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
biggest
Token biggest
Feature activation+4.233
Top resid features:
international
Token international
Feature activation+0.015
Top resid features:
operations
Token operations
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.052
Top resid features:
date
Token date
Feature activation-0.103
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.49

Head 2: 0.02

Head 3: 0.06

Head 4: 0.02

Head 5: 0.06

Head 6: 0.06

Head 7: 0.10

Head 8: 0.01

Head 9: 0.05

Head 10: 0.01

Head 11: 0.08

Positive logits

imaginable2.29

ever2.22

EVER2.11

ever1.95

possible1.71

conceivable1.71

Ever1.67

shortest1.57

Ever1.55

feas1.55

anywhere1.48

humankind1.48

mankind1.43

practicable1.42

allowable1.37

secut1.32

since1.31

since1.25

Possible1.23

feasible1.23

Negative logits

ilial-1.61

accompanied-1.56

oother-1.52

inventoryQuantity-1.47

Bundy-1.38

KEY-1.37

Cosponsors-1.34

aleb-1.26

asper-1.25

-1.25

inances-1.25

00200000-1.24

-1.24

EngineDebug-1.23

ADRA-1.23

ł-1.22

ritz-1.21

20439-1.21

heimer-1.20

uckles-1.19

INTERVAL 3.711 - 4.124
CONTAINS 0.001%

The
Token The
Feature activation+0.000
Most
Token Most
Feature activation+0.000
Meta
Token Meta
Feature activation+0.562
Sn
Token Sn
Feature activation+0.426
ack
Tokenack
Feature activation+2.482
Ever
Token Ever
Feature activation+3.738
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
celebrated
Token celebrated
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
to
Token to
Feature activation+2.150
ever
Token ever
Feature activation+3.823
work
Token work
Feature activation+2.841
in
Token in
Feature activation+0.116
the
Token the
Feature activation+0.000
medium
Token medium
Feature activation+1.792
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
honest
Token honest
Feature activation+0.000
statement
Token statement
Feature activation+2.987
I
Token I
Feature activation+3.118
can
Token can
Feature activation+3.728
muster
Token muster
Feature activation+2.492
about
Token about
Feature activation+1.964
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Creat
TokenCreat
Feature activation+0.000
akings
Tokenakings
Feature activation+1.342
you
Token you
Feature activation+1.052
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.039
ever
Token ever
Feature activation+3.713
face
Token face
Feature activation+0.475
in
Token in
Feature activation+0.140
a
Token a
Feature activation+0.000
PC
Token PC
Feature activation+0.000
flight
Token flight
Feature activation+0.000
most
Token most
Feature activation+0.000
brutal
Token brutal
Feature activation+0.000
K
Token K
Feature activation+1.767
ombat
Tokenombat
Feature activation+0.898
experience
Token experience
Feature activation+2.427
ever
Token ever
Feature activation+4.105
,
Token,
Feature activation+0.000
offering
Token offering
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
fully
Token fully
Feature activation+0.000

INTERVAL 3.299 - 3.711
CONTAINS 0.003%

gru
Token gru
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
est
Tokenest
Feature activation+0.000
voice
Token voice
Feature activation+1.447
you
Token you
Feature activation+1.715
can
Token can
Feature activation+3.523
.
Token.
Feature activation+0.000
SC
Token SC
Feature activation+0.000
OTT
TokenOTT
Feature activation+0.000
CHAR
Token CHAR
Feature activation+0.000
LES
TokenLES
Feature activation+0.000
offered
Token offered
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.190
lease
Token lease
Feature activation+0.776
sale
Token sale
Feature activation+1.543
ever
Token ever
Feature activation+3.508
in
Token in
Feature activation+1.356
the
Token the
Feature activation+0.705
National
Token National
Feature activation+0.000
Petroleum
Token Petroleum
Feature activation+0.000
Reserve
Token Reserve
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
international
Token international
Feature activation+0.448
operations
Token operations
Feature activation+0.000
to
Token to
Feature activation+2.491
date
Token date
Feature activation+3.469
against
Token against
Feature activation+0.613
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.045
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
heaviest
Token heaviest
Feature activation+0.000
mattress
Token mattress
Feature activation+0.970
they
Token they
Feature activation+1.408
can
Token can
Feature activation+3.057
find
Token find
Feature activation+3.366
.
Token.
Feature activation+0.000
Skip
Token Skip
Feature activation+0.000
unnecessary
Token unnecessary
Feature activation+0.000
features
Token features
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
important
Token important
Feature activation+0.404
section
Token section
Feature activation+0.543
of
Token of
Feature activation+0.000
any
Token any
Feature activation+3.350
critic
Token critic
Feature activation+0.335
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
collection
Token collection
Feature activation+0.355

INTERVAL 2.887 - 3.299
CONTAINS 0.007%

the
Token the
Feature activation+0.000
worst
Token worst
Feature activation+0.000
shootings
Token shootings
Feature activation+0.334
in
Token in
Feature activation+1.872
American
Token American
Feature activation+1.562
history
Token history
Feature activation+3.209
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ball
Token ball
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
cliff
Token cliff
Feature activation+0.416
-
Token-
Feature activation+0.000
side
Tokenside
Feature activation+0.346
pathway
Token pathway
Feature activation+1.633
ever
Token ever
Feature activation+3.266
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
any
Token any
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
important
Token important
Feature activation+0.000
ruling
Token ruling
Feature activation+1.148
ever
Token ever
Feature activation+2.952
on
Token on
Feature activation+1.060
the
Token the
Feature activation+0.541
issue
Token issue
Feature activation+1.553
by
Token by
Feature activation+0.499
the
Token the
Feature activation+0.073
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
honest
Token honest
Feature activation+0.000
statement
Token statement
Feature activation+2.987
I
Token I
Feature activation+3.118
can
Token can
Feature activation+3.728
muster
Token muster
Feature activation+2.492
about
Token about
Feature activation+1.964
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ing
Tokening
Feature activation+0.401
facilities
Token facilities
Feature activation+0.853
in
Token in
Feature activation+0.827
the
Token the
Feature activation+1.558
world
Token world
Feature activation+3.036
.
Token.
Feature activation+0.000
Check
Token Check
Feature activation+0.000
www
Token www
Feature activation+0.000
.
Token.
Feature activation+0.000
c
Tokenc
Feature activation+0.000

INTERVAL 2.474 - 2.887
CONTAINS 0.010%

American
Token American
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
American
Token American
Feature activation+0.091
America
Token America
Feature activation+1.058
that
Token that
Feature activation+1.560
any
Token any
Feature activation+2.684
American
Token American
Feature activation+0.115
has
Token has
Feature activation+1.497
ever
Token ever
Feature activation+2.982
American
Token American
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
we
Token we
Feature activation+1.075
could
Token could
Feature activation+1.934
have
Token have
Feature activation+2.488
in
Token in
Feature activation+1.460
Scotland
Token Scotland
Feature activation+1.394
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.174
mountain
Token mountain
Feature activation+1.988
gorilla
Token gorilla
Feature activation+1.059
population
Token population
Feature activation+2.596
âĢĵ
Token âĢĵ
Feature activation+0.000
received
Token received
Feature activation+0.000
550
Token 550
Feature activation+0.000
visitors
Token visitors
Feature activation+0.000
.
Token.
Feature activation+0.000
most
Token most
Feature activation+0.000
honest
Token honest
Feature activation+0.000
statement
Token statement
Feature activation+2.987
I
Token I
Feature activation+3.118
can
Token can
Feature activation+3.728
muster
Token muster
Feature activation+2.492
about
Token about
Feature activation+1.964
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Creat
TokenCreat
Feature activation+0.000
ures
Tokenures
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
Most
Token Most
Feature activation+0.000
Meta
Token Meta
Feature activation+0.562
Sn
Token Sn
Feature activation+0.426
ack
Tokenack
Feature activation+2.482
Ever
Token Ever
Feature activation+3.738
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 2.062 - 2.474
CONTAINS 0.012%

in
Token in
Feature activation+1.042
Montreal
Token Montreal
Feature activation+0.094
Canadiens
Token Canadiens
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
history
Token history
Feature activation+2.298
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
smartphones
Token smartphones
Feature activation+0.000
you
Token you
Feature activation+0.874
can
Token can
Feature activation+1.422
get
Token get
Feature activation+2.425
under
Token under
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
.
Token.
Feature activation+0.000
5000
Token 5000
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
radical
Token radical
Feature activation+0.000
candidate
Token candidate
Feature activation+1.660
in
Token in
Feature activation+1.336
a
Token a
Feature activation+1.967
long
Token long
Feature activation+2.405
time
Token time
Feature activation+2.331
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Ron
TokenRon
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
most
Token most
Feature activation+0.000
complicated
Token complicated
Feature activation+0.000
Britain
Token Britain
Feature activation+1.062
has
Token has
Feature activation+2.578
ever
Token ever
Feature activation+3.166
undertaken
Token undertaken
Feature activation+2.434
.
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
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
tallest
Token tallest
Feature activation+0.000
tree
Token tree
Feature activation+0.785
I
Token I
Feature activation+2.177
have
Token have
Feature activation+2.512
seen
Token seen
Feature activation+3.207
since
Token since
Feature activation+2.776
Yosemite
Token Yosemite
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.649 - 2.062
CONTAINS 0.018%

,
Token,
Feature activation+0.000
dumb
Token dumb
Feature activation+0.000
est
Tokenest
Feature activation+0.000
boy
Token boy
Feature activation+2.215
in
Token in
Feature activation+2.557
the
Token the
Feature activation+2.053
room
Token room
Feature activation+1.791
for
Token for
Feature activation+0.000
half
Token half
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.460
dumb
Token dumb
Feature activation+0.000
est
Tokenest
Feature activation+0.000
boy
Token boy
Feature activation+2.215
in
Token in
Feature activation+2.557
the
Token the
Feature activation+2.053
room
Token room
Feature activation+1.791
for
Token for
Feature activation+0.000
half
Token half
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.460
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.314
've
Token've
Feature activation+2.468
been
Token been
Feature activation+2.083
for
Token for
Feature activation+0.469
a
Token a
Feature activation+0.860
long
Token long
Feature activation+1.758
time
Token time
Feature activation+1.949
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
felt
Token felt
Feature activation+0.000
most
Token most
Feature activation+0.000
nasty
Token nasty
Feature activation+0.000
and
Token and
Feature activation+0.000
personal
Token personal
Feature activation+0.051
campaigns
Token campaigns
Feature activation+0.872
I
Token I
Feature activation+1.954
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+1.813
seen
Token seen
Feature activation+3.280
,
Token,
Feature activation+0.095
Kansas
Token Kansas
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
highest
Token highest
Feature activation+0.000
elevation
Token elevation
Feature activation+1.797
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
:
Token:
Feature activation+0.000
CC
Token CC
Feature activation+0.000

INTERVAL 1.237 - 1.649
CONTAINS 0.024%

the
Token the
Feature activation+0.000
highest
Token highest
Feature activation+0.000
-
Token-
Feature activation+0.000
paid
Tokenpaid
Feature activation+0.003
player
Token player
Feature activation+1.928
in
Token in
Feature activation+1.622
English
Token English
Feature activation+0.818
Rugby
Token Rugby
Feature activation+0.258
,
Token,
Feature activation+0.000
earning
Token earning
Feature activation+0.000
NZ
Token NZ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
most
Token most
Feature activation+0.000
spectacular
Token spectacular
Feature activation+0.000
episode
Token episode
Feature activation+0.890
in
Token in
Feature activation+1.546
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Game
TokenGame
Feature activation+0.000
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+0.000
a
Token a
Feature activation+0.000
mask
Token mask
Feature activation+0.000
whose
Token whose
Feature activation+0.000
best
Token best
Feature activation+0.000
pass
Token pass
Feature activation+1.059
of
Token of
Feature activation+1.572
2015
Token 2015
Feature activation+1.967
earned
Token earned
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
500
Token 500
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
albums
Token albums
Feature activation+0.372
of
Token of
Feature activation+1.014
all
Token all
Feature activation+2.581
time
Token time
Feature activation+1.508
list
Token list
Feature activation+0.000
,
Token,
Feature activation+0.000
#
Token #
Feature activation+0.000
13
Token13
Feature activation+0.000
on
Token on
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
lly
Tokenlly
Feature activation+0.000
A
Token A
Feature activation+0.000
Best
Token Best
Feature activation+0.000
Eff
Token Eff
Feature activation+0.545
ort
Tokenort
Feature activation+1.265
Cache
Token Cache
Feature activation+0.000
Syn
Token Syn
Feature activation+0.000
chron
Tokenchron
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
Library
Token Library
Feature activation+0.106

INTERVAL 0.825 - 1.237
CONTAINS 0.039%

the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
important
Token important
Feature activation+0.000
Hond
Token Hond
Feature activation+0.315
as
Tokenas
Feature activation+0.000
in
Token in
Feature activation+0.975
history
Token history
Feature activation+2.430
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
sedan
Token sedan
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
player
Token player
Feature activation+0.000
in
Token in
Feature activation+0.484
the
Token the
Feature activation+0.315
world
Token world
Feature activation+1.229
has
Token has
Feature activation+0.000
broken
Token broken
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
longest
Token longest
Feature activation+0.000
ten
Token ten
Feature activation+0.000
ured
Tokenured
Feature activation+0.000
crew
Token crew
Feature activation+0.000
chiefs
Token chiefs
Feature activation+0.000
in
Token in
Feature activation+0.972
the
Token the
Feature activation+1.439
NASCAR
Token NASCAR
Feature activation+0.000
Sprint
Token Sprint
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
garage
Token garage
Feature activation+0.000
Its
Token Its
Feature activation+0.000
Worst
Token Worst
Feature activation+0.000
One
Token One
Feature activation+0.819
Night
Token Night
Feature activation+0.026
at
Token at
Feature activation+0.429
Yet
Token Yet
Feature activation+0.866
i
Tokeni
Feature activation+0.000
's
Token's
Feature activation+0.000
Spring
Token Spring
Feature activation+0.000
He
Token He
Feature activation+0.000
els
Tokenels
Feature activation+0.000
blamed
Token blamed
Feature activation+0.000
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
laugh
Token laugh
Feature activation+0.000
ably
Tokenably
Feature activation+1.209
arguing
Token arguing
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
PM
Token PM
Feature activation+0.000
does
Token does
Feature activation+0.000

INTERVAL 0.412 - 0.825
CONTAINS 0.062%

proposals
Token proposals
Feature activation+0.458
he
Token he
Feature activation+1.570
âĢ
TokenâĢ
Feature activation+0.070
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.437
put
Token put
Feature activation+0.783
out
Token out
Feature activation+0.631
of
Token of
Feature activation+0.306
any
Token any
Feature activation+3.356
kind
Token kind
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
largest
Token largest
Feature activation+0.000
chain
Token chain
Feature activation+0.168
of
Token of
Feature activation+0.349
English
Token English
Feature activation+1.183
-
Token-
Feature activation+0.000
language
Tokenlanguage
Feature activation+0.475
d
Token d
Feature activation+0.000
ail
Tokenail
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
gruesome
Token gruesome
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.415
upsetting
Token upsetting
Feature activation+0.976
,
Token,
Feature activation+0.715
still
Token still
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
record
Token record
Feature activation+1.711
in
Token in
Feature activation+1.166
the
Token the
Feature activation+0.746
O
Token O
Feature activation+0.000
HL
TokenHL
Feature activation+0.000
this
Token this
Feature activation+1.023
season
Token season
Feature activation+1.286
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
complaint
Token complaint
Feature activation+0.000
I
Token I
Feature activation+0.794
hear
Token hear
Feature activation+1.357
from
Token from
Feature activation+0.925
teachers
Token teachers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.412
CONTAINS 99.824%

seven
Token seven
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
raised
Token raised
Feature activation+0.000
a
Token a
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
occurred
Token occurred
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
been
Token been
Feature activation+0.000
ages
Token ages
Feature activation+0.000
l
Tokenl
Feature activation+0.000
au
Tokenau
Feature activation+0.000
's
Token's
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
G
Token G
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
l
Tokenl
Feature activation+0.000
au
Tokenau
Feature activation+0.000
's
Token's
Feature activation+0.000
design
Token design
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
in
Token in
Feature activation+0.000
climate
Token climate
Feature activation+0.000
projections
Token projections
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
il
Tokenil
Feature activation+0.000
organic
Token organic
Feature activation+0.000
carbon
Token carbon
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
's
Token's
Feature activation+0.000
court
Token court
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
new
Token new
Feature activation+0.000
revelations
Token revelations
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 H4.1: (feature 21481)

TOP ACTIVATIONS
MAX = 5.394

same
Token same
Feature activation+0.000
problem
Token problem
Feature activation+1.494
of
Token of
Feature activation+0.474
poor
Token poor
Feature activation+0.295
disposal
Token disposal
Feature activation+0.000
that
Token that
Feature activation+5.394
haunted
Token haunted
Feature activation+2.908
the
Token the
Feature activation+0.000
home
Token home
Feature activation+0.000
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.000
tools
Token tools
Feature activation+1.956
Bethesda
Token Bethesda
Feature activation+5.091
used
Token used
Feature activation+4.568
to
Token to
Feature activation+3.063
create
Token create
Feature activation+1.078
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
inflicting
Token inflicting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
he
Token he
Feature activation+4.880
endured
Token endured
Feature activation+4.927
as
Token as
Feature activation+3.778
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
was
Token was
Feature activation+0.000
inflicting
Token inflicting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
he
Token he
Feature activation+4.880
endured
Token endured
Feature activation+4.927
as
Token as
Feature activation+3.778
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
ashing
Tokenashing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
arguments
Token arguments
Feature activation+2.533
that
Token that
Feature activation+4.271
were
Token were
Feature activation+4.702
given
Token given
Feature activation+2.134
to
Token to
Feature activation+1.518
me
Token me
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
mainstream
Token mainstream
Feature activation+1.939
media
Token media
Feature activation+2.783
journalists
Token journalists
Feature activation+3.859
who
Token who
Feature activation+4.700
lav
Token lav
Feature activation+0.117
ishing
Tokenishing
Feature activation+0.541
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
feelings
Token feelings
Feature activation+0.107
about
Token about
Feature activation+1.454
it
Token it
Feature activation+0.000
that
Token that
Feature activation+4.683
Churchill
Token Churchill
Feature activation+0.000
did
Token did
Feature activation+3.371
about
Token about
Feature activation+0.485
democracy
Token democracy
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.000
tools
Token tools
Feature activation+1.956
Bethesda
Token Bethesda
Feature activation+5.091
used
Token used
Feature activation+4.568
to
Token to
Feature activation+3.063
create
Token create
Feature activation+1.078
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
epit
Token epit
Feature activation+0.000
het
Tokenhet
Feature activation+1.590
Trump
Token Trump
Feature activation+3.826
used
Token used
Feature activation+4.557
against
Token against
Feature activation+3.725
him
Token him
Feature activation+0.692
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
painting
Token painting
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
rules
Token rules
Feature activation+1.153
as
Token as
Feature activation+4.522
the
Token the
Feature activation+0.805
territorial
Token territorial
Feature activation+0.000
and
Token and
Feature activation+0.000
federal
Token federal
Feature activation+0.000
governments
Token governments
Feature activation+0.000
change
Token change
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
capitalism
Token capitalism
Feature activation+1.746
that
Token that
Feature activation+4.356
made
Token made
Feature activation+2.543
it
Token it
Feature activation+0.000
possible
Token possible
Feature activation+0.000
for
Token for
Feature activation+0.000
almost
Token almost
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ashing
Tokenashing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
arguments
Token arguments
Feature activation+2.533
that
Token that
Feature activation+4.271
were
Token were
Feature activation+4.702
given
Token given
Feature activation+2.134
to
Token to
Feature activation+1.518
me
Token me
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
--
Token--
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.301
industry
Token industry
Feature activation+2.500
that
Token that
Feature activation+4.244
uses
Token uses
Feature activation+3.315
children
Token children
Feature activation+0.000
as
Token as
Feature activation+1.795
gu
Token gu
Feature activation+0.000
inea
Tokeninea
Feature activation+0.000
spent
Token spent
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
groups
Token groups
Feature activation+3.388
working
Token working
Feature activation+4.201
against
Token against
Feature activation+0.000
SB
Token SB
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+0.000
defeat
Token defeat
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
with
Token with
Feature activation+0.000
endorsements
Token endorsements
Feature activation+0.000
and
Token and
Feature activation+0.000
stories
Token stories
Feature activation+0.000
that
Token that
Feature activation+4.193
legitim
Token legitim
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Google
Token Google
Feature activation+0.803
Maps
Token Maps
Feature activation+0.000
features
Token features
Feature activation+3.100
you
Token you
Feature activation+4.135
âĢ
TokenâĢ
Feature activation+0.704
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.043
used
Token used
Feature activation+3.367
to
Token to
Feature activation+0.676
same
Token same
Feature activation+0.000
test
Token test
Feature activation+0.069
the
Token the
Feature activation+3.775
high
Token high
Feature activation+0.157
court
Token court
Feature activation+1.199
used
Token used
Feature activation+4.098
to
Token to
Feature activation+1.475
invalid
Token invalid
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.000
15
Token15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.356
weapon
Token weapon
Feature activation+2.147
used
Token used
Feature activation+4.093
by
Token by
Feature activation+3.740
Adam
Token Adam
Feature activation+0.000
Lan
Token Lan
Feature activation+0.000
za
Tokenza
Feature activation+0.000
to
Token to
Feature activation+1.290
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
complaints
Token complaints
Feature activation+0.966
that
Token that
Feature activation+4.025
plagued
Token plagued
Feature activation+3.047
Batman
Token Batman
Feature activation+0.000
v
Token v
Feature activation+0.000
Superman
Token Superman
Feature activation+0.000
.
Token.
Feature activation+0.000
-
Token -
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neuro
Token neuro
Feature activation+0.000
sis
Tokensis
Feature activation+1.851
that
Token that
Feature activation+3.902
Harold
Token Harold
Feature activation+0.357
Mac
Token Mac
Feature activation+0.000
Mill
TokenMill
Feature activation+0.000
an
Tokenan
Feature activation+0.000
spoke
Token spoke
Feature activation+0.895

Top DFA by src position
MAX = 5.664

lead
Token lead
Feature activation-0.017
Top resid features:
with
Token with
Feature activation+0.024
Top resid features:
Brisbane
Token Brisbane
Feature activation-0.015
Top resid features:
suffering
Token suffering
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.206
Top resid features:
same
Token same
Feature activation+5.300
Top resid features:
problem
Token problem
Feature activation+0.191
Top resid features:
of
Token of
Feature activation+0.235
Top resid features:
poor
Token poor
Feature activation+0.039
Top resid features:
disposal
Token disposal
Feature activation+0.220
Top resid features:
that
Token that
Feature activation-0.020
Top resid features:
it
Token it
Feature activation+0.055
Top resid features:
allows
Token allows
Feature activation+0.061
Top resid features:
access
Token access
Feature activation-0.038
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
same
Token same
Feature activation+5.634
Top resid features:
development
Token development
Feature activation+0.044
Top resid features:
tools
Token tools
Feature activation+0.130
Top resid features:
Bethesda
Token Bethesda
Feature activation-0.120
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
Peterson
Token Peterson
Feature activation-0.057
Top resid features:
was
Token was
Feature activation-0.017
Top resid features:
inflicting
Token inflicting
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.080
Top resid features:
same
Token same
Feature activation+5.662
Top resid features:
discipline
Token discipline
Feature activation-0.006
Top resid features:
he
Token he
Feature activation+0.081
Top resid features:
endured
Token endured
Feature activation-0.061
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
Peterson
Token Peterson
Feature activation-0.078
Top resid features:
was
Token was
Feature activation-0.048
Top resid features:
inflicting
Token inflicting
Feature activation+0.108
Top resid features:
the
Token the
Feature activation+0.162
Top resid features:
same
Token same
Feature activation+5.501
Top resid features:
discipline
Token discipline
Feature activation+0.081
Top resid features:
he
Token he
Feature activation-0.071
Top resid features:
endured
Token endured
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:
was
Token was
Feature activation-0.004
Top resid features:
re
Token re
Feature activation+0.014
Top resid features:
h
Tokenh
Feature activation+0.009
Top resid features:
ashing
Tokenashing
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.131
Top resid features:
same
Token same
Feature activation+5.664
Top resid features:
arguments
Token arguments
Feature activation-0.091
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
were
Token were
Feature activation-0.250
Top resid features:
given
Token given
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
ethos
Token ethos
Feature activation+0.045
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
The
Token The
Feature activation+0.115
Top resid features:
same
Token same
Feature activation+5.088
Top resid features:
mainstream
Token mainstream
Feature activation+0.027
Top resid features:
media
Token media
Feature activation-0.058
Top resid features:
journalists
Token journalists
Feature activation+0.152
Top resid features:
who
Token who
Feature activation+0.020
Top resid features:
lav
Token lav
Feature activation+0.000
Top resid features:
critics
Token critics
Feature activation-0.020
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
We
Token We
Feature activation+0.045
Top resid features:
have
Token have
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
same
Token same
Feature activation+5.382
Top resid features:
feelings
Token feelings
Feature activation+0.003
Top resid features:
about
Token about
Feature activation+0.038
Top resid features:
it
Token it
Feature activation+0.177
Top resid features:
that
Token that
Feature activation-0.160
Top resid features:
Churchill
Token Churchill
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.020
Top resid features:
allows
Token allows
Feature activation+0.044
Top resid features:
access
Token access
Feature activation-0.020
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
same
Token same
Feature activation+5.401
Top resid features:
development
Token development
Feature activation+0.014
Top resid features:
tools
Token tools
Feature activation+0.035
Top resid features:
Bethesda
Token Bethesda
Feature activation-0.150
Top resid features:
used
Token used
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
boat
Tokenboat
Feature activation-0.007
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
same
Token same
Feature activation+5.314
Top resid features:
epit
Token epit
Feature activation+0.001
Top resid features:
het
Tokenhet
Feature activation+0.023
Top resid features:
Trump
Token Trump
Feature activation+0.082
Top resid features:
used
Token used
Feature activation-0.021
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
governments
Token governments
Feature activation-0.006
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
subject
Token subject
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
same
Token same
Feature activation+5.282
Top resid features:
privacy
Token privacy
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
access
Token access
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
to
Tokento
Feature activation+0.011
Top resid features:
for
Token for
Feature activation-0.017
Top resid features:
climate
Token climate
Feature activation+0.001
Top resid features:
change
Token change
Feature activation-0.006
Top resid features:
?
Token?
Feature activation+0.050
Top resid features:
The
Token The
Feature activation+0.105
Top resid features:
same
Token same
Feature activation+5.039
Top resid features:
capitalism
Token capitalism
Feature activation+0.180
Top resid features:
that
Token that
Feature activation-0.057
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.022
Top resid features:
re
Token re
Feature activation+0.026
Top resid features:
h
Tokenh
Feature activation+0.007
Top resid features:
ashing
Tokenashing
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.117
Top resid features:
same
Token same
Feature activation+5.104
Top resid features:
arguments
Token arguments
Feature activation-0.101
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
given
Token given
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
whims
Token whims
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
--
Token--
Feature activation+0.098
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
same
Token same
Feature activation+5.031
Top resid features:
industry
Token industry
Feature activation+0.009
Top resid features:
that
Token that
Feature activation-0.078
Top resid features:
uses
Token uses
Feature activation+0.000
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.011
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
spent
Token spent
Feature activation-0.007
Top resid features:
by
Token by
Feature activation+0.208
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
same
Token same
Feature activation+4.883
Top resid features:
groups
Token groups
Feature activation-0.001
Top resid features:
working
Token working
Feature activation-0.245
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
SB
Token SB
Feature activation+0.000
Top resid features:
5
Token 5
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
ethos
Token ethos
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
The
Token The
Feature activation+0.056
Top resid features:
same
Token same
Feature activation+4.828
Top resid features:
mainstream
Token mainstream
Feature activation+0.016
Top resid features:
media
Token media
Feature activation+0.011
Top resid features:
journalists
Token journalists
Feature activation-0.003
Top resid features:
who
Token who
Feature activation+0.033
Top resid features:
lav
Token lav
Feature activation+0.019
Top resid features:
can
Token can
Feature activation-0.027
Top resid features:
use
Token use
Feature activation-0.031
Top resid features:
many
Token many
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.222
Top resid features:
same
Token same
Feature activation+4.913
Top resid features:
Google
Token Google
Feature activation-0.004
Top resid features:
Maps
Token Maps
Feature activation+0.016
Top resid features:
features
Token features
Feature activation+0.039
Top resid features:
you
Token you
Feature activation-0.199
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
court
Token court
Feature activation+0.003
Top resid features:
judges
Token judges
Feature activation-0.013
Top resid features:
must
Token must
Feature activation+0.036
Top resid features:
apply
Token apply
Feature activation-0.024
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
same
Token same
Feature activation+4.617
Top resid features:
test
Token test
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.116
Top resid features:
high
Token high
Feature activation-0.055
Top resid features:
court
Token court
Feature activation+0.147
Top resid features:
used
Token used
Feature activation-0.013
Top resid features:
M
TokenM
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
15
Token15
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
same
Token same
Feature activation+5.190
Top resid features:
weapon
Token weapon
Feature activation+0.002
Top resid features:
used
Token used
Feature activation-0.286
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Adam
Token Adam
Feature activation+0.000
Top resid features:
Lan
Token Lan
Feature activation+0.000
Top resid features:
suffer
Token suffer
Feature activation+0.011
Top resid features:
from
Token from
Feature activation-0.064
Top resid features:
many
Token many
Feature activation-0.019
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.132
Top resid features:
same
Token same
Feature activation+4.508
Top resid features:
complaints
Token complaints
Feature activation+0.325
Top resid features:
that
Token that
Feature activation+0.078
Top resid features:
plagued
Token plagued
Feature activation+0.000
Top resid features:
Batman
Token Batman
Feature activation+0.000
Top resid features:
v
Token v
Feature activation+0.000
Top resid features:
amb
Token amb
Feature activation-0.007
Top resid features:
ival
Tokenival
Feature activation-0.007
Top resid features:
ence
Tokenence
Feature activation+0.018
Top resid features:
-
Token -
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
same
Token same
Feature activation+4.510
Top resid features:
neuro
Token neuro
Feature activation+0.030
Top resid features:
sis
Tokensis
Feature activation+0.239
Top resid features:
that
Token that
Feature activation-0.036
Top resid features:
Harold
Token Harold
Feature activation+0.000
Top resid features:
Mac
Token Mac
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.49

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.10

Head 6: 0.06

Head 7: 0.07

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.06

Positive logits

erest1.63

legions1.33

ignor1.29

outgoing1.28

Nost1.27

bestselling1.17

predecessors1.17

wildfire1.15

accustomed1.15

mouths1.15

aths1.14

iac1.13

oths1.12

rats1.12

incumbent1.11

kinderg1.11

Shock1.11

Sap1.10

jaws1.10

determining1.10

Negative logits

...]-1.46

ONSORED-1.35

vr-1.34

-1.34

GBT-1.33

qus-1.33

SPONSORED-1.32

…]-1.28

GMT-1.27

ONG-1.27

amily-1.24

metry-1.22

cture-1.22

liga-1.22

dors-1.22

-1.21

-1.21

IQ-1.21

IDER-1.20

CHAT-1.19

INTERVAL 4.854 - 5.394
CONTAINS 0.000%

to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.000
tools
Token tools
Feature activation+1.956
Bethesda
Token Bethesda
Feature activation+5.091
used
Token used
Feature activation+4.568
to
Token to
Feature activation+3.063
create
Token create
Feature activation+1.078
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
was
Token was
Feature activation+0.000
inflicting
Token inflicting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
he
Token he
Feature activation+4.880
endured
Token endured
Feature activation+4.927
as
Token as
Feature activation+3.778
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
inflicting
Token inflicting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
he
Token he
Feature activation+4.880
endured
Token endured
Feature activation+4.927
as
Token as
Feature activation+3.778
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
same
Token same
Feature activation+0.000
problem
Token problem
Feature activation+1.494
of
Token of
Feature activation+0.474
poor
Token poor
Feature activation+0.295
disposal
Token disposal
Feature activation+0.000
that
Token that
Feature activation+5.394
haunted
Token haunted
Feature activation+2.908
the
Token the
Feature activation+0.000
home
Token home
Feature activation+0.000
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 4.315 - 4.854
CONTAINS 0.001%

change
Token change
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
capitalism
Token capitalism
Feature activation+1.746
that
Token that
Feature activation+4.356
made
Token made
Feature activation+2.543
it
Token it
Feature activation+0.000
possible
Token possible
Feature activation+0.000
for
Token for
Feature activation+0.000
almost
Token almost
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
rules
Token rules
Feature activation+1.153
as
Token as
Feature activation+4.522
the
Token the
Feature activation+0.805
territorial
Token territorial
Feature activation+0.000
and
Token and
Feature activation+0.000
federal
Token federal
Feature activation+0.000
governments
Token governments
Feature activation+0.000
ashing
Tokenashing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
arguments
Token arguments
Feature activation+2.533
that
Token that
Feature activation+4.271
were
Token were
Feature activation+4.702
given
Token given
Feature activation+2.134
to
Token to
Feature activation+1.518
me
Token me
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.000
tools
Token tools
Feature activation+1.956
Bethesda
Token Bethesda
Feature activation+5.091
used
Token used
Feature activation+4.568
to
Token to
Feature activation+3.063
create
Token create
Feature activation+1.078
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
feelings
Token feelings
Feature activation+0.107
about
Token about
Feature activation+1.454
it
Token it
Feature activation+0.000
that
Token that
Feature activation+4.683
Churchill
Token Churchill
Feature activation+0.000
did
Token did
Feature activation+3.371
about
Token about
Feature activation+0.485
democracy
Token democracy
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.776 - 4.315
CONTAINS 0.002%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
rape
Token rape
Feature activation+0.000
culture
Token culture
Feature activation+0.696
that
Token that
Feature activation+3.877
views
Token views
Feature activation+2.661
the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
--
Token--
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.301
industry
Token industry
Feature activation+2.500
that
Token that
Feature activation+4.244
uses
Token uses
Feature activation+3.315
children
Token children
Feature activation+0.000
as
Token as
Feature activation+1.795
gu
Token gu
Feature activation+0.000
inea
Tokeninea
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
mainstream
Token mainstream
Feature activation+1.939
media
Token media
Feature activation+2.783
journalists
Token journalists
Feature activation+3.859
who
Token who
Feature activation+4.700
lav
Token lav
Feature activation+0.117
ishing
Tokenishing
Feature activation+0.541
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
he
Token he
Feature activation+4.880
endured
Token endured
Feature activation+4.927
as
Token as
Feature activation+3.778
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ans
Tokenans
Feature activation+0.106
that
Token that
Feature activation+3.782
was
Token was
Feature activation+3.704
used
Token used
Feature activation+3.896
by
Token by
Feature activation+3.168
that
Token that
Feature activation+0.717
group
Token group
Feature activation+0.195

INTERVAL 3.236 - 3.776
CONTAINS 0.003%

8
Token 8
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
of
Token of
Feature activation+0.000
internal
Token internal
Feature activation+0.000
storage
Token storage
Feature activation+0.000
as
Token as
Feature activation+3.548
the
Token the
Feature activation+0.000
G
Token G
Feature activation+0.000
4
Token4
Feature activation+0.000
St
Token St
Feature activation+0.000
yl
Tokenyl
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
rape
Token rape
Feature activation+0.722
culture
Token culture
Feature activation+0.560
that
Token that
Feature activation+3.348
leaves
Token leaves
Feature activation+0.132
the
Token the
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
rape
Token rape
Feature activation+0.000
must
Token must
Feature activation+0.000
apply
Token apply
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
test
Token test
Feature activation+0.069
the
Token the
Feature activation+3.775
high
Token high
Feature activation+0.157
court
Token court
Feature activation+1.199
used
Token used
Feature activation+4.098
to
Token to
Feature activation+1.475
invalid
Token invalid
Feature activation+0.000
/
Token/
Feature activation+0.000
do
Tokendo
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
they
Token they
Feature activation+3.304
tricked
Token tricked
Feature activation+3.374
the
Token the
Feature activation+0.443
girls
Token girls
Feature activation+0.498
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.049
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
failed
Token failed
Feature activation+0.000
strategies
Token strategies
Feature activation+1.378
that
Token that
Feature activation+3.696
got
Token got
Feature activation+3.742
Trump
Token Trump
Feature activation+0.019
get
Token get
Feature activation+0.000
elected
Token elected
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.697 - 3.236
CONTAINS 0.003%

way
Token way
Feature activation+1.463
as
Token as
Feature activation+1.137
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+2.948
on
Token on
Feature activation+0.048
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
mindset
Token mindset
Feature activation+0.000
.
Token.
Feature activation+0.000
ethos
Token ethos
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
mainstream
Token mainstream
Feature activation+1.939
media
Token media
Feature activation+2.783
journalists
Token journalists
Feature activation+3.859
who
Token who
Feature activation+4.700
lav
Token lav
Feature activation+0.117
ishing
Tokenishing
Feature activation+0.541
her
Token her
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
things
Token things
Feature activation+0.551
that
Token that
Feature activation+2.857
we
Token we
Feature activation+2.606
used
Token used
Feature activation+3.842
to
Token to
Feature activation+0.495
do
Token do
Feature activation+0.457
faster
Token faster
Feature activation+0.000
(
Token (
Feature activation+0.000
using
Tokenusing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
maths
Token maths
Feature activation+0.000
as
Token as
Feature activation+2.834
before
Token before
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
gives
Token gives
Feature activation+0.000
you
Token you
Feature activation+0.000
the
Token the
Feature activation+0.000
exact
Token exact
Feature activation+0.000
same
Token same
Feature activation+0.000
people
Token people
Feature activation+1.436
as
Token as
Feature activation+2.161
those
Token those
Feature activation+2.920
who
Token who
Feature activation+1.809
would
Token would
Feature activation+2.241
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.653
members
Token members
Feature activation+0.000

INTERVAL 2.157 - 2.697
CONTAINS 0.004%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
unit
Token unit
Feature activation+0.000
that
Token that
Feature activation+3.576
arrested
Token arrested
Feature activation+2.249
other
Token other
Feature activation+0.028
AW
Token AW
Feature activation+0.000
@
Token@
Feature activation+0.000
L
TokenL
Feature activation+0.000
members
Token members
Feature activation+1.587
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
-
Token-
Feature activation+0.000
che
Tokenche
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
manner
Token manner
Feature activation+2.441
with
Token with
Feature activation+0.000
its
Token its
Feature activation+0.000
USA
Token USA
Feature activation+0.000
Gross
Token Gross
Feature activation+0.000
National
Token National
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
one
Token one
Feature activation+1.754
that
Token that
Feature activation+2.192
has
Token has
Feature activation+2.619
been
Token been
Feature activation+1.560
shared
Token shared
Feature activation+0.000
many
Token many
Feature activation+0.000
times
Token times
Feature activation+0.000
in
Token in
Feature activation+0.000
clinics
Token clinics
Feature activation+0.000
that
Token that
Feature activation+0.000
perform
Token perform
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
services
Token services
Feature activation+2.259
but
Token but
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
perform
Token perform
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
lifetime
Token lifetime
Feature activation+0.173
as
Token as
Feature activation+1.843
the
Token the
Feature activation+0.759
&
Token &
Feature activation+0.000
str
Tokenstr
Feature activation+0.000
that
Token that
Feature activation+2.587
it
Token it
Feature activation+2.822
contains
Token contains
Feature activation+0.721
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 1.618 - 2.157
CONTAINS 0.005%

-
Token-
Feature activation+0.000
15
Token15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.356
weapon
Token weapon
Feature activation+2.147
used
Token used
Feature activation+4.093
by
Token by
Feature activation+3.740
Adam
Token Adam
Feature activation+0.000
Lan
Token Lan
Feature activation+0.000
za
Tokenza
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
used
Token used
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Pant
Token Pant
Feature activation+2.018
one
Tokenone
Feature activation+2.496
color
Token color
Feature activation+0.537
when
Token when
Feature activation+0.000
rec
Token rec
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
researching
Token researching
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
topics
Token topics
Feature activation+1.684
as
Token as
Feature activation+1.484
you
Token you
Feature activation+1.383
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
same
Token same
Feature activation+0.000
attitude
Token attitude
Feature activation+1.008
that
Token that
Feature activation+3.475
led
Token led
Feature activation+2.002
up
Token up
Feature activation+0.288
to
Token to
Feature activation+0.000
instances
Token instances
Feature activation+0.000
like
Token like
Feature activation+0.000
#
Token #
Feature activation+0.000
(
Token(
Feature activation+0.000
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
this
Token this
Feature activation+0.000
same
Token same
Feature activation+0.000
question
Token question
Feature activation+1.951
)
Token)
Feature activation+0.663
Sam
Token Sam
Feature activation+0.000
M
Token M
Feature activation+0.000
D
Token D
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000

INTERVAL 1.079 - 1.618
CONTAINS 0.009%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.000
general
Token general
Feature activation+0.000
lack
Token lack
Feature activation+1.402
of
Token of
Feature activation+0.000
good
Token good
Feature activation+0.000
humor
Token humor
Feature activation+0.000
by
Token by
Feature activation+1.682
most
Token most
Feature activation+0.000
have
Token have
Feature activation+0.000
almost
Token almost
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
DNA
Token DNA
Feature activation+0.000
as
Token as
Feature activation+1.307
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
humans
Token humans
Feature activation+0.000
can
Token can
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
position
Token position
Feature activation+0.000
that
Token that
Feature activation+2.479
I
Token I
Feature activation+2.697
will
Token will
Feature activation+1.497
be
Token be
Feature activation+1.113
in
Token in
Feature activation+0.048
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
to
Token to
Feature activation+0.000
fear
Token fear
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
same
Token same
Feature activation+0.000
lobby
Token lobby
Feature activation+1.276
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ¢
TokenâĢ¢
Feature activation+0.000
For
Token For
Feature activation+0.000
composed
Token composed
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
exact
Token exact
Feature activation+0.000
same
Token same
Feature activation+0.000
people
Token people
Feature activation+1.436
as
Token as
Feature activation+2.161
those
Token those
Feature activation+2.920
who
Token who
Feature activation+1.809
would
Token would
Feature activation+2.241
have
Token have
Feature activation+0.000

INTERVAL 0.539 - 1.079
CONTAINS 0.013%

ists
Tokenists
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
basic
Token basic
Feature activation+0.000
tendencies
Token tendencies
Feature activation+0.864
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
lifetime
Token lifetime
Feature activation+0.173
as
Token as
Feature activation+1.843
the
Token the
Feature activation+0.759
&
Token &
Feature activation+0.000
str
Tokenstr
Feature activation+0.000
that
Token that
Feature activation+2.587
it
Token it
Feature activation+2.822
contains
Token contains
Feature activation+0.721
sorts
Token sorts
Feature activation+0.000
of
Token of
Feature activation+0.000
mass
Token mass
Feature activation+0.000
sl
Token sl
Feature activation+0.000
aughters
Tokenaughters
Feature activation+0.000
that
Token that
Feature activation+0.639
so
Token so
Feature activation+0.000
recently
Token recently
Feature activation+0.000
horrified
Token horrified
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
pain
Token pain
Feature activation+0.000
than
Token than
Feature activation+0.607
normal
Token normal
Feature activation+0.000
.
Token.
Feature activation+0.000
Offensive
Token Offensive
Feature activation+0.000
linemen
Token linemen
Feature activation+0.000
have
Token have
Feature activation+0.000
same
Token same
Feature activation+0.000
Google
Token Google
Feature activation+0.803
Maps
Token Maps
Feature activation+0.000
features
Token features
Feature activation+3.100
you
Token you
Feature activation+4.135
âĢ
TokenâĢ
Feature activation+0.704
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.043
used
Token used
Feature activation+3.367
to
Token to
Feature activation+0.676
from
Token from
Feature activation+0.000

INTERVAL 0.000 - 0.539
CONTAINS 99.960%

to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
toilet
Token toilet
Feature activation+0.000
exploded
Token exploded
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
General
Token General
Feature activation+0.000
Services
Token Services
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
time
Token time
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
and
Token and
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
two
Token two
Feature activation+0.000
colors
Token colors
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
nature
Token nature
Feature activation+0.000
are
Token are
Feature activation+0.000
used
Token used
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
victim
Token victim
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
hit
Token hit
Feature activation+0.000
engineered
Token engineered
Feature activation+0.000
by
Token by
Feature activation+0.000
someone
Token someone
Feature activation+0.000
he
Token he
Feature activation+0.000
with
Token with
Feature activation+0.000
ice
Token ice
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
methamphetamine
Token methamphetamine
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
what
Token what
Feature activation+0.000
are
Token are
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 H4.1: (feature 2278)

TOP ACTIVATIONS
MAX = 4.219

an
Token an
Feature activation+2.971
oil
Token oil
Feature activation+0.064
and
Token and
Feature activation+0.000
gas
Token gas
Feature activation+0.000
producer
Token producer
Feature activation+1.277
since
Token since
Feature activation+4.219
prices
Token prices
Feature activation+0.000
started
Token started
Feature activation+0.000
falling
Token falling
Feature activation+0.000
last
Token last
Feature activation+0.000
summer
Token summer
Feature activation+0.000
-
Token-
Feature activation+0.000
oper
Tokenoper
Feature activation+0.000
a
Tokena
Feature activation+0.000
in
Token in
Feature activation+1.848
music
Token music
Feature activation+0.688
history
Token history
Feature activation+4.210
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
futures
Token futures
Feature activation+1.360
market
Token market
Feature activation+1.208
in
Token in
Feature activation+2.813
history
Token history
Feature activation+4.161
,
Token,
Feature activation+0.601
and
Token and
Feature activation+0.000
like
Token like
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
first
Token first
Feature activation+0.000
African
Token African
Feature activation+3.121
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+2.830
Republican
Token Republican
Feature activation+0.683
to
Token to
Feature activation+4.145
serve
Token serve
Feature activation+3.875
in
Token in
Feature activation+0.983
the
Token the
Feature activation+1.038
Oregon
Token Oregon
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
RPG
Token RPG
Feature activation+2.273
to
Token to
Feature activation+4.099
allow
Token allow
Feature activation+3.217
its
Token its
Feature activation+0.388
players
Token players
Feature activation+0.000
to
Token to
Feature activation+0.177
create
Token create
Feature activation+0.371
of
Token of
Feature activation+0.100
the
Token the
Feature activation+0.902
NSA
Token NSA
Feature activation+0.105
's
Token's
Feature activation+0.000
powers
Token powers
Feature activation+0.000
since
Token since
Feature activation+4.093
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.113
woman
Token woman
Feature activation+2.615
to
Token to
Feature activation+3.923
run
Token run
Feature activation+2.805
under
Token under
Feature activation+1.119
66
Token 66
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
first
Token first
Feature activation+0.000
strategic
Token strategic
Feature activation+1.218
bombing
Token bombing
Feature activation+0.263
in
Token in
Feature activation+2.358
history
Token history
Feature activation+3.916
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
instance
Token instance
Feature activation+0.065
African
Token African
Feature activation+3.121
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+2.830
Republican
Token Republican
Feature activation+0.683
to
Token to
Feature activation+4.145
serve
Token serve
Feature activation+3.875
in
Token in
Feature activation+0.983
the
Token the
Feature activation+1.038
Oregon
Token Oregon
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
marketplace
Token marketplace
Feature activation+0.000
in
Token in
Feature activation+1.382
Malaysia
Token Malaysia
Feature activation+0.667
to
Token to
Feature activation+3.875
have
Token have
Feature activation+3.853
integrated
Token integrated
Feature activation+1.385
a
Token a
Feature activation+0.755
Bitcoin
Token Bitcoin
Feature activation+0.000
wallet
Token wallet
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
marketplace
Token marketplace
Feature activation+0.000
in
Token in
Feature activation+1.382
Malaysia
Token Malaysia
Feature activation+0.667
to
Token to
Feature activation+3.875
have
Token have
Feature activation+3.853
integrated
Token integrated
Feature activation+1.385
a
Token a
Feature activation+0.755
Bitcoin
Token Bitcoin
Feature activation+0.000
wallet
Token wallet
Feature activation+0.000
into
Token into
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.315
relief
Token relief
Feature activation+0.000
pitcher
Token pitcher
Feature activation+3.177
to
Token to
Feature activation+3.780
win
Token win
Feature activation+3.615
the
Token the
Feature activation+0.854
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
U
Token U
Feature activation+1.722
.
Token.
Feature activation+1.457
S
TokenS
Feature activation+1.285
.
Token.
Feature activation+2.703
President
Token President
Feature activation+2.847
to
Token to
Feature activation+3.674
be
Token be
Feature activation+3.605
given
Token given
Feature activation+2.432
a
Token a
Feature activation+1.751
state
Token state
Feature activation+0.205
dinner
Token dinner
Feature activation+0.000
passing
Token passing
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
legislation
Token legislation
Feature activation+0.684
in
Token in
Feature activation+1.488
decades
Token decades
Feature activation+3.646
to
Token to
Feature activation+0.468
address
Token address
Feature activation+0.077
the
Token the
Feature activation+0.000
sorts
Token sorts
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.315
relief
Token relief
Feature activation+0.000
pitcher
Token pitcher
Feature activation+3.177
to
Token to
Feature activation+3.780
win
Token win
Feature activation+3.615
the
Token the
Feature activation+0.854
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+0.000
.
Token.
Feature activation+1.457
S
TokenS
Feature activation+1.285
.
Token.
Feature activation+2.703
President
Token President
Feature activation+2.847
to
Token to
Feature activation+3.674
be
Token be
Feature activation+3.605
given
Token given
Feature activation+2.432
a
Token a
Feature activation+1.751
state
Token state
Feature activation+0.205
dinner
Token dinner
Feature activation+0.000
in
Token in
Feature activation+0.731
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
dev
Token dev
Feature activation+0.000
board
Token board
Feature activation+0.236
to
Token to
Feature activation+2.946
support
Token support
Feature activation+3.604
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.261
former
Token former
Feature activation+2.399
CIA
Token CIA
Feature activation+0.000
officer
Token officer
Feature activation+2.745
to
Token to
Feature activation+3.593
speak
Token speak
Feature activation+3.315
out
Token out
Feature activation+0.045
publicly
Token publicly
Feature activation+2.521
about
Token about
Feature activation+1.448
the
Token the
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
EU
Token EU
Feature activation+0.887
country
Token country
Feature activation+3.217
to
Token to
Feature activation+3.592
ban
Token ban
Feature activation+2.469
GMOs
Token GMOs
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Deputy
Token Deputy
Feature activation+0.000
first
Token first
Feature activation+0.267
kn
Token kn
Feature activation+0.000
uckle
Tokenuckle
Feature activation+0.000
ball
Tokenball
Feature activation+0.106
pitcher
Token pitcher
Feature activation+3.311
to
Token to
Feature activation+3.590
win
Token win
Feature activation+3.363
the
Token the
Feature activation+0.325
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000

Top DFA by src position
MAX = 4.469

billion
Token billion
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
It
Token It
Feature activation-0.014
Top resid features:
is
Token is
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
first
Token first
Feature activation+4.395
Top resid features:
major
Token major
Feature activation+0.009
Top resid features:
deal
Token deal
Feature activation+0.097
Top resid features:
for
Token for
Feature activation+0.116
Top resid features:
an
Token an
Feature activation-0.027
Top resid features:
oil
Token oil
Feature activation-0.016
Top resid features:
my
Token my
Feature activation+0.024
Top resid features:
ambition
Token ambition
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
compose
Token compose
Feature activation-0.032
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
first
Token first
Feature activation+4.330
Top resid features:
computer
Token computer
Feature activation+0.033
Top resid features:
-
Token-
Feature activation+0.046
Top resid features:
oper
Tokenoper
Feature activation-0.009
Top resid features:
a
Tokena
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.329
Top resid features:
bulbs
Token bulbs
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.016
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
first
Token first
Feature activation+4.469
Top resid features:
futures
Token futures
Feature activation+0.136
Top resid features:
market
Token market
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.306
Top resid features:
history
Token history
Feature activation+0.150
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.184
Top resid features:
,
Token,
Feature activation-0.035
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
first
Token first
Feature activation+4.062
Top resid features:
African
Token African
Feature activation+0.100
Top resid features:
-
Token-
Feature activation+0.041
Top resid features:
American
TokenAmerican
Feature activation+0.078
Top resid features:
Republican
Token Republican
Feature activation+0.364
Top resid features:
to
Token to
Feature activation+0.362
Top resid features:
),
Token),
Feature activation+0.005
Top resid features:
as
Token as
Feature activation+0.015
Top resid features:
it
Token it
Feature activation-0.042
Top resid features:
was
Token was
Feature activation-0.075
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
first
Token first
Feature activation+4.401
Top resid features:
RPG
Token RPG
Feature activation+0.433
Top resid features:
to
Token to
Feature activation+0.260
Top resid features:
allow
Token allow
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
laws
Token laws
Feature activation-0.010
Top resid features:
would
Token would
Feature activation+0.031
Top resid features:
represent
Token represent
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
first
Token first
Feature activation+3.918
Top resid features:
roll
Token roll
Feature activation+0.129
Top resid features:
back
Tokenback
Feature activation+0.101
Top resid features:
of
Token of
Feature activation+0.124
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
NSA
Token NSA
Feature activation-0.019
Top resid features:
mar
Tokenmar
Feature activation-0.004
Top resid features:
athon
Tokenathon
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
becoming
Token becoming
Feature activation-0.038
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
first
Token first
Feature activation+4.404
Top resid features:
woman
Token woman
Feature activation+0.142
Top resid features:
to
Token to
Feature activation+0.161
Top resid features:
run
Token run
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
66
Token 66
Feature activation+0.000
Top resid features:
edit
Token edit
Feature activation+0.002
Top resid features:
]
Token ]
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
TokenThe
Feature activation+0.027
Top resid features:
first
Token first
Feature activation+4.204
Top resid features:
strategic
Token strategic
Feature activation+0.064
Top resid features:
bombing
Token bombing
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.272
Top resid features:
history
Token history
Feature activation+0.197
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.190
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
first
Token first
Feature activation+4.301
Top resid features:
African
Token African
Feature activation+0.090
Top resid features:
-
Token-
Feature activation+0.034
Top resid features:
American
TokenAmerican
Feature activation+0.067
Top resid features:
Republican
Token Republican
Feature activation+0.125
Top resid features:
to
Token to
Feature activation-0.083
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
we
Token we
Feature activation+0.045
Top resid features:
have
Token have
Feature activation+0.012
Top resid features:
become
Token become
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
first
Token first
Feature activation+4.107
Top resid features:
-
Token-
Feature activation+0.040
Top resid features:
ever
Tokenever
Feature activation+0.029
Top resid features:
marketplace
Token marketplace
Feature activation-0.043
Top resid features:
in
Token in
Feature activation+0.175
Top resid features:
Malaysia
Token Malaysia
Feature activation+0.131
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
we
Token we
Feature activation+0.039
Top resid features:
have
Token have
Feature activation+0.008
Top resid features:
become
Token become
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
first
Token first
Feature activation+4.390
Top resid features:
-
Token-
Feature activation+0.027
Top resid features:
ever
Tokenever
Feature activation+0.039
Top resid features:
marketplace
Token marketplace
Feature activation-0.051
Top resid features:
in
Token in
Feature activation+0.078
Top resid features:
Malaysia
Token Malaysia
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
award
Token award
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
becoming
Token becoming
Feature activation-0.018
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
first
Token first
Feature activation+4.136
Top resid features:
relief
Token relief
Feature activation+0.115
Top resid features:
pitcher
Token pitcher
Feature activation+0.101
Top resid features:
to
Token to
Feature activation+0.290
Top resid features:
win
Token win
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
also
Token also
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
first
Token first
Feature activation+3.997
Top resid features:
U
Token U
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
S
TokenS
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.049
Top resid features:
President
Token President
Feature activation+0.126
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
key
Token key
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
passing
Token passing
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
first
Token first
Feature activation+4.017
Top resid features:
legislation
Token legislation
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.408
Top resid features:
decades
Token decades
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
address
Token address
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
award
Token award
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
becoming
Token becoming
Feature activation-0.035
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
first
Token first
Feature activation+4.071
Top resid features:
relief
Token relief
Feature activation+0.089
Top resid features:
pitcher
Token pitcher
Feature activation+0.056
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
win
Token win
Feature activation+0.281
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
also
Token also
Feature activation-0.055
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
first
Token first
Feature activation+4.013
Top resid features:
U
Token U
Feature activation+0.050
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
S
TokenS
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
President
Token President
Feature activation+0.101
Top resid features:
20
Token20
Feature activation-0.004
Top resid features:
So
Token So
Feature activation-0.008
Top resid features:
C
TokenC
Feature activation-0.007
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
first
Token first
Feature activation+4.081
Top resid features:
dev
Token dev
Feature activation+0.058
Top resid features:
board
Token board
Feature activation+0.071
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
support
Token support
Feature activation+0.256
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
ator
Tokenator
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
He
Token He
Feature activation-0.026
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
first
Token first
Feature activation+3.941
Top resid features:
former
Token former
Feature activation+0.139
Top resid features:
CIA
Token CIA
Feature activation+0.041
Top resid features:
officer
Token officer
Feature activation+0.160
Top resid features:
to
Token to
Feature activation+0.117
Top resid features:
speak
Token speak
Feature activation+0.000
Top resid features:
announced
Token announced
Feature activation+0.039
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
they
Token they
Feature activation+0.010
Top resid features:
are
Token are
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
first
Token first
Feature activation+3.902
Top resid features:
EU
Token EU
Feature activation+0.133
Top resid features:
country
Token country
Feature activation+0.084
Top resid features:
to
Token to
Feature activation+0.173
Top resid features:
ban
Token ban
Feature activation+0.000
Top resid features:
GMOs
Token GMOs
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
D
Token D
Feature activation-0.009
Top resid features:
ickey
Tokenickey
Feature activation-0.002
Top resid features:
became
Token became
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
first
Token first
Feature activation+3.944
Top resid features:
kn
Token kn
Feature activation+0.033
Top resid features:
uckle
Tokenuckle
Feature activation+0.028
Top resid features:
ball
Tokenball
Feature activation+0.026
Top resid features:
pitcher
Token pitcher
Feature activation+0.216
Top resid features:
to
Token to
Feature activation+0.198
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.48

Head 2: 0.02

Head 3: 0.06

Head 4: 0.02

Head 5: 0.04

Head 6: 0.05

Head 7: 0.10

Head 8: 0.02

Head 9: 0.09

Head 10: 0.02

Head 11: 0.08

Positive logits

ever1.97

EVER1.89

officially1.49

major1.47

explicitly1.39

overtly1.36

permitted1.35

remotely1.35

reversible1.33

anywhere1.33

imaginable1.31

contiguous1.30

outlawed1.30

banned1.29

spotting1.27

recognized1.27

publicly1.27

yet1.27

ever1.26

formally1.26

Negative logits

[|-1.48

blade-1.46

-1.44

00200000-1.43

otto-1.42

ゴン-1.42

aund-1.40

-1.37

裏�-1.36

uyomi-1.36

Cosponsors-1.35

\\\\-1.35

tnc-1.30

east-1.29

mar-1.28

inventoryQuantity-1.27

":[{"-1.27

ILCS-1.27

nl-1.26

soDeliveryDate-1.26

INTERVAL 3.798 - 4.219
CONTAINS 0.001%

ever
Tokenever
Feature activation+0.000
marketplace
Token marketplace
Feature activation+0.000
in
Token in
Feature activation+1.382
Malaysia
Token Malaysia
Feature activation+0.667
to
Token to
Feature activation+3.875
have
Token have
Feature activation+3.853
integrated
Token integrated
Feature activation+1.385
a
Token a
Feature activation+0.755
Bitcoin
Token Bitcoin
Feature activation+0.000
wallet
Token wallet
Feature activation+0.000
into
Token into
Feature activation+0.000
-
Token-
Feature activation+0.000
oper
Tokenoper
Feature activation+0.000
a
Tokena
Feature activation+0.000
in
Token in
Feature activation+1.848
music
Token music
Feature activation+0.688
history
Token history
Feature activation+4.210
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
African
Token African
Feature activation+3.121
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+2.830
Republican
Token Republican
Feature activation+0.683
to
Token to
Feature activation+4.145
serve
Token serve
Feature activation+3.875
in
Token in
Feature activation+0.983
the
Token the
Feature activation+1.038
Oregon
Token Oregon
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
first
Token first
Feature activation+0.000
strategic
Token strategic
Feature activation+1.218
bombing
Token bombing
Feature activation+0.263
in
Token in
Feature activation+2.358
history
Token history
Feature activation+3.916
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
instance
Token instance
Feature activation+0.065
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
futures
Token futures
Feature activation+1.360
market
Token market
Feature activation+1.208
in
Token in
Feature activation+2.813
history
Token history
Feature activation+4.161
,
Token,
Feature activation+0.601
and
Token and
Feature activation+0.000
like
Token like
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 3.376 - 3.798
CONTAINS 0.002%

was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Japanese
Token Japanese
Feature activation+1.321
car
Token car
Feature activation+1.673
built
Token built
Feature activation+3.471
in
Token in
Feature activation+1.041
America
Token America
Feature activation+1.585
,
Token,
Feature activation+0.000
early
Token early
Feature activation+0.000
models
Token models
Feature activation+0.000
first
Token first
Feature activation+0.267
kn
Token kn
Feature activation+0.000
uckle
Tokenuckle
Feature activation+0.000
ball
Tokenball
Feature activation+0.106
pitcher
Token pitcher
Feature activation+3.311
to
Token to
Feature activation+3.590
win
Token win
Feature activation+3.363
the
Token the
Feature activation+0.325
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
EU
Token EU
Feature activation+0.887
country
Token country
Feature activation+3.217
to
Token to
Feature activation+3.592
ban
Token ban
Feature activation+2.469
GMOs
Token GMOs
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Deputy
Token Deputy
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.100
national
Token national
Feature activation+2.461
news
Token news
Feature activation+2.736
outlet
Token outlet
Feature activation+3.364
to
Token to
Feature activation+3.416
report
Token report
Feature activation+2.548
in
Token in
Feature activation+2.942
detail
Token detail
Feature activation+1.961
on
Token on
Feature activation+1.071
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.230
such
Token such
Feature activation+2.290
visit
Token visit
Feature activation+1.080
by
Token by
Feature activation+3.225
a
Token a
Feature activation+3.489
sitting
Token sitting
Feature activation+0.777
president
Token president
Feature activation+1.838
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000

INTERVAL 2.954 - 3.376
CONTAINS 0.004%

,
Token,
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.315
relief
Token relief
Feature activation+0.000
pitcher
Token pitcher
Feature activation+3.177
to
Token to
Feature activation+3.780
win
Token win
Feature activation+3.615
the
Token the
Feature activation+0.854
award
Token award
Feature activation+0.000
.[
Token.[
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.265
blind
Token blind
Feature activation+0.188
person
Token person
Feature activation+2.053
to
Token to
Feature activation+3.161
be
Token be
Feature activation+3.265
appointed
Token appointed
Feature activation+3.002
to
Token to
Feature activation+0.375
the
Token the
Feature activation+0.000
Upper
Token Upper
Feature activation+0.000
House
Token House
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
EU
Token EU
Feature activation+0.887
country
Token country
Feature activation+3.217
to
Token to
Feature activation+3.592
ban
Token ban
Feature activation+2.469
GMOs
Token GMOs
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.137
eight
Token eight
Feature activation+0.000
-
Token-
Feature activation+0.000
win
Tokenwin
Feature activation+1.356
season
Token season
Feature activation+3.118
since
Token since
Feature activation+3.287
2004
Token 2004
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Part
Token Part
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
scored
Token scored
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
professional
Token professional
Feature activation+3.170
goal
Token goal
Feature activation+1.211
with
Token with
Feature activation+0.798
a
Token a
Feature activation+1.008
fl
Token fl
Feature activation+0.000
icked
Tokenicked
Feature activation+0.000

INTERVAL 2.532 - 2.954
CONTAINS 0.007%

my
Token my
Feature activation+0.000
first
Token first
Feature activation+0.190
sports
Token sports
Feature activation+1.315
reference
Token reference
Feature activation+2.210
in
Token in
Feature activation+2.409
a
Token a
Feature activation+2.945
story
Token story
Feature activation+0.758
during
Token during
Feature activation+0.642
my
Token my
Feature activation+0.000
journalism
Token journalism
Feature activation+0.000
career
Token career
Feature activation+0.591
Computer
Token Computer
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
computer
Token computer
Feature activation+1.208
with
Token with
Feature activation+2.852
native
Token native
Feature activation+2.694
hardware
Token hardware
Feature activation+2.493
and
Token and
Feature activation+0.000
software
Token software
Feature activation+0.762
support
Token support
Feature activation+1.501
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
dev
Token dev
Feature activation+0.000
board
Token board
Feature activation+0.236
to
Token to
Feature activation+2.946
support
Token support
Feature activation+3.604
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
and
Token and
Feature activation+0.000
up
Tokenup
Feature activation+0.000
edia
Tokenedia
Feature activation+0.000
.
Token.
Feature activation+0.000
Its
Token Its
Feature activation+0.000
first
Token first
Feature activation+0.000
major
Token major
Feature activation+2.777
mainstream
Token mainstream
Feature activation+2.352
media
Token media
Feature activation+0.099
coverage
Token coverage
Feature activation+0.549
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
in
Token in
Feature activation+1.655
the
Token the
Feature activation+1.177
city
Token city
Feature activation+1.169
to
Token to
Feature activation+2.895
employ
Token employ
Feature activation+3.499
an
Token an
Feature activation+2.951
armed
Token armed
Feature activation+1.851
boun
Token boun
Feature activation+0.000
cer
Tokencer
Feature activation+0.000
,
Token,
Feature activation+0.068
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 2.110 - 2.532
CONTAINS 0.010%

over
Token over
Feature activation+0.000
Wonder
Token Wonder
Feature activation+0.000
Woman
Token Woman
Feature activation+0.000
as
Token as
Feature activation+0.000
First
Token First
Feature activation+0.000
Female
Token Female
Feature activation+2.383
Super
Token Super
Feature activation+1.180
hero
Tokenhero
Feature activation+0.067
âĦ¢
TokenâĦ¢
Feature activation+0.095
both
Token both
Feature activation+0.000
fost
Token fost
Feature activation+0.000
general
Token general
Feature activation+1.424
and
Token and
Feature activation+1.951
US
Token US
Feature activation+0.346
presidential
Token presidential
Feature activation+0.196
cabinet
Token cabinet
Feature activation+0.746
member
Token member
Feature activation+2.321
to
Token to
Feature activation+3.380
be
Token be
Feature activation+3.205
held
Token held
Feature activation+2.977
in
Token in
Feature activation+1.127
contempt
Token contempt
Feature activation+0.050
will
Token will
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
player
Token player
Feature activation+2.636
in
Token in
Feature activation+2.121
program
Token program
Feature activation+1.231
history
Token history
Feature activation+3.473
and
Token and
Feature activation+0.103
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
This
TokenThis
Feature activation+0.000
show
Token show
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.100
national
Token national
Feature activation+2.461
news
Token news
Feature activation+2.736
outlet
Token outlet
Feature activation+3.364
to
Token to
Feature activation+3.416
report
Token report
Feature activation+2.548
in
Token in
Feature activation+2.942
âĢĶ
TokenâĢĶ
Feature activation+0.000
will
Tokenwill
Feature activation+0.000
make
Token make
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.000
public
Token public
Feature activation+2.302
appearance
Token appearance
Feature activation+1.477
in
Token in
Feature activation+1.147
"
Token "
Feature activation+0.000
Watch
TokenWatch
Feature activation+0.000
This
Token This
Feature activation+0.000

INTERVAL 1.688 - 2.110
CONTAINS 0.011%

Britain
Token Britain
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
world
Token world
Feature activation+0.000
war
Token war
Feature activation+0.000
effort
Token effort
Feature activation+1.818
to
Token to
Feature activation+0.588
help
Token help
Feature activation+0.000
improve
Token improve
Feature activation+0.000
community
Token community
Feature activation+0.000
relations
Token relations
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.981
in
Token in
Feature activation+0.683
a
Token a
Feature activation+1.973
few
Token few
Feature activation+0.000
years
Token years
Feature activation+2.084
,
Token,
Feature activation+0.000
R
Token R
Feature activation+0.000
iddle
Tokeniddle
Feature activation+0.000
is
Token is
Feature activation+0.000
fearful
Token fearful
Feature activation+0.000
ively
Tokenively
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
two
Token two
Feature activation+0.000
full
Token full
Feature activation+1.918
seasons
Token seasons
Feature activation+0.540
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
MLB
Token MLB
Feature activation+0.000
Record
Token Record
Feature activation+0.000
news
Token news
Feature activation+2.736
outlet
Token outlet
Feature activation+3.364
to
Token to
Feature activation+3.416
report
Token report
Feature activation+2.548
in
Token in
Feature activation+2.942
detail
Token detail
Feature activation+1.961
on
Token on
Feature activation+1.071
that
Token that
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
involved
Tokeninvolved
Feature activation+0.000
shooting
Token shooting
Feature activation+2.122
of
Token of
Feature activation+3.587
the
Token the
Feature activation+2.060
year
Token year
Feature activation+1.825
in
Token in
Feature activation+2.346
San
Token San
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000

INTERVAL 1.266 - 1.688
CONTAINS 0.014%

United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
in
Token in
Feature activation+1.279
more
Token more
Feature activation+3.042
than
Token than
Feature activation+3.453
a
Token a
Feature activation+1.336
year
Token year
Feature activation+2.441
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Be
Token Be
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.399
hear
Token hear
Feature activation+1.479
about
Token about
Feature activation+0.248
Nation
Token Nation
Feature activation+0.000
Travels
Token Travels
Feature activation+0.000
destinations
Token destinations
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
choice
Token choice
Feature activation+0.000
transfer
Token transfer
Feature activation+1.344
target
Token target
Feature activation+1.100
of
Token of
Feature activation+0.117
technical
Token technical
Feature activation+0.000
coordinator
Token coordinator
Feature activation+0.000
Ig
Token Ig
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.137
eight
Token eight
Feature activation+0.000
-
Token-
Feature activation+0.000
win
Tokenwin
Feature activation+1.356
season
Token season
Feature activation+3.118
since
Token since
Feature activation+3.287
2004
Token 2004
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
probably
Token probably
Feature activation+0.000
my
Token my
Feature activation+0.000
first
Token first
Feature activation+0.190
sports
Token sports
Feature activation+1.315
reference
Token reference
Feature activation+2.210
in
Token in
Feature activation+2.409
a
Token a
Feature activation+2.945
story
Token story
Feature activation+0.758
during
Token during
Feature activation+0.642

INTERVAL 0.844 - 1.266
CONTAINS 0.019%

through
Token through
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.000
round
Token round
Feature activation+0.000
of
Token of
Feature activation+0.392
2018
Token 2018
Feature activation+1.033
World
Token World
Feature activation+0.073
Cup
Token Cup
Feature activation+1.318
Qual
Token Qual
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
big
Token big
Feature activation+0.995
step
Token step
Feature activation+0.000
to
Token to
Feature activation+0.000
having
Token having
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
year
Token year
Feature activation+0.972
since
Token since
Feature activation+1.344
the
Token the
Feature activation+0.000
inception
Token inception
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+1.107
by
Token by
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
30
Token 30
Feature activation+0.000
,
Token,
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.000
ever
Token ever
Feature activation+0.912
Stand
Token Stand
Feature activation+0.607
Up
Token Up
Feature activation+0.000
for
Token for
Feature activation+1.087
Mental
Token Mental
Feature activation+0.284
Health
Token Health
Feature activation+0.000
(
Token (
Feature activation+0.034
SU
TokenSU
Feature activation+0.000
FM
TokenFM
Feature activation+0.000

INTERVAL 0.422 - 0.844
CONTAINS 0.032%

majority
Token majority
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.991
in
Token in
Feature activation+0.684
a
Token a
Feature activation+1.623
decade
Token decade
Feature activation+2.319
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.823
Tud
Token Tud
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
dating
Token dating
Feature activation+1.270
back
Token back
Feature activation+0.537
from
Token from
Feature activation+0.000
14
Token 14
Feature activation+0.000
93
Token93
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.525
a
Token a
Feature activation+0.468
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
sided
Token sided
Feature activation+0.000
against
Token against
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
first
Token first
Feature activation+0.023
direct
Token direct
Feature activation+1.716
response
Token response
Feature activation+0.574
to
Token to
Feature activation+0.708
the
Token the
Feature activation+0.000
November
Token November
Feature activation+0.000
9
Token 9
Feature activation+0.000
election
Token election
Feature activation+0.000
result
Token result
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
distributed
Token distributed
Feature activation+0.595
-
Token-
Feature activation+0.000
com
Tokencom
Feature activation+0.000
puting
Tokenputing
Feature activation+0.000
projects
Token projects
Feature activation+0.561
that
Token that
Feature activation+0.000

INTERVAL 0.000 - 0.422
CONTAINS 99.900%

Here
TokenHere
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
description
Token description
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
event
Token event
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
been
Token been
Feature activation+0.000
reinstated
Token reinstated
Feature activation+0.000
,''
Token,''
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
felt
Token felt
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Instead
TokenInstead
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
watched
Token watched
Feature activation+0.000
its
Token its
Feature activation+0.000
conception
Token conception
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
70
Token 70
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
Hip
Token Hip
Feature activation+0.000
-
Token-
Feature activation+0.000
Hop
TokenHop
Feature activation+0.000
has
Token has
Feature activation+0.000
of
Token of
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
an
Token an
Feature activation+0.000
economic
Token economic
Feature activation+0.000
disaster
Token disaster
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
doomed
Token doomed
Feature activation+0.000
to
Token to
Feature activation+0.000
collapse
Token collapse
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H4.1: (feature 14326)

TOP ACTIVATIONS
MAX = 4.949

is
Token is
Feature activation+0.000
bad
Token bad
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+2.186
people
Token people
Feature activation+4.949
and
Token and
Feature activation+0.656
public
Token public
Feature activation+0.000
health
Token health
Feature activation+0.000
:
Token:
Feature activation+0.000
When
Token When
Feature activation+0.000
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
both
Token both
Feature activation+0.000
law
Token law
Feature activation+2.214
enforcement
Token enforcement
Feature activation+4.435
and
Token and
Feature activation+1.573
those
Token those
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
home
Token home
Feature activation+0.000
wide
Token wide
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
over
Token over
Feature activation+1.235
-
Token-
Feature activation+4.365
the
Tokenthe
Feature activation+3.050
-
Token-
Feature activation+2.620
counter
Tokencounter
Feature activation+3.577
and
Token and
Feature activation+0.000
prescription
Token prescription
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.401
number
Token number
Feature activation+3.688
of
Token of
Feature activation+4.175
registered
Token registered
Feature activation+0.000
female
Token female
Feature activation+1.319
players
Token players
Feature activation+0.124
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Climate
TokenClimate
Feature activation+0.000
change
Token change
Feature activation+0.000
poses
Token poses
Feature activation+0.000
both
Token both
Feature activation+0.000
economic
Token economic
Feature activation+1.867
risks
Token risks
Feature activation+4.127
and
Token and
Feature activation+1.628
opportunities
Token opportunities
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
Japanese
Token Japanese
Feature activation+1.829
audio
Token audio
Feature activation+2.887
with
Token with
Feature activation+3.974
English
Token English
Feature activation+0.000
subtitles
Token subtitles
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
attempting
Token attempting
Feature activation+0.000
to
Token to
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
both
Token both
Feature activation+0.000
future
Token future
Feature activation+1.876
demand
Token demand
Feature activation+3.973
and
Token and
Feature activation+0.532
the
Token the
Feature activation+0.000
reduction
Token reduction
Feature activation+0.000
in
Token in
Feature activation+0.000
demand
Token demand
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+1.604
respect
Token respect
Feature activation+3.934
of
Token of
Feature activation+2.991
the
Token the
Feature activation+1.191
world
Token world
Feature activation+0.509
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
car
Token car
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+2.317
terms
Token terms
Feature activation+3.895
of
Token of
Feature activation+2.776
production
Token production
Feature activation+0.451
and
Token and
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
.
Token.
Feature activation+0.000
widely
Token widely
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
climate
Token climate
Feature activation+1.788
modeling
Token modeling
Feature activation+3.876
and
Token and
Feature activation+1.702
observation
Token observation
Feature activation+0.000
data
Token data
Feature activation+0.000
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
is
Token is
Feature activation+0.000
unique
Token unique
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
its
Token its
Feature activation+2.747
abundance
Token abundance
Feature activation+3.837
of
Token of
Feature activation+3.303
solar
Token solar
Feature activation+0.848
-
Token-
Feature activation+0.000
powered
Tokenpowered
Feature activation+1.754
homes
Token homes
Feature activation+0.329
H
TokenH
Feature activation+0.000
variable
Token variable
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
participant
Token participant
Feature activation+1.831
-
Token-
Feature activation+3.817
and
Token and
Feature activation+0.427
physician
Token physician
Feature activation+0.000
-
Token-
Feature activation+0.000
ass
Tokenass
Feature activation+0.069
essed
Tokenessed
Feature activation+0.000
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
draining
Token draining
Feature activation+0.000
both
Token both
Feature activation+0.000
Anarch
Token Anarch
Feature activation+0.000
ism
Tokenism
Feature activation+3.813
and
Token and
Feature activation+0.808
capitalism
Token capitalism
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
historical
Token historical
Feature activation+0.000
election
Token election
Feature activation+0.000
was
Token was
Feature activation+0.000
both
Token both
Feature activation+0.000
his
Token his
Feature activation+1.524
inexper
Token inexper
Feature activation+2.867
ience
Tokenience
Feature activation+3.722
and
Token and
Feature activation+0.767
the
Token the
Feature activation+0.000
sur
Token sur
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
burning
Token burning
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.857
present
Token present
Feature activation+2.495
level
Token level
Feature activation+3.719
of
Token of
Feature activation+2.687
greenhouse
Token greenhouse
Feature activation+0.656
g
Token g
Feature activation+0.477
asses
Tokenasses
Feature activation+1.750
in
Token in
Feature activation+0.197
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.401
number
Token number
Feature activation+3.688
of
Token of
Feature activation+4.175
registered
Token registered
Feature activation+0.000
female
Token female
Feature activation+1.319
players
Token players
Feature activation+0.124
and
Token and
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
mountain
Token mountain
Feature activation+0.074
b
Token b
Feature activation+0.438
ikers
Tokenikers
Feature activation+3.646
and
Token and
Feature activation+0.000
equ
Token equ
Feature activation+0.000
est
Tokenest
Feature activation+0.000
rians
Tokenrians
Feature activation+0.000
understand
Token understand
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
facilitate
Token facilitate
Feature activation+3.646
local
Token local
Feature activation+2.509
economic
Token economic
Feature activation+2.864
growth
Token growth
Feature activation+2.502
and
Token and
Feature activation+0.431
alleviate
Token alleviate
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.473
regular
Token regular
Feature activation+3.093
season
Token season
Feature activation+3.619
and
Token and
Feature activation+1.670
Stanley
Token Stanley
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
Playoffs
Token Playoffs
Feature activation+0.000
,
Token,
Feature activation+0.000
deal
Token deal
Feature activation+0.000
must
Token must
Feature activation+0.000
serve
Token serve
Feature activation+0.000
both
Token both
Feature activation+0.000
national
Token national
Feature activation+1.706
interests
Token interests
Feature activation+3.607
.
Token.
Feature activation+0.180
(
Token (
Feature activation+0.000
This
TokenThis
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000

Top DFA by src position
MAX = 5.235

said
Token said
Feature activation+0.012
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
bad
Token bad
Feature activation+0.070
Top resid features:
for
Token for
Feature activation+0.049
Top resid features:
both
Token both
Feature activation+5.235
Top resid features:
vulnerable
Token vulnerable
Feature activation+0.520
Top resid features:
people
Token people
Feature activation+0.632
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
health
Token health
Feature activation+0.000
Top resid features:
gear
Token gear
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
made
Token made
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
protect
Token protect
Feature activation+0.123
Top resid features:
both
Token both
Feature activation+4.908
Top resid features:
law
Token law
Feature activation+0.849
Top resid features:
enforcement
Token enforcement
Feature activation+0.103
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
inside
Token inside
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
wide
Token wide
Feature activation+0.012
Top resid features:
variety
Token variety
Feature activation-0.020
Top resid features:
of
Token of
Feature activation-0.026
Top resid features:
both
Token both
Feature activation+4.698
Top resid features:
over
Token over
Feature activation+1.105
Top resid features:
-
Token-
Feature activation+0.030
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
counter
Tokencounter
Feature activation+0.000
Top resid features:
key
Token key
Feature activation-0.009
Top resid features:
objective
Token objective
Feature activation+0.058
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
increase
Token increase
Feature activation+0.148
Top resid features:
both
Token both
Feature activation+4.719
Top resid features:
the
Token the
Feature activation+0.189
Top resid features:
number
Token number
Feature activation+0.264
Top resid features:
of
Token of
Feature activation+0.294
Top resid features:
registered
Token registered
Feature activation+0.000
Top resid features:
female
Token female
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
ľ
Tokenľ
Feature activation+0.020
Top resid features:
Climate
TokenClimate
Feature activation-0.015
Top resid features:
change
Token change
Feature activation+0.065
Top resid features:
poses
Token poses
Feature activation+0.304
Top resid features:
both
Token both
Feature activation+4.463
Top resid features:
economic
Token economic
Feature activation+0.453
Top resid features:
risks
Token risks
Feature activation+0.479
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
opportunities
Token opportunities
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
States
Token States
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.037
Top resid features:
Canada
Token Canada
Feature activation-0.040
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
in
Token in
Feature activation+0.067
Top resid features:
both
Token both
Feature activation+4.598
Top resid features:
Japanese
Token Japanese
Feature activation+0.140
Top resid features:
audio
Token audio
Feature activation+0.572
Top resid features:
with
Token with
Feature activation+0.254
Top resid features:
English
Token English
Feature activation+0.000
Top resid features:
subtitles
Token subtitles
Feature activation+0.000
Top resid features:
introduced
Token introduced
Feature activation+0.012
Top resid features:
when
Token when
Feature activation+0.034
Top resid features:
attempting
Token attempting
Feature activation+0.040
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
estimate
Token estimate
Feature activation+0.185
Top resid features:
both
Token both
Feature activation+4.275
Top resid features:
future
Token future
Feature activation+0.474
Top resid features:
demand
Token demand
Feature activation+0.403
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
reduction
Token reduction
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
best
Token best
Feature activation+0.029
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
you
Token you
Feature activation+0.015
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
both
Token both
Feature activation+4.986
Top resid features:
in
Token in
Feature activation+0.104
Top resid features:
respect
Token respect
Feature activation+0.320
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
emerging
Token emerging
Feature activation+0.012
Top resid features:
electric
Token electric
Feature activation+0.003
Top resid features:
car
Token car
Feature activation-0.002
Top resid features:
industry
Token industry
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
both
Token both
Feature activation+5.011
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
terms
Token terms
Feature activation+0.133
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
production
Token production
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.005
Top resid features:
been
Token been
Feature activation-0.045
Top resid features:
widely
Token widely
Feature activation-0.010
Top resid features:
suggested
Token suggested
Feature activation+0.012
Top resid features:
from
Token from
Feature activation-0.005
Top resid features:
both
Token both
Feature activation+4.426
Top resid features:
climate
Token climate
Feature activation+0.721
Top resid features:
modeling
Token modeling
Feature activation+0.198
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
observation
Token observation
Feature activation+0.000
Top resid features:
data
Token data
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Australia
Token Australia
Feature activation-0.036
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
unique
Token unique
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.200
Top resid features:
both
Token both
Feature activation+4.745
Top resid features:
its
Token its
Feature activation-0.079
Top resid features:
abundance
Token abundance
Feature activation+0.466
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
solar
Token solar
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
G
Token G
Feature activation+0.028
Top resid features:
SR
TokenSR
Feature activation+0.014
Top resid features:
H
TokenH
Feature activation-0.005
Top resid features:
variable
Token variable
Feature activation+0.018
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
both
Token both
Feature activation+4.638
Top resid features:
participant
Token participant
Feature activation+0.435
Top resid features:
-
Token-
Feature activation+0.289
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
physician
Token physician
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
term
Token term
Feature activation-0.002
Top resid features:
capitalism
Token capitalism
Feature activation+0.044
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
By
Token By
Feature activation-0.025
Top resid features:
draining
Token draining
Feature activation+0.257
Top resid features:
both
Token both
Feature activation+4.298
Top resid features:
Anarch
Token Anarch
Feature activation+0.530
Top resid features:
ism
Tokenism
Feature activation+0.370
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
capitalism
Token capitalism
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.003
Top resid features:
throughout
Token throughout
Feature activation+0.026
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
election
Token election
Feature activation+0.048
Top resid features:
was
Token was
Feature activation+0.121
Top resid features:
both
Token both
Feature activation+4.171
Top resid features:
his
Token his
Feature activation+0.154
Top resid features:
inexper
Token inexper
Feature activation+0.315
Top resid features:
ience
Tokenience
Feature activation+0.500
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
continued
Token continued
Feature activation-0.014
Top resid features:
fossil
Token fossil
Feature activation+0.060
Top resid features:
fuel
Token fuel
Feature activation+0.040
Top resid features:
burning
Token burning
Feature activation+0.062
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
both
Token both
Feature activation+4.103
Top resid features:
the
Token the
Feature activation+0.309
Top resid features:
present
Token present
Feature activation+0.363
Top resid features:
level
Token level
Feature activation+0.236
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
greenhouse
Token greenhouse
Feature activation+0.000
Top resid features:
key
Token key
Feature activation-0.009
Top resid features:
objective
Token objective
Feature activation+0.040
Top resid features:
is
Token is
Feature activation+0.021
Top resid features:
to
Token to
Feature activation-0.031
Top resid features:
increase
Token increase
Feature activation+0.218
Top resid features:
both
Token both
Feature activation+4.581
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
number
Token number
Feature activation+0.294
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
registered
Token registered
Feature activation+0.000
Top resid features:
female
Token female
Feature activation+0.000
Top resid features:
reality
Token reality
Feature activation+0.024
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
majority
Token majority
Feature activation-0.091
Top resid features:
of
Token of
Feature activation-0.186
Top resid features:
both
Token both
Feature activation+4.497
Top resid features:
mountain
Token mountain
Feature activation+0.236
Top resid features:
b
Token b
Feature activation+0.689
Top resid features:
ikers
Tokenikers
Feature activation+0.202
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
equ
Token equ
Feature activation+0.000
Top resid features:
gaps
Token gaps
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
in
Token in
Feature activation+0.050
Top resid features:
order
Token order
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.029
Top resid features:
both
Token both
Feature activation+4.412
Top resid features:
facilitate
Token facilitate
Feature activation+0.432
Top resid features:
local
Token local
Feature activation+0.000
Top resid features:
economic
Token economic
Feature activation+0.000
Top resid features:
growth
Token growth
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.034
Top resid features:
every
Token every
Feature activation-0.027
Top resid features:
game
Token game
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
in
Token in
Feature activation+0.075
Top resid features:
both
Token both
Feature activation+4.124
Top resid features:
the
Token the
Feature activation+0.168
Top resid features:
regular
Token regular
Feature activation+0.589
Top resid features:
season
Token season
Feature activation+0.081
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Stanley
Token Stanley
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
new
Token new
Feature activation-0.003
Top resid features:
deal
Token deal
Feature activation+0.040
Top resid features:
must
Token must
Feature activation-0.118
Top resid features:
serve
Token serve
Feature activation+0.205
Top resid features:
both
Token both
Feature activation+4.206
Top resid features:
national
Token national
Feature activation+0.360
Top resid features:
interests
Token interests
Feature activation+0.428
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
This
TokenThis
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.48

Head 2: 0.02

Head 3: 0.04

Head 4: 0.02

Head 5: 0.06

Head 6: 0.07

Head 7: 0.09

Head 8: 0.02

Head 9: 0.04

Head 10: 0.02

Head 11: 0.11

Positive logits

versus1.53

AND1.44

vs1.43

and1.27

nor1.25

eers1.21

sake1.21

avoidance1.16

Vs1.09

1.08

Leone1.08

Physicians1.06

Seller1.06

Fighters1.05

beh1.03

ForgeModLoader1.03

ainment1.02

statically1.02

convenience1.02

acceptance1.01

Negative logits

覚醒-1.69

��-1.63

��極-1.46

-1.34

��-1.31

Tags-1.30

-1.26

��-1.23

yo-1.22

Ingredients-1.22

Layer-1.21

��-1.20

-1.20

itialized-1.18

orgetown-1.17

Amen-1.16

ynski-1.15

ritz-1.15

orem-1.14

-1.14

INTERVAL 4.454 - 4.949
CONTAINS 0.000%

is
Token is
Feature activation+0.000
bad
Token bad
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+2.186
people
Token people
Feature activation+4.949
and
Token and
Feature activation+0.656
public
Token public
Feature activation+0.000
health
Token health
Feature activation+0.000
:
Token:
Feature activation+0.000
When
Token When
Feature activation+0.000

INTERVAL 3.959 - 4.454
CONTAINS 0.001%

Climate
TokenClimate
Feature activation+0.000
change
Token change
Feature activation+0.000
poses
Token poses
Feature activation+0.000
both
Token both
Feature activation+0.000
economic
Token economic
Feature activation+1.867
risks
Token risks
Feature activation+4.127
and
Token and
Feature activation+1.628
opportunities
Token opportunities
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
attempting
Token attempting
Feature activation+0.000
to
Token to
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
both
Token both
Feature activation+0.000
future
Token future
Feature activation+1.876
demand
Token demand
Feature activation+3.973
and
Token and
Feature activation+0.532
the
Token the
Feature activation+0.000
reduction
Token reduction
Feature activation+0.000
in
Token in
Feature activation+0.000
demand
Token demand
Feature activation+0.000
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
both
Token both
Feature activation+0.000
law
Token law
Feature activation+2.214
enforcement
Token enforcement
Feature activation+4.435
and
Token and
Feature activation+1.573
those
Token those
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
home
Token home
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.401
number
Token number
Feature activation+3.688
of
Token of
Feature activation+4.175
registered
Token registered
Feature activation+0.000
female
Token female
Feature activation+1.319
players
Token players
Feature activation+0.124
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
Japanese
Token Japanese
Feature activation+1.829
audio
Token audio
Feature activation+2.887
with
Token with
Feature activation+3.974
English
Token English
Feature activation+0.000
subtitles
Token subtitles
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.464 - 3.959
CONTAINS 0.002%

,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
facilitate
Token facilitate
Feature activation+3.646
local
Token local
Feature activation+2.509
economic
Token economic
Feature activation+2.864
growth
Token growth
Feature activation+2.502
and
Token and
Feature activation+0.431
alleviate
Token alleviate
Feature activation+0.000
burning
Token burning
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.857
present
Token present
Feature activation+2.495
level
Token level
Feature activation+3.719
of
Token of
Feature activation+2.687
greenhouse
Token greenhouse
Feature activation+0.656
g
Token g
Feature activation+0.477
asses
Tokenasses
Feature activation+1.750
in
Token in
Feature activation+0.197
car
Token car
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+2.317
terms
Token terms
Feature activation+3.895
of
Token of
Feature activation+2.776
production
Token production
Feature activation+0.451
and
Token and
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
.
Token.
Feature activation+0.000
their
Token their
Feature activation+0.000
bosses
Token bosses
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.333
public
Token public
Feature activation+3.591
and
Token and
Feature activation+1.624
the
Token the
Feature activation+0.000
private
Token private
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
pay
Token pay
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
mountain
Token mountain
Feature activation+0.074
b
Token b
Feature activation+0.438
ikers
Tokenikers
Feature activation+3.646
and
Token and
Feature activation+0.000
equ
Token equ
Feature activation+0.000
est
Tokenest
Feature activation+0.000
rians
Tokenrians
Feature activation+0.000
understand
Token understand
Feature activation+0.000

INTERVAL 2.969 - 3.464
CONTAINS 0.002%

left
Token left
Feature activation+0.000
field
Token field
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.704
minors
Token minors
Feature activation+3.429
and
Token and
Feature activation+0.791
majors
Token majors
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
we
Token we
Feature activation+0.000
fight
Token fight
Feature activation+0.000
is
Token is
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+2.220
benchmark
Token benchmark
Feature activation+3.114
and
Token and
Feature activation+3.086
a
Token a
Feature activation+0.000
determin
Token determin
Feature activation+0.000
ant
Tokenant
Feature activation+0.130
of
Token of
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
over
Token over
Feature activation+1.235
-
Token-
Feature activation+4.365
the
Tokenthe
Feature activation+3.050
-
Token-
Feature activation+2.620
counter
Tokencounter
Feature activation+3.577
and
Token and
Feature activation+0.000
prescription
Token prescription
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
ctions
Tokenctions
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
Spider
Token Spider
Feature activation+0.000
-
Token-
Feature activation+0.648
Man
TokenMan
Feature activation+2.993
and
Token and
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Panther
Token Panther
Feature activation+0.000
,
Token,
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
fight
Token fight
Feature activation+0.000
is
Token is
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+2.220
benchmark
Token benchmark
Feature activation+3.114
and
Token and
Feature activation+3.086
a
Token a
Feature activation+0.000
determin
Token determin
Feature activation+0.000
ant
Tokenant
Feature activation+0.130
of
Token of
Feature activation+0.000
human
Token human
Feature activation+0.000

INTERVAL 2.474 - 2.969
CONTAINS 0.005%

that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
crushing
Token crushing
Feature activation+0.000
both
Token both
Feature activation+0.000
his
Token his
Feature activation+2.945
professional
Token professional
Feature activation+2.767
and
Token and
Feature activation+1.170
personal
Token personal
Feature activation+0.000
life
Token life
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.035
but
Tokenbut
Feature activation+0.000
active
Token active
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.896
Congress
Token Congress
Feature activation+1.868
on
Token on
Feature activation+2.704
Racial
Token Racial
Feature activation+0.155
Equality
Token Equality
Feature activation+0.435
(
Token (
Feature activation+1.035
C
TokenC
Feature activation+0.000
ORE
TokenORE
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+1.285
cluster
Token cluster
Feature activation+2.847
in
Token in
Feature activation+1.626
security
Token security
Feature activation+2.248
(
Token (
Feature activation+2.602
3
Token3
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
top
Token top
Feature activation+0.000
5
Token 5
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
facilitate
Token facilitate
Feature activation+3.646
local
Token local
Feature activation+2.509
economic
Token economic
Feature activation+2.864
growth
Token growth
Feature activation+2.502
and
Token and
Feature activation+0.431
alleviate
Token alleviate
Feature activation+0.000
pressures
Token pressures
Feature activation+0.000
in
Token in
Feature activation+0.000
provide
Token provide
Feature activation+0.000
ample
Token ample
Feature activation+0.000
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
developing
Token developing
Feature activation+2.617
and
Token and
Feature activation+1.334
mature
Token mature
Feature activation+0.000
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.980 - 2.474
CONTAINS 0.007%

problem
Token problem
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.044
short
Token short
Feature activation+2.387
and
Token and
Feature activation+0.446
long
Token long
Feature activation+0.000
terms
Token terms
Feature activation+0.000
.
Token.
Feature activation+0.000
being
Token being
Feature activation+0.000
used
Token used
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+1.919
the
Token the
Feature activation+1.931
trailer
Token trailer
Feature activation+2.055
,
Token,
Feature activation+1.158
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
poster
Token poster
Feature activation+0.000
to
Token to
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+2.195
the
Token the
Feature activation+2.618
Muslim
Token Muslim
Feature activation+1.588
region
Token region
Feature activation+2.146
and
Token and
Feature activation+0.000
across
Token across
Feature activation+0.000
India
Token India
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
fault
Token fault
Feature activation+0.000
lines
Token lines
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
is
Tokenis
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+1.993
city
Token city
Feature activation+2.063
to
Token to
Feature activation+1.492
watch
Token watch
Feature activation+1.029
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
matching
Token matching
Feature activation+0.000
values
Token values
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.794
new
Token new
Feature activation+2.369
request
Token request
Feature activation+2.987
and
Token and
Feature activation+1.535
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
internal
Token internal
Feature activation+0.000

INTERVAL 1.485 - 1.980
CONTAINS 0.011%

upon
Token upon
Feature activation+0.000
his
Token his
Feature activation+0.000
skills
Token skills
Feature activation+0.000
as
Token as
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+1.898
journalist
Token journalist
Feature activation+2.357
and
Token and
Feature activation+1.851
a
Token a
Feature activation+0.000
fiction
Token fiction
Feature activation+0.000
writer
Token writer
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
tool
Token tool
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
genius
Token genius
Feature activation+1.694
villains
Token villains
Feature activation+2.467
and
Token and
Feature activation+0.000
celebrated
Token celebrated
Feature activation+0.000
heroes
Token heroes
Feature activation+0.000
.
Token.
Feature activation+0.000
I
TokenI
Feature activation+0.000
love
Token love
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.751
Young
Token Young
Feature activation+0.738
Avengers
Token Avengers
Feature activation+1.613
and
Token and
Feature activation+0.342
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000
Warriors
Token Warriors
Feature activation+0.000
,
Token,
Feature activation+0.000
bosses
Token bosses
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+2.333
public
Token public
Feature activation+3.591
and
Token and
Feature activation+1.624
the
Token the
Feature activation+0.000
private
Token private
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
pay
Token pay
Feature activation+0.000
each
Token each
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
among
Token among
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.893
w
Token w
Feature activation+0.786
ett
Tokenett
Feature activation+0.550
est
Tokenest
Feature activation+3.360
and
Token and
Feature activation+1.512
dri
Token dri
Feature activation+0.000

INTERVAL 0.990 - 1.485
CONTAINS 0.011%

were
Token were
Feature activation+0.000
crushing
Token crushing
Feature activation+0.000
both
Token both
Feature activation+0.000
his
Token his
Feature activation+2.945
professional
Token professional
Feature activation+2.767
and
Token and
Feature activation+1.170
personal
Token personal
Feature activation+0.000
life
Token life
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.035
but
Tokenbut
Feature activation+0.000
who
Token who
Feature activation+0.000
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
Kurdish
Token Kurdish
Feature activation+0.000
both
Token both
Feature activation+0.000
online
Token online
Feature activation+2.416
and
Token and
Feature activation+1.183
in
Token in
Feature activation+0.000
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Des
Token Des
Feature activation+0.000
perate
Tokenperate
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
both
Token both
Feature activation+0.000
val
Token val
Feature activation+1.202
u
Tokenu
Feature activation+1.883
ables
Tokenables
Feature activation+3.570
,
Token,
Feature activation+0.060
I
Token I
Feature activation+0.000
tried
Token tried
Feature activation+0.000
embraced
Token embraced
Feature activation+0.000
both
Token both
Feature activation+0.000
Bul
Token Bul
Feature activation+0.000
le
Tokenle
Feature activation+0.000
it
Tokenit
Feature activation+0.000
Bourbon
Token Bourbon
Feature activation+1.391
and
Token and
Feature activation+0.000
Bul
Token Bul
Feature activation+0.000
le
Tokenle
Feature activation+0.000
it
Tokenit
Feature activation+0.000
Rye
Token Rye
Feature activation+0.000
that
Token that
Feature activation+0.000
both
Token both
Feature activation+0.000
allow
Token allow
Feature activation+1.063
for
Token for
Feature activation+1.708
induction
Token induction
Feature activation+0.723
charging
Token charging
Feature activation+1.017
and
Token and
Feature activation+0.000
extend
Token extend
Feature activation+0.000
play
Token play
Feature activation+0.000
lifetime
Token lifetime
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.495 - 0.990
CONTAINS 0.017%

and
Token and
Feature activation+0.000
products
Token products
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
commercially
Token commercially
Feature activation+2.136
and
Token and
Feature activation+0.959
in
Token in
Feature activation+0.000
open
Token open
Feature activation+0.000
field
Token field
Feature activation+0.000
trials
Token trials
Feature activation+0.000
,
Token,
Feature activation+0.000
outside
Token outside
Feature activation+1.816
the
Token the
Feature activation+1.369
E
Token E
Feature activation+0.000
uch
Tokenuch
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
istic
Tokenistic
Feature activation+0.863
celebration
Token celebration
Feature activation+0.196
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
4
Token4
Feature activation+0.000
was
Token was
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
study
Token study
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.644
effect
Token effect
Feature activation+2.490
of
Token of
Feature activation+2.513
flu
Token flu
Feature activation+0.000
ox
Tokenox
Feature activation+0.000
et
Tokenet
Feature activation+0.000
protecting
Token protecting
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+1.961
H
Token H
Feature activation+0.688
MI
TokenMI
Feature activation+2.044
and
Token and
Feature activation+0.744
the
Token the
Feature activation+0.000
overall
Token overall
Feature activation+0.000
system
Token system
Feature activation+0.000
from
Token from
Feature activation+0.000
unpredictable
Token unpredictable
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
prisoners
Token prisoners
Feature activation+2.459
and
Token and
Feature activation+0.953
guards
Token guards
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Gul
Token Gul
Feature activation+0.000
ags
Tokenags
Feature activation+0.000

INTERVAL 0.000 - 0.495
CONTAINS 99.944%

and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
being
Token being
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
breathe
Token breathe
Feature activation+0.000
the
Token the
Feature activation+0.000
polluted
Token polluted
Feature activation+0.000
air
Token air
Feature activation+0.000
.
Token.
Feature activation+0.000
Other
Token Other
Feature activation+0.000
countries
Token countries
Feature activation+0.000
attend
Token attend
Feature activation+0.000
the
Token the
Feature activation+0.000
Games
Token Games
Feature activation+0.000
,
Token,
Feature activation+0.000
potentially
Token potentially
Feature activation+0.000
acquire
Token acquire
Feature activation+0.000
that
Token that
Feature activation+0.000
strain
Token strain
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
was
Token was
Feature activation+0.000
carried
Token carried
Feature activation+0.000
out
Token out
Feature activation+0.000
by
Token by
Feature activation+0.000
means
Token means
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
lever
Token lever
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+0.000
C
Token C
Feature activation+0.000
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
T
TokenT
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
discrimination
Tokendiscrimination
Feature activation+0.000
provision
Token provision
Feature activation+0.000
prohibits
Token prohibits
Feature activation+0.000
employers
Token employers
Feature activation+0.000
from
Token from
Feature activation+0.000
limiting
Token limiting
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
to
Token to
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
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 H4.1: (feature 5878)

TOP ACTIVATIONS
MAX = 5.566

with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
it
Token it
Feature activation+2.135
all
Token all
Feature activation+2.410
went
Token went
Feature activation+5.566
down
Token down
Feature activation+2.903
,
Token,
Feature activation+1.514
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
posted
Token posted
Feature activation+0.000
grow
Token grow
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
a
Token a
Feature activation+1.810
plant
Token plant
Feature activation+2.916
grows
Token grows
Feature activation+5.365
on
Token on
Feature activation+3.532
rabbit
Token rabbit
Feature activation+0.000
manure
Token manure
Feature activation+0.384
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
news
Token news
Feature activation+1.547
stories
Token stories
Feature activation+3.715
are
Token are
Feature activation+4.236
covered
Token covered
Feature activation+5.244
to
Token to
Feature activation+0.000
national
Token national
Feature activation+0.000
political
Token political
Feature activation+0.000
issues
Token issues
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.212
and
Token and
Feature activation+1.204
businesses
Token businesses
Feature activation+2.916
transact
Token transact
Feature activation+5.083
,
Token,
Feature activation+2.558
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
will
Token will
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.903
game
Token game
Feature activation+1.725
was
Token was
Feature activation+3.604
offic
Token offic
Feature activation+1.677
iated
Tokeniated
Feature activation+4.882
,
Token,
Feature activation+1.448
I
Token I
Feature activation+0.206
'm
Token'm
Feature activation+0.026
gonna
Token gonna
Feature activation+0.000
leave
Token leave
Feature activation+0.000
of
Token of
Feature activation+0.142
personal
Token personal
Feature activation+0.000
and
Token and
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
behaviour
Token behaviour
Feature activation+0.628
are
Token are
Feature activation+4.777
handled
Token handled
Feature activation+4.350
by
Token by
Feature activation+2.791
society
Token society
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
they
Token they
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+1.660
present
Token present
Feature activation+4.643
themselves
Token themselves
Feature activation+3.572
and
Token and
Feature activation+1.369
it
Token it
Feature activation+0.110
gets
Token gets
Feature activation+0.000
over
Token over
Feature activation+0.000
believe
Token believe
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+0.707
general
Token general
Feature activation+4.003
ize
Tokenize
Feature activation+4.606
all
Token all
Feature activation+0.831
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.200
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
goes
Token goes
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+0.735
plan
Token plan
Feature activation+4.516
and
Token and
Feature activation+1.042
I
Token I
Feature activation+0.418
have
Token have
Feature activation+0.000
faith
Token faith
Feature activation+0.000
that
Token that
Feature activation+0.000
games
Token games
Feature activation+0.000
past
Token past
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
characters
Token characters
Feature activation+1.805
look
Token look
Feature activation+4.505
on
Token on
Feature activation+3.051
the
Token the
Feature activation+0.993
surface
Token surface
Feature activation+0.744
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.437
look
Token look
Feature activation+3.433
at
Token at
Feature activation+4.492
food
Token food
Feature activation+0.270
.
Token.
Feature activation+0.182
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
you
Token you
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
literally
Token literally
Feature activation+0.000
everyone
Token everyone
Feature activation+4.088
looks
Token looks
Feature activation+4.458
at
Token at
Feature activation+3.322
m
Token m
Feature activation+0.000
eryl
Tokeneryl
Feature activation+0.000
stre
Token stre
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
computers
Token computers
Feature activation+3.023
are
Token are
Feature activation+4.385
used
Token used
Feature activation+3.772
in
Token in
Feature activation+2.594
many
Token many
Feature activation+0.000
industries
Token industries
Feature activation+0.045
,
Token,
Feature activation+0.000
personal
Token personal
Feature activation+0.000
and
Token and
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
behaviour
Token behaviour
Feature activation+0.628
are
Token are
Feature activation+4.777
handled
Token handled
Feature activation+4.350
by
Token by
Feature activation+2.791
society
Token society
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
creative
Token creative
Feature activation+0.000
way
Token way
Feature activation+0.000
Baker
Token Baker
Feature activation+0.000
promoted
Token promoted
Feature activation+4.286
the
Token the
Feature activation+2.148
brand
Token brand
Feature activation+0.218
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.467
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
the
Token the
Feature activation+1.225
season
Token season
Feature activation+0.464
is
Token is
Feature activation+4.284
going
Token going
Feature activation+3.575
,
Token,
Feature activation+0.090
all
Token all
Feature activation+0.000
at
Token at
Feature activation+0.000
19
Token 19
Feature activation+0.000
everything
Token everything
Feature activation+0.000
appearing
Token appearing
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
it
Token it
Feature activation+2.844
should
Token should
Feature activation+4.244
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
settled
Token settled
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
news
Token news
Feature activation+1.547
stories
Token stories
Feature activation+3.715
are
Token are
Feature activation+4.236
covered
Token covered
Feature activation+5.244
to
Token to
Feature activation+0.000
national
Token national
Feature activation+0.000
political
Token political
Feature activation+0.000
issues
Token issues
Feature activation+0.000
global
Token global
Feature activation+1.406
ized
Tokenized
Feature activation+1.227
capitalist
Token capitalist
Feature activation+0.000
order
Token order
Feature activation+0.289
is
Token is
Feature activation+3.932
organized
Token organized
Feature activation+4.213
,
Token,
Feature activation+1.036
particularly
Token particularly
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Anon
Token Anon
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
ox
Tokenox
Feature activation+0.000
should
Token should
Feature activation+3.723
have
Token have
Feature activation+1.386
done
Token done
Feature activation+4.152
it
Token it
Feature activation+0.675
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PORT
TokenPORT
Feature activation+0.000

Top DFA by src position
MAX = 6.390

Ļ
TokenĻ
Feature activation-0.006
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
thrilled
Token thrilled
Feature activation+0.022
Top resid features:
with
Token with
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
way
Token way
Feature activation+6.390
Top resid features:
it
Token it
Feature activation+0.097
Top resid features:
all
Token all
Feature activation+0.587
Top resid features:
went
Token went
Feature activation-0.095
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
never
Token never
Feature activation-0.012
Top resid features:
seen
Token seen
Feature activation-0.024
Top resid features:
anything
Token anything
Feature activation+0.029
Top resid features:
grow
Token grow
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
way
Token way
Feature activation+6.014
Top resid features:
a
Token a
Feature activation+0.125
Top resid features:
plant
Token plant
Feature activation+0.542
Top resid features:
grows
Token grows
Feature activation-0.165
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
rabbit
Token rabbit
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.024
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
everything
Token everything
Feature activation+0.026
Top resid features:
from
Token from
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
way
Token way
Feature activation+5.785
Top resid features:
news
Token news
Feature activation+0.239
Top resid features:
stories
Token stories
Feature activation+0.281
Top resid features:
are
Token are
Feature activation+0.310
Top resid features:
covered
Token covered
Feature activation-0.078
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
technology
Token technology
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
fundamentally
Token fundamentally
Feature activation+0.019
Top resid features:
changing
Token changing
Feature activation-0.074
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
way
Token way
Feature activation+6.112
Top resid features:
people
Token people
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+0.293
Top resid features:
businesses
Token businesses
Feature activation+0.183
Top resid features:
transact
Token transact
Feature activation-0.135
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
wasn
Token wasn
Feature activation-0.001
Top resid features:
't
Token't
Feature activation-0.003
Top resid features:
happy
Token happy
Feature activation-0.022
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
way
Token way
Feature activation+5.289
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
game
Token game
Feature activation+0.281
Top resid features:
was
Token was
Feature activation-0.027
Top resid features:
offic
Token offic
Feature activation+0.772
Top resid features:
iated
Tokeniated
Feature activation-0.178
Top resid features:
change
Token change
Feature activation-0.026
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
underway
Token underway
Feature activation-0.101
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
way
Token way
Feature activation+5.293
Top resid features:
issues
Token issues
Feature activation+0.739
Top resid features:
of
Token of
Feature activation+0.078
Top resid features:
personal
Token personal
Feature activation-0.040
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
sexual
Token sexual
Feature activation+0.044
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
when
Token when
Feature activation-0.068
Top resid features:
they
Token they
Feature activation-0.009
Top resid features:
change
Token change
Feature activation-0.089
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
way
Token way
Feature activation+5.697
Top resid features:
they
Token they
Feature activation+0.399
Top resid features:
present
Token present
Feature activation-0.110
Top resid features:
themselves
Token themselves
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Some
Token Some
Feature activation-0.004
Top resid features:
atheists
Token atheists
Feature activation-0.028
Top resid features:
may
Token may
Feature activation-0.016
Top resid features:
believe
Token believe
Feature activation-0.046
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
way
Token way
Feature activation+5.225
Top resid features:
you
Token you
Feature activation+0.202
Top resid features:
general
Token general
Feature activation+0.683
Top resid features:
ize
Tokenize
Feature activation-0.287
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
not
Token not
Feature activation-0.010
Top resid features:
everything
Token everything
Feature activation-0.045
Top resid features:
goes
Token goes
Feature activation-0.052
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
way
Token way
Feature activation+5.250
Top resid features:
you
Token you
Feature activation+0.241
Top resid features:
plan
Token plan
Feature activation+0.318
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
these
Token these
Feature activation+0.038
Top resid features:
games
Token games
Feature activation-0.054
Top resid features:
past
Token past
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
way
Token way
Feature activation+4.669
Top resid features:
characters
Token characters
Feature activation+0.866
Top resid features:
look
Token look
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:
surface
Token surface
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
way
Token way
Feature activation+5.432
Top resid features:
people
Token people
Feature activation+0.045
Top resid features:
look
Token look
Feature activation+0.212
Top resid features:
at
Token at
Feature activation+0.237
Top resid features:
food
Token food
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.106
Top resid features:
looks
Token looks
Feature activation+0.053
Top resid features:
at
Token at
Feature activation+0.047
Top resid features:
you
Token you
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
way
Token way
Feature activation+5.676
Top resid features:
literally
Token literally
Feature activation-0.073
Top resid features:
everyone
Token everyone
Feature activation+0.209
Top resid features:
looks
Token looks
Feature activation-0.127
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
m
Token m
Feature activation+0.000
Top resid features:
seem
Token seem
Feature activation+0.014
Top resid features:
destined
Token destined
Feature activation-0.023
Top resid features:
to
Token to
Feature activation-0.053
Top resid features:
change
Token change
Feature activation-0.095
Top resid features:
the
Token the
Feature activation+0.080
Top resid features:
way
Token way
Feature activation+5.500
Top resid features:
computers
Token computers
Feature activation+0.334
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
change
Token change
Feature activation-0.045
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
underway
Token underway
Feature activation-0.098
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
way
Token way
Feature activation+5.102
Top resid features:
issues
Token issues
Feature activation+0.560
Top resid features:
of
Token of
Feature activation+0.098
Top resid features:
personal
Token personal
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
sexual
Token sexual
Feature activation+0.022
Top resid features:
advertising
Token advertising
Feature activation+0.003
Top resid features:
--
Token --
Feature activation-0.059
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
creative
Token creative
Feature activation-0.021
Top resid features:
way
Token way
Feature activation+5.303
Top resid features:
Baker
Token Baker
Feature activation+0.544
Top resid features:
promoted
Token promoted
Feature activation-0.143
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
brand
Token brand
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
emotional
Token emotional
Feature activation-0.002
Top resid features:
factor
Token factor
Feature activation-0.050
Top resid features:
of
Token of
Feature activation-0.051
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
way
Token way
Feature activation+5.081
Top resid features:
the
Token the
Feature activation+0.103
Top resid features:
season
Token season
Feature activation+0.514
Top resid features:
is
Token is
Feature activation-0.085
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
charged
Token charged
Feature activation-0.095
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
everything
Token everything
Feature activation+0.012
Top resid features:
appearing
Token appearing
Feature activation-0.091
Top resid features:
the
Token the
Feature activation+0.091
Top resid features:
way
Token way
Feature activation+5.302
Top resid features:
it
Token it
Feature activation+0.563
Top resid features:
should
Token should
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
settled
Token settled
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.030
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
everything
Token everything
Feature activation+0.026
Top resid features:
from
Token from
Feature activation-0.140
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
way
Token way
Feature activation+5.207
Top resid features:
news
Token news
Feature activation+0.141
Top resid features:
stories
Token stories
Feature activation+0.455
Top resid features:
are
Token are
Feature activation-0.228
Top resid features:
covered
Token covered
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
formulations
Token formulations
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Changes
Token Changes
Feature activation-0.057
Top resid features:
in
Token in
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
way
Token way
Feature activation+5.476
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
global
Token global
Feature activation-0.028
Top resid features:
ized
Tokenized
Feature activation-0.021
Top resid features:
capitalist
Token capitalist
Feature activation-0.027
Top resid features:
order
Token order
Feature activation+0.258
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
re
Tokenre
Feature activation+0.009
Top resid features:
doing
Token doing
Feature activation-0.011
Top resid features:
it
Token it
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.071
Top resid features:
way
Token way
Feature activation+5.072
Top resid features:
that
Token that
Feature activation+0.070
Top resid features:
Anon
Token Anon
Feature activation-0.087
Top resid features:
ab
Tokenab
Feature activation-0.027
Top resid features:
ox
Tokenox
Feature activation-0.018
Top resid features:
should
Token should
Feature activation-0.069
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.48

Head 2: 0.02

Head 3: 0.07

Head 4: 0.04

Head 5: 0.04

Head 6: 0.05

Head 7: 0.11

Head 8: 0.02

Head 9: 0.06

Head 10: 0.01

Head 11: 0.08

Positive logits

fare1.52

phr1.46

fares1.34

fared1.30

react1.28

vulner1.28

traditionally1.27

raph1.26

structured1.26

processed1.26

handled1.25

interact1.23

unfolded1.21

reacted1.21

behave1.20

operates1.20

Dill1.19

Virgin1.19

interacts1.19

handle1.18

Negative logits

milo-1.45

phrine-1.38

voy-1.36

OTOS-1.33

使-1.33

technical-1.25

%);-1.24

teness-1.24

TERN-1.23

899-1.23

ikers-1.23

mberg-1.22

clipse-1.21

ikes-1.21

985-1.21

actory-1.21

osate-1.20

requisites-1.20

cluding-1.17

enium-1.17

INTERVAL 5.009 - 5.566
CONTAINS 0.000%

the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
news
Token news
Feature activation+1.547
stories
Token stories
Feature activation+3.715
are
Token are
Feature activation+4.236
covered
Token covered
Feature activation+5.244
to
Token to
Feature activation+0.000
national
Token national
Feature activation+0.000
political
Token political
Feature activation+0.000
issues
Token issues
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.212
and
Token and
Feature activation+1.204
businesses
Token businesses
Feature activation+2.916
transact
Token transact
Feature activation+5.083
,
Token,
Feature activation+2.558
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
will
Token will
Feature activation+0.000
grow
Token grow
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
a
Token a
Feature activation+1.810
plant
Token plant
Feature activation+2.916
grows
Token grows
Feature activation+5.365
on
Token on
Feature activation+3.532
rabbit
Token rabbit
Feature activation+0.000
manure
Token manure
Feature activation+0.384
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
it
Token it
Feature activation+2.135
all
Token all
Feature activation+2.410
went
Token went
Feature activation+5.566
down
Token down
Feature activation+2.903
,
Token,
Feature activation+1.514
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
posted
Token posted
Feature activation+0.000

INTERVAL 4.453 - 5.009
CONTAINS 0.001%

of
Token of
Feature activation+0.142
personal
Token personal
Feature activation+0.000
and
Token and
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
behaviour
Token behaviour
Feature activation+0.628
are
Token are
Feature activation+4.777
handled
Token handled
Feature activation+4.350
by
Token by
Feature activation+2.791
society
Token society
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
everything
Token everything
Feature activation+0.000
goes
Token goes
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+0.735
plan
Token plan
Feature activation+4.516
and
Token and
Feature activation+1.042
I
Token I
Feature activation+0.418
have
Token have
Feature activation+0.000
faith
Token faith
Feature activation+0.000
that
Token that
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.437
look
Token look
Feature activation+3.433
at
Token at
Feature activation+4.492
food
Token food
Feature activation+0.270
.
Token.
Feature activation+0.182
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
they
Token they
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+1.660
present
Token present
Feature activation+4.643
themselves
Token themselves
Feature activation+3.572
and
Token and
Feature activation+1.369
it
Token it
Feature activation+0.110
gets
Token gets
Feature activation+0.000
over
Token over
Feature activation+0.000
believe
Token believe
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+0.707
general
Token general
Feature activation+4.003
ize
Tokenize
Feature activation+4.606
all
Token all
Feature activation+0.831
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.200
and
Token and
Feature activation+0.000

INTERVAL 3.896 - 4.453
CONTAINS 0.002%

everything
Token everything
Feature activation+0.000
appearing
Token appearing
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
it
Token it
Feature activation+2.844
should
Token should
Feature activation+4.244
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
settled
Token settled
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
this
Token this
Feature activation+0.723
optimization
Token optimization
Feature activation+0.000
is
Token is
Feature activation+3.608
implemented
Token implemented
Feature activation+3.993
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
additional
Token additional
Feature activation+0.000
virtual
Token virtual
Feature activation+0.000
table
Token table
Feature activation+0.000
Anon
Token Anon
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
ox
Tokenox
Feature activation+0.000
should
Token should
Feature activation+3.723
have
Token have
Feature activation+1.386
done
Token done
Feature activation+4.152
it
Token it
Feature activation+0.675
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PORT
TokenPORT
Feature activation+0.000
global
Token global
Feature activation+1.406
ized
Tokenized
Feature activation+1.227
capitalist
Token capitalist
Feature activation+0.000
order
Token order
Feature activation+0.289
is
Token is
Feature activation+3.932
organized
Token organized
Feature activation+4.213
,
Token,
Feature activation+1.036
particularly
Token particularly
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
me
Token me
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+0.621
raise
Token raise
Feature activation+3.975
my
Token my
Feature activation+2.732
kid
Token kid
Feature activation+0.988
.
Token.
Feature activation+0.000
Ye
Token Ye
Feature activation+0.000
a
Tokena
Feature activation+0.000

INTERVAL 3.339 - 3.896
CONTAINS 0.003%

the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
the
Token the
Feature activation+1.225
season
Token season
Feature activation+0.464
is
Token is
Feature activation+4.284
going
Token going
Feature activation+3.575
,
Token,
Feature activation+0.090
all
Token all
Feature activation+0.000
at
Token at
Feature activation+0.000
19
Token 19
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
camera
Token camera
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+1.296
do
Token do
Feature activation+3.743
on
Token on
Feature activation+2.336
the
Token the
Feature activation+1.064
S
Token S
Feature activation+0.000
8
Token8
Feature activation+0.000
and
Token and
Feature activation+0.000
changes
Token changes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
we
Token we
Feature activation+1.583
handle
Token handle
Feature activation+3.422
the
Token the
Feature activation+2.572
review
Token review
Feature activation+0.148
process
Token process
Feature activation+0.835
for
Token for
Feature activation+0.000
tax
Token tax
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
this
Token this
Feature activation+0.431
game
Token game
Feature activation+1.717
is
Token is
Feature activation+3.713
at
Token at
Feature activation+3.654
the
Token the
Feature activation+0.000
moment
Token moment
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+1.660
present
Token present
Feature activation+4.643
themselves
Token themselves
Feature activation+3.572
and
Token and
Feature activation+1.369
it
Token it
Feature activation+0.110
gets
Token gets
Feature activation+0.000
over
Token over
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 2.783 - 3.339
CONTAINS 0.005%

created
Token created
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+2.121
heard
Token heard
Feature activation+3.097
and
Token and
Feature activation+2.488
felt
Token felt
Feature activation+1.823
it
Token it
Feature activation+2.735
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
literally
Token literally
Feature activation+0.000
everyone
Token everyone
Feature activation+4.088
looks
Token looks
Feature activation+4.458
at
Token at
Feature activation+3.322
m
Token m
Feature activation+0.000
eryl
Tokeneryl
Feature activation+0.000
stre
Token stre
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
pic
Token pic
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+1.092
saw
Token saw
Feature activation+3.177
it
Token it
Feature activation+3.056
from
Token from
Feature activation+1.045
overseas
Token overseas
Feature activation+0.000
,
Token,
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
changing
Token changing
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.212
and
Token and
Feature activation+1.204
businesses
Token businesses
Feature activation+2.916
transact
Token transact
Feature activation+5.083
,
Token,
Feature activation+2.558
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
higher
Token higher
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
the
Token the
Feature activation+0.988
artist
Token artist
Feature activation+2.874
made
Token made
Feature activation+2.688
it
Token it
Feature activation+3.855
,
Token,
Feature activation+1.072
exactly
Token exactly
Feature activation+0.089
.
Token.
Feature activation+0.000

INTERVAL 2.226 - 2.783
CONTAINS 0.004%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
To
Token To
Feature activation+0.000
this
Token this
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+1.400
thinking
Token thinking
Feature activation+2.433
,
Token,
Feature activation+0.181
poverty
Token poverty
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
things
Token things
Feature activation+1.484
are
Token are
Feature activation+2.402
;
Token;
Feature activation+0.051
diversity
Token diversity
Feature activation+0.000
was
Token was
Feature activation+0.000
often
Token often
Feature activation+0.000
contentious
Token contentious
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
ways
Token ways
Feature activation+0.000
users
Token users
Feature activation+0.860
interacted
Token interacted
Feature activation+2.497
with
Token with
Feature activation+2.286
it
Token it
Feature activation+0.441
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
typically
Token typically
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+0.621
raise
Token raise
Feature activation+3.975
my
Token my
Feature activation+2.732
kid
Token kid
Feature activation+0.988
.
Token.
Feature activation+0.000
Ye
Token Ye
Feature activation+0.000
a
Tokena
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
the
Token the
Feature activation+0.988
artist
Token artist
Feature activation+2.874
made
Token made
Feature activation+2.688
it
Token it
Feature activation+3.855
,
Token,
Feature activation+1.072
exactly
Token exactly
Feature activation+0.089
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000

INTERVAL 1.670 - 2.226
CONTAINS 0.005%

to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+0.319
conserve
Token conserve
Feature activation+2.172
,
Token,
Feature activation+0.000
manage
Token manage
Feature activation+0.000
or
Token or
Feature activation+0.000
obtain
Token obtain
Feature activation+0.000
water
Token water
Feature activation+0.000
questions
Token questions
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
Robertson
Token Robertson
Feature activation+0.000
handled
Token handled
Feature activation+1.903
the
Token the
Feature activation+1.497
succession
Token succession
Feature activation+0.000
process
Token process
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.127
learn
Token learn
Feature activation+2.947
to
Token to
Feature activation+2.872
perceive
Token perceive
Feature activation+2.162
the
Token the
Feature activation+0.778
world
Token world
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
movies
Token movies
Feature activation+0.000
the
Token the
Feature activation+0.000
creative
Token creative
Feature activation+0.000
way
Token way
Feature activation+0.000
Baker
Token Baker
Feature activation+0.000
promoted
Token promoted
Feature activation+4.286
the
Token the
Feature activation+2.148
brand
Token brand
Feature activation+0.218
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.467
to
Token to
Feature activation+0.812
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
way
Token way
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+1.757
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Paul
TokenPaul
Feature activation+0.000
Morris
Token Morris
Feature activation+0.000

INTERVAL 1.113 - 1.670
CONTAINS 0.010%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
known
Tokenknown
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.188
measuring
Token measuring
Feature activation+1.457
the
Token the
Feature activation+0.000
age
Token age
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
tree
Token tree
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
characters
Token characters
Feature activation+0.271
are
Token are
Feature activation+2.773
just
Token just
Feature activation+1.251
coming
Token coming
Feature activation+1.232
right
Token right
Feature activation+0.515
at
Token at
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000
traditional
Token traditional
Feature activation+0.130
four
Token four
Feature activation+0.000
or
Token or
Feature activation+0.000
five
Token five
Feature activation+0.000
piece
Token piece
Feature activation+0.788
band
Token band
Feature activation+1.188
could
Token could
Feature activation+1.721
stir
Token stir
Feature activation+2.383
us
Token us
Feature activation+0.213
up
Token up
Feature activation+0.000
enough
Token enough
Feature activation+0.000
saw
Token saw
Feature activation+0.000
something
Token something
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+1.162
she
Token she
Feature activation+1.336
denied
Token denied
Feature activation+0.971
knowing
Token knowing
Feature activation+0.000
anything
Token anything
Feature activation+0.000
about
Token about
Feature activation+0.000
significant
Token significant
Feature activation+0.000
changes
Token changes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
we
Token we
Feature activation+1.583
handle
Token handle
Feature activation+3.422
the
Token the
Feature activation+2.572
review
Token review
Feature activation+0.148
process
Token process
Feature activation+0.835
for
Token for
Feature activation+0.000

INTERVAL 0.557 - 1.113
CONTAINS 0.013%

revival
Token revival
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.988
bourbon
Token bourbon
Feature activation+0.000
have
Token have
Feature activation+0.000
expanded
Token expanded
Feature activation+0.000
exponentially
Token exponentially
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.054
poll
Token poll
Feature activation+0.256
was
Token was
Feature activation+3.671
set
Token set
Feature activation+3.862
up
Token up
Feature activation+3.588
to
Token to
Feature activation+0.683
allow
Token allow
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
votes
Token votes
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
the
Token the
Feature activation+0.475
rules
Token rules
Feature activation+0.740
are
Token are
Feature activation+3.780
written
Token written
Feature activation+3.027
for
Token for
Feature activation+0.459
the
Token the
Feature activation+0.000
Fire
Token Fire
Feature activation+0.000
and
Tokenand
Feature activation+0.000
arguably
Token arguably
Feature activation+0.000
distracting
Token distracting
Feature activation+0.000
)
Token)
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.973
watching
Token watching
Feature activation+1.112
a
Token a
Feature activation+0.000
film
Token film
Feature activation+0.000
.
Token.
Feature activation+0.000
Who
Token Who
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+3.127
learn
Token learn
Feature activation+2.947
to
Token to
Feature activation+2.872
perceive
Token perceive
Feature activation+2.162
the
Token the
Feature activation+0.778
world
Token world
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
movies
Token movies
Feature activation+0.000
have
Token have
Feature activation+0.091

INTERVAL 0.000 - 0.557
CONTAINS 99.957%

more
Token more
Feature activation+0.000
salads
Token salads
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Har
TokenHar
Feature activation+0.000
je
Tokenje
Feature activation+0.000
et
Tokenet
Feature activation+0.000
Singh
Token Singh
Feature activation+0.000
,
Token,
Feature activation+0.000
plant
Token plant
Feature activation+0.000
manager
Token manager
Feature activation+0.000
would
Token would
Feature activation+0.000
see
Token see
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
cup
Token cup
Feature activation+0.000
of
Token of
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
three
Token three
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
will
Token will
Feature activation+0.000
force
Token force
Feature activation+0.000
our
Token our
Feature activation+0.000
people
Token people
Feature activation+0.000
into
Token into
Feature activation+0.000
more
Token more
Feature activation+0.000
wars
Token wars
Feature activation+0.000
of
Token of
Feature activation+0.000
occupation
Token occupation
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.000
characters
Token characters
Feature activation+0.000
syn
Token syn
Feature activation+0.000
ced
Tokenced
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
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 H4.1: (feature 6399)

TOP ACTIVATIONS
MAX = 5.856

Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
Trump
Token Trump
Feature activation+2.848
could
Token could
Feature activation+5.472
do
Token do
Feature activation+5.856
is
Token is
Feature activation+0.000
talk
Token talk
Feature activation+0.359
about
Token about
Feature activation+0.304
his
Token his
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
.
Token.
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
Trump
Token Trump
Feature activation+2.848
could
Token could
Feature activation+5.472
do
Token do
Feature activation+5.856
is
Token is
Feature activation+0.000
talk
Token talk
Feature activation+0.359
about
Token about
Feature activation+0.304
his
Token his
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
she
Token she
Feature activation+4.128
has
Token has
Feature activation+4.404
to
Token to
Feature activation+4.851
do
Token do
Feature activation+5.131
is
Token is
Feature activation+0.584
tell
Token tell
Feature activation+0.112
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
all
Token all
Feature activation+0.000
it
Token it
Feature activation+3.576
has
Token has
Feature activation+3.851
done
Token done
Feature activation+5.079
is
Token is
Feature activation+0.000
attack
Token attack
Feature activation+0.000
the
Token the
Feature activation+0.000
BJP
Token BJP
Feature activation+0.000
through
Token through
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.526
had
Token had
Feature activation+3.559
to
Token to
Feature activation+4.651
do
Token do
Feature activation+4.906
to
Token to
Feature activation+2.716
get
Token get
Feature activation+0.000
laid
Token laid
Feature activation+0.000
was
Token was
Feature activation+0.000
go
Token go
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
she
Token she
Feature activation+4.128
has
Token has
Feature activation+4.404
to
Token to
Feature activation+4.851
do
Token do
Feature activation+5.131
is
Token is
Feature activation+0.584
tell
Token tell
Feature activation+0.112
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
she
Token she
Feature activation+3.492
wanted
Token wanted
Feature activation+4.839
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.639
enjoy
Token enjoy
Feature activation+0.000
herself
Token herself
Feature activation+0.000
,
Token,
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+3.206
have
Token have
Feature activation+3.396
to
Token to
Feature activation+4.557
do
Token do
Feature activation+4.802
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
rash
Token rash
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
says
Token says
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+2.801
need
Token need
Feature activation+4.759
to
Token to
Feature activation+4.623
know
Token know
Feature activation+4.737
about
Token about
Feature activation+1.820
the
Token the
Feature activation+0.000
mov
Token mov
Feature activation+0.000
says
Token says
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+2.801
need
Token need
Feature activation+4.759
to
Token to
Feature activation+4.623
know
Token know
Feature activation+4.737
about
Token about
Feature activation+1.820
the
Token the
Feature activation+0.000
mov
Token mov
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
she
Token she
Feature activation+3.675
wanted
Token wanted
Feature activation+4.713
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.687
take
Token take
Feature activation+0.000
over
Token over
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
There
Token There
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.526
had
Token had
Feature activation+3.559
to
Token to
Feature activation+4.651
do
Token do
Feature activation+4.906
to
Token to
Feature activation+2.716
get
Token get
Feature activation+0.000
laid
Token laid
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
they
Token they
Feature activation+3.721
care
Token care
Feature activation+4.638
about
Token about
Feature activation+4.517
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
money
Token money
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
.
Token.
Feature activation+0.000
Until
Token Until
Feature activation+0.000
then
Token then
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+4.293
had
Token had
Feature activation+4.633
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
New
TokenNew
Feature activation+0.000
USC
Token USC
Feature activation+0.000
survey
Token survey
Feature activation+0.000
finds
Token finds
Feature activation+0.000
This
TokenThis
Feature activation+0.000
says
Token says
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+2.801
need
Token need
Feature activation+4.759
to
Token to
Feature activation+4.623
know
Token know
Feature activation+4.737
about
Token about
Feature activation+1.820
the
Token the
Feature activation+0.000
mov
Token mov
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
tubes
Token tubes
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
I
Token I
Feature activation+2.699
could
Token could
Feature activation+3.938
see
Token see
Feature activation+4.587
was
Token was
Feature activation+0.134
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+3.206
have
Token have
Feature activation+3.396
to
Token to
Feature activation+4.557
do
Token do
Feature activation+4.802
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
they
Token they
Feature activation+3.721
care
Token care
Feature activation+4.638
about
Token about
Feature activation+4.517
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
money
Token money
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
They
Token They
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+4.241
see
Token see
Feature activation+4.437
is
Token is
Feature activation+0.000
increased
Token increased
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+4.029
have
Token have
Feature activation+3.953
to
Token to
Feature activation+4.426
offer
Token offer
Feature activation+3.741
to
Token to
Feature activation+1.750
our
Token our
Feature activation+0.000
community
Token community
Feature activation+0.000
is
Token is
Feature activation+0.000

Top DFA by src position
MAX = 5.779

discussing
Token discussing
Feature activation+0.018
Top resid features:
business
Token business
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Meanwhile
Token Meanwhile
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
all
Token all
Feature activation+5.779
Top resid features:
Trump
Token Trump
Feature activation+0.178
Top resid features:
could
Token could
Feature activation+0.554
Top resid features:
do
Token do
Feature activation+0.242
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.000
Top resid features:
discussing
Token discussing
Feature activation+0.018
Top resid features:
business
Token business
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Meanwhile
Token Meanwhile
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
all
Token all
Feature activation+5.601
Top resid features:
Trump
Token Trump
Feature activation+0.393
Top resid features:
could
Token could
Feature activation+0.297
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
uncomfortable
Token uncomfortable
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
all
Token all
Feature activation+5.533
Top resid features:
she
Token she
Feature activation+0.121
Top resid features:
has
Token has
Feature activation+0.061
Top resid features:
to
Token to
Feature activation+0.314
Top resid features:
do
Token do
Feature activation+0.107
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.030
Top resid features:
react
Token react
Feature activation-0.016
Top resid features:
soon
Token soon
Feature activation-0.029
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
but
Token but
Feature activation+0.006
Top resid features:
all
Token all
Feature activation+5.500
Top resid features:
it
Token it
Feature activation+0.041
Top resid features:
has
Token has
Feature activation+0.305
Top resid features:
done
Token done
Feature activation+0.286
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
attack
Token attack
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
anyway
Token anyway
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
There
Token There
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
all
Token all
Feature activation+5.393
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
had
Token had
Feature activation+0.053
Top resid features:
to
Token to
Feature activation+0.311
Top resid features:
do
Token do
Feature activation+0.114
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
uncomfortable
Token uncomfortable
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
all
Token all
Feature activation+5.452
Top resid features:
she
Token she
Feature activation+0.079
Top resid features:
has
Token has
Feature activation+0.164
Top resid features:
to
Token to
Feature activation+0.091
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
fault
Token fault
Feature activation+0.012
Top resid features:
of
Token of
Feature activation-0.013
Top resid features:
her
Token her
Feature activation+0.006
Top resid features:
own
Token own
Feature activation-0.010
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
All
Token All
Feature activation+5.436
Top resid features:
she
Token she
Feature activation+0.094
Top resid features:
wanted
Token wanted
Feature activation+0.292
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
enjoy
Token enjoy
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-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.017
Top resid features:
All
TokenAll
Feature activation+5.367
Top resid features:
you
Token you
Feature activation-0.006
Top resid features:
have
Token have
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.307
Top resid features:
do
Token do
Feature activation+0.173
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
This
TokenThis
Feature activation-0.003
Top resid features:
says
Token says
Feature activation-0.059
Top resid features:
all
Token all
Feature activation+5.764
Top resid features:
we
Token we
Feature activation-0.015
Top resid features:
need
Token need
Feature activation+0.115
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
This
TokenThis
Feature activation+0.006
Top resid features:
says
Token says
Feature activation+0.002
Top resid features:
all
Token all
Feature activation+5.521
Top resid features:
we
Token we
Feature activation-0.039
Top resid features:
need
Token need
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.278
Top resid features:
know
Token know
Feature activation+0.004
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
uphold
Token uphold
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
tradition
Token tradition
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
All
Token All
Feature activation+5.345
Top resid features:
she
Token she
Feature activation+0.101
Top resid features:
wanted
Token wanted
Feature activation+0.299
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
anyway
Token anyway
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
There
Token There
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
all
Token all
Feature activation+5.284
Top resid features:
you
Token you
Feature activation-0.015
Top resid features:
had
Token had
Feature activation+0.234
Top resid features:
to
Token to
Feature activation+0.072
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
local
Token local
Feature activation-0.009
Top resid features:
news
Token news
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
âĢ
Token âĢ
Feature activation-0.006
Top resid features:
ľ
Tokenľ
Feature activation-0.008
Top resid features:
All
TokenAll
Feature activation+5.310
Top resid features:
they
Token they
Feature activation+0.157
Top resid features:
care
Token care
Feature activation+0.183
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
or
Token or
Feature activation-0.002
Top resid features:
so
Token so
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Until
Token Until
Feature activation-0.008
Top resid features:
then
Token then
Feature activation+0.046
Top resid features:
all
Token all
Feature activation+5.214
Top resid features:
we
Token we
Feature activation+0.114
Top resid features:
had
Token had
Feature activation+0.327
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
New
TokenNew
Feature activation+0.000
Top resid features:
USC
Token USC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
This
TokenThis
Feature activation-0.024
Top resid features:
says
Token says
Feature activation-0.025
Top resid features:
all
Token all
Feature activation+5.394
Top resid features:
we
Token we
Feature activation-0.010
Top resid features:
need
Token need
Feature activation+0.202
Top resid features:
to
Token to
Feature activation+0.112
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
machines
Token machines
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
tubes
Token tubes
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
all
Token all
Feature activation+4.755
Top resid features:
I
Token I
Feature activation+0.109
Top resid features:
could
Token could
Feature activation+0.494
Top resid features:
see
Token see
Feature activation+0.123
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.012
Top resid features:
All
TokenAll
Feature activation+5.322
Top resid features:
you
Token you
Feature activation-0.026
Top resid features:
have
Token have
Feature activation+0.116
Top resid features:
to
Token to
Feature activation+0.155
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
local
Token local
Feature activation-0.005
Top resid features:
news
Token news
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
âĢ
Token âĢ
Feature activation-0.004
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
All
TokenAll
Feature activation+5.026
Top resid features:
they
Token they
Feature activation+0.067
Top resid features:
care
Token care
Feature activation+0.162
Top resid features:
about
Token about
Feature activation+0.279
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.006
Top resid features:
doubts
Token doubts
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
but
Token but
Feature activation+0.002
Top resid features:
now
Token now
Feature activation+0.023
Top resid features:
all
Token all
Feature activation+5.306
Top resid features:
you
Token you
Feature activation+0.008
Top resid features:
see
Token see
Feature activation+0.195
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
doubt
Token doubt
Feature activation+0.000
Top resid features:
injured
Token injured
Feature activation+0.011
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
night
Token night
Feature activation+0.014
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
all
Token all
Feature activation+5.034
Top resid features:
you
Token you
Feature activation+0.026
Top resid features:
have
Token have
Feature activation+0.152
Top resid features:
to
Token to
Feature activation+0.110
Top resid features:
offer
Token offer
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.47

Head 2: 0.02

Head 3: 0.07

Head 4: 0.03

Head 5: 0.06

Head 6: 0.05

Head 7: 0.10

Head 8: 0.02

Head 9: 0.04

Head 10: 0.01

Head 11: 0.11

Positive logits

soever1.45

fuss1.41

except1.40

INGS1.31

belts1.30

scanners1.28

chicks1.28

Pry1.26

Scully1.25

generators1.24

buckets1.23

negatives1.23

goodies1.23

CU1.20

Classes1.18

stands1.18

Sounds1.18

cans1.18

Learned1.18

lins1.17

Negative logits

mone-1.39

-1.35

uca-1.33

ector-1.32

otaur-1.29

��士-1.29

utton-1.28

-1.27

bishop-1.27

-1.24

utenant-1.24

omew-1.23

Minotaur-1.23

itus-1.22

nown-1.20

gur-1.19

azard-1.19

ildo-1.18

ogun-1.18

cellence-1.17

INTERVAL 5.270 - 5.856
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
Trump
Token Trump
Feature activation+2.848
could
Token could
Feature activation+5.472
do
Token do
Feature activation+5.856
is
Token is
Feature activation+0.000
talk
Token talk
Feature activation+0.359
about
Token about
Feature activation+0.304
his
Token his
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
Trump
Token Trump
Feature activation+2.848
could
Token could
Feature activation+5.472
do
Token do
Feature activation+5.856
is
Token is
Feature activation+0.000
talk
Token talk
Feature activation+0.359
about
Token about
Feature activation+0.304
his
Token his
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000

INTERVAL 4.685 - 5.270
CONTAINS 0.001%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
all
Token all
Feature activation+0.000
it
Token it
Feature activation+3.576
has
Token has
Feature activation+3.851
done
Token done
Feature activation+5.079
is
Token is
Feature activation+0.000
attack
Token attack
Feature activation+0.000
the
Token the
Feature activation+0.000
BJP
Token BJP
Feature activation+0.000
through
Token through
Feature activation+0.000
says
Token says
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+2.801
need
Token need
Feature activation+4.759
to
Token to
Feature activation+4.623
know
Token know
Feature activation+4.737
about
Token about
Feature activation+1.820
the
Token the
Feature activation+0.000
mov
Token mov
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
of
Token of
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+3.206
have
Token have
Feature activation+3.396
to
Token to
Feature activation+4.557
do
Token do
Feature activation+4.802
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
rash
Token rash
Feature activation+0.000
the
Token the
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
she
Token she
Feature activation+3.675
wanted
Token wanted
Feature activation+4.713
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.687
take
Token take
Feature activation+0.000
over
Token over
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
she
Token she
Feature activation+4.128
has
Token has
Feature activation+4.404
to
Token to
Feature activation+4.851
do
Token do
Feature activation+5.131
is
Token is
Feature activation+0.584
tell
Token tell
Feature activation+0.112
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 4.099 - 4.685
CONTAINS 0.002%

.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
they
Token they
Feature activation+3.721
care
Token care
Feature activation+4.638
about
Token about
Feature activation+4.517
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
money
Token money
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
now
Token now
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.449
is
Token is
Feature activation+1.313
needed
Token needed
Feature activation+4.408
to
Token to
Feature activation+1.676
program
Token program
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
IoT
Token IoT
Feature activation+0.000
projects
Token projects
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.422
do
Token do
Feature activation+4.378
is
Token is
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+2.508
need
Token need
Feature activation+4.032
to
Token to
Feature activation+4.148
know
Token know
Feature activation+3.111
about
Token about
Feature activation+1.097
the
Token the
Feature activation+0.000
catastrophic
Token catastrophic
Feature activation+0.000
anthrop
Token anthrop
Feature activation+0.000
doubts
Token doubts
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+4.241
see
Token see
Feature activation+4.437
is
Token is
Feature activation+0.000
increased
Token increased
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.513 - 4.099
CONTAINS 0.004%

plan
Token plan
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+1.717
would
Token would
Feature activation+3.554
be
Token be
Feature activation+3.691
required
Token required
Feature activation+3.772
.
Token.
Feature activation+0.000
Waiting
Token Waiting
Feature activation+0.000
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
place
Token place
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.371
have
Token have
Feature activation+3.685
for
Token for
Feature activation+3.845
directions
Token directions
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
vague
Token vague
Feature activation+0.000
take
Token take
Feature activation+0.000
other
Token other
Feature activation+0.000
guys
Token guys
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+3.684
can
Token can
Feature activation+4.096
do
Token do
Feature activation+4.675
now
Token now
Feature activation+0.254
is
Token is
Feature activation+0.000
train
Token train
Feature activation+0.000
guys
Token guys
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+3.684
can
Token can
Feature activation+4.096
do
Token do
Feature activation+4.675
now
Token now
Feature activation+0.254
is
Token is
Feature activation+0.000
train
Token train
Feature activation+0.000
very
Token very
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.526
had
Token had
Feature activation+3.559
to
Token to
Feature activation+4.651
do
Token do
Feature activation+4.906
to
Token to
Feature activation+2.716
get
Token get
Feature activation+0.000
laid
Token laid
Feature activation+0.000

INTERVAL 2.928 - 3.513
CONTAINS 0.003%

long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.000
they
Token they
Feature activation+3.141
are
Token are
Feature activation+0.241
doing
Token doing
Feature activation+3.099
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
place
Token place
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+3.371
have
Token have
Feature activation+3.685
for
Token for
Feature activation+3.845
directions
Token directions
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
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
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+3.206
have
Token have
Feature activation+3.396
to
Token to
Feature activation+4.557
do
Token do
Feature activation+4.802
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+2.219
need
Token need
Feature activation+3.448
to
Token to
Feature activation+3.709
make
Token make
Feature activation+0.347
this
Token this
Feature activation+0.000
guilt
Token guilt
Feature activation+0.000
-
Token-
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
mine
Tokenmine
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.618
needs
Token needs
Feature activation+3.406
if
Token if
Feature activation+0.000
required
Token required
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.342 - 2.928
CONTAINS 0.004%

ization
Tokenization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+2.526
have
Token have
Feature activation+2.390
to
Token to
Feature activation+3.362
do
Token do
Feature activation+4.137
is
Token is
Feature activation+0.000
tap
Token tap
Feature activation+0.000
conductor
Token conductor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+2.508
need
Token need
Feature activation+4.032
to
Token to
Feature activation+4.148
know
Token know
Feature activation+3.111
about
Token about
Feature activation+1.097
the
Token the
Feature activation+0.000
argument
Token argument
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
needs
Token needs
Feature activation+2.911
to
Token to
Feature activation+2.678
stop
Token stop
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
intuitive
Token intuitive
Feature activation+0.000
mindset
Token mindset
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.072
is
Token is
Feature activation+0.257
done
Token done
Feature activation+2.517
with
Token with
Feature activation+0.154
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
click
Token click
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+1.894
need
Token need
Feature activation+2.615
to
Token to
Feature activation+3.060
do
Token do
Feature activation+3.953
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
adjust
Token adjust
Feature activation+0.000

INTERVAL 1.757 - 2.342
CONTAINS 0.004%

forces
Token forces
Feature activation+0.000
threw
Token threw
Feature activation+0.000
all
Token all
Feature activation+0.000
they
Token they
Feature activation+2.261
had
Token had
Feature activation+3.061
at
Token at
Feature activation+1.977
the
Token the
Feature activation+0.182
island
Token island
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
on
Token on
Feature activation+0.000
As
Token As
Feature activation+0.000
Axis
Token Axis
Feature activation+0.000
forces
Token forces
Feature activation+0.000
threw
Token threw
Feature activation+0.000
all
Token all
Feature activation+0.000
they
Token they
Feature activation+2.261
had
Token had
Feature activation+3.061
at
Token at
Feature activation+1.977
the
Token the
Feature activation+0.182
island
Token island
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
All
TokenAll
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+2.196
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.068
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+2.424
was
Token was
Feature activation+1.787
playing
Token playing
Feature activation+1.052
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.359
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
where
Token where
Feature activation+0.000
all
Token all
Feature activation+0.000
at
Token at
Feature activation+0.000
once
Token once
Feature activation+0.450
there
Token there
Feature activation+0.412
is
Token is
Feature activation+1.801
none
Token none
Feature activation+0.000
.
Token.
Feature activation+0.000
Recogn
Token Recogn
Feature activation+0.000
ition
Tokenition
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.171 - 1.757
CONTAINS 0.007%

Supplement
TokenSupplement
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
protection
Token protection
Feature activation+0.000
(
Token (
Feature activation+0.000
all
Tokenall
Feature activation+0.000
TPP
Token TPP
Feature activation+1.354
countries
Token countries
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
US
Token US
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Figure
TokenFigure
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
ICE
Token ICE
Feature activation+1.509
Dep
Token Dep
Feature activation+0.093
ort
Tokenort
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
and
Token and
Feature activation+0.000
Det
Token Det
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.134
caucus
Token caucus
Feature activation+0.000
that
Token that
Feature activation+0.000
really
Token really
Feature activation+1.344
want
Token want
Feature activation+0.465
to
Token to
Feature activation+0.006
ban
Token ban
Feature activation+0.000
guns
Token guns
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
occur
Token occur
Feature activation+0.000
when
Token when
Feature activation+0.000
all
Token all
Feature activation+0.000
our
Token our
Feature activation+0.000
talent
Token talent
Feature activation+1.260
is
Token is
Feature activation+0.000
assembled
Token assembled
Feature activation+0.000
in
Token in
Feature activation+0.242
Baltimore
Token Baltimore
Feature activation+0.000
the
Token the
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
D
Token D
Feature activation+1.141
ax
Tokenax
Feature activation+1.301
am
Tokenam
Feature activation+0.940
ites
Tokenites
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 0.586 - 1.171
CONTAINS 0.018%

The
Token The
Feature activation+0.000
shelf
Token shelf
Feature activation+0.000
life
Token life
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
Obama
Token Obama
Feature activation+0.956
-
Token-
Feature activation+0.000
hat
Tokenhat
Feature activation+0.000
red
Tokenred
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
experts
Token experts
Feature activation+0.000
say
Token say
Feature activation+0.000
all
Token all
Feature activation+0.000
web
Token web
Feature activation+0.618
users
Token users
Feature activation+0.011
will
Token will
Feature activation+0.274
be
Token be
Feature activation+0.063
at
Token at
Feature activation+0.133
risk
Token risk
Feature activation+0.334
sure
Token sure
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
all
Token all
Feature activation+0.000
still
Token still
Feature activation+1.436
there
Token there
Feature activation+0.903
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.000
transported
Token transported
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
memory
Token memory
Feature activation+0.999
is
Token is
Feature activation+0.241
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
comes
Token comes
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
brow
Token brow
Feature activation+0.000
colour
Token colour
Feature activation+0.799
options
Token options
Feature activation+0.000
you
Token you
Feature activation+0.000
could
Token could
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
need
Token need
Feature activation+0.000

INTERVAL 0.000 - 0.586
CONTAINS 99.957%

Dana
Token Dana
Feature activation+0.000
White
Token White
Feature activation+0.000
interview
Token interview
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
always
Token always
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
colors
Token colors
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Select
TokenSelect
Feature activation+0.000
members
Token members
Feature activation+0.000
(
Token (
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
ual
Tokenual
Feature activation+0.000
fail
Token fail
Feature activation+0.000
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
trying
Token trying
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
know
Token know
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
someone
Token someone
Feature activation+0.000
came
Token came
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
house
Token house
Feature activation+0.000
of
Token of
Feature activation+0.000
J
Token J
Feature activation+0.000
air
Tokenair
Feature activation+0.000
us
Tokenus
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
q
Tokenq
Feature activation+0.000
bal
Tokenbal
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
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

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 H4.1: (feature 8317)

TOP ACTIVATIONS
MAX = 4.502

working
Token working
Feature activation+2.940
for
Token for
Feature activation+0.163
the
Token the
Feature activation+1.489
NSA
Token NSA
Feature activation+0.759
to
Token to
Feature activation+4.163
be
Token be
Feature activation+4.502
arrested
Token arrested
Feature activation+3.021
for
Token for
Feature activation+0.030
removing
Token removing
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
arrested
Token arrested
Feature activation+3.021
for
Token for
Feature activation+0.030
removing
Token removing
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
since
Token since
Feature activation+4.448
October
Token October
Feature activation+0.000
of
Token of
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
city
Token city
Feature activation+0.000
's
Token's
Feature activation+0.000
fourth
Token fourth
Feature activation+1.593
city
Token city
Feature activation+0.986
manager
Token manager
Feature activation+2.116
since
Token since
Feature activation+4.256
2009
Token 2009
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
medical
Token medical
Feature activation+0.589
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+1.421
to
Token to
Feature activation+4.237
ask
Token ask
Feature activation+1.262
the
Token the
Feature activation+0.000
DEA
Token DEA
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.871
election
Token election
Feature activation+3.309
in
Token in
Feature activation+4.027
a
Token a
Feature activation+4.191
row
Token row
Feature activation+3.182
in
Token in
Feature activation+3.075
which
Token which
Feature activation+2.909
Democrats
Token Democrats
Feature activation+0.000
prevailed
Token prevailed
Feature activation+0.000
person
Token person
Feature activation+3.090
working
Token working
Feature activation+2.940
for
Token for
Feature activation+0.163
the
Token the
Feature activation+1.489
NSA
Token NSA
Feature activation+0.759
to
Token to
Feature activation+4.163
be
Token be
Feature activation+4.502
arrested
Token arrested
Feature activation+3.021
for
Token for
Feature activation+0.030
removing
Token removing
Feature activation+0.000
classified
Token classified
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+3.769
derail
Token derail
Feature activation+3.750
ment
Tokenment
Feature activation+4.093
at
Token at
Feature activation+3.402
the
Token the
Feature activation+3.761
busy
Token busy
Feature activation+0.481
Manhattan
Token Manhattan
Feature activation+0.000
hub
Token hub
Feature activation+0.000
Fernand
Token Fernand
Feature activation+0.000
es
Tokenes
Feature activation+0.000
'
Token'
Feature activation+0.000
second
Token second
Feature activation+2.164
fight
Token fight
Feature activation+2.974
in
Token in
Feature activation+4.070
the
Token the
Feature activation+3.679
2016
Token 2016
Feature activation+3.262
calendar
Token calendar
Feature activation+2.332
.
Token.
Feature activation+0.118
Fernand
Token Fernand
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.871
election
Token election
Feature activation+3.309
in
Token in
Feature activation+4.027
a
Token a
Feature activation+4.191
row
Token row
Feature activation+3.182
in
Token in
Feature activation+3.075
which
Token which
Feature activation+2.909
Democrats
Token Democrats
Feature activation+0.000
and
Token and
Feature activation+0.000
second
Token second
Feature activation+0.075
Welsh
Token Welsh
Feature activation+2.794
man
Tokenman
Feature activation+2.744
,
Token,
Feature activation+0.030
to
Token to
Feature activation+3.853
take
Token take
Feature activation+3.496
charge
Token charge
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.028
Rugby
Token Rugby
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+1.615
state
Token state
Feature activation+3.306
with
Token with
Feature activation+3.687
a
Token a
Feature activation+3.836
medical
Token medical
Feature activation+0.589
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+1.421
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
complete
Token complete
Feature activation+2.121
dinosaur
Token dinosaur
Feature activation+0.879
skeleton
Token skeleton
Feature activation+2.172
unearthed
Token unearthed
Feature activation+3.785
in
Token in
Feature activation+1.622
Japan
Token Japan
Feature activation+0.172
after
Token after
Feature activation+0.713
Fuk
Token Fuk
Feature activation+0.000
u
Tokenu
Feature activation+0.000
for
Token for
Feature activation+3.042
the
Token the
Feature activation+1.944
Mount
Token Mount
Feature activation+0.487
aine
Tokenaine
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
this
Token this
Feature activation+3.782
offseason
Token offseason
Feature activation+2.664
following
Token following
Feature activation+1.828
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+3.769
derail
Token derail
Feature activation+3.750
ment
Tokenment
Feature activation+4.093
at
Token at
Feature activation+3.402
the
Token the
Feature activation+3.761
busy
Token busy
Feature activation+0.481
the
Token the
Feature activation+0.000
second
Token second
Feature activation+3.769
derail
Token derail
Feature activation+3.750
ment
Tokenment
Feature activation+4.093
at
Token at
Feature activation+3.402
the
Token the
Feature activation+3.761
busy
Token busy
Feature activation+0.481
Manhattan
Token Manhattan
Feature activation+0.000
hub
Token hub
Feature activation+0.000
in
Token in
Feature activation+3.284
11
Token 11
Feature activation+2.862
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+3.769
derail
Token derail
Feature activation+3.750
ment
Tokenment
Feature activation+4.093
at
Token at
Feature activation+3.402
the
Token the
Feature activation+3.761
busy
Token busy
Feature activation+0.481
Manhattan
Token Manhattan
Feature activation+0.000
of
Token of
Feature activation+2.336
the
Token the
Feature activation+1.738
3
Token 3
Feature activation+0.623
DS
TokenDS
Feature activation+0.142
family
Token family
Feature activation+0.082
released
Token released
Feature activation+3.748
in
Token in
Feature activation+2.446
as
Token as
Feature activation+3.505
many
Token many
Feature activation+2.211
years
Token years
Feature activation+1.274
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
Leafs
Token Leafs
Feature activation+0.914
goaltender
Token goaltender
Feature activation+1.425
to
Token to
Feature activation+3.689
record
Token record
Feature activation+2.157
a
Token a
Feature activation+1.716
shut
Token shut
Feature activation+0.000
out
Tokenout
Feature activation+0.000
in
Token in
Feature activation+2.065
Colorado
TokenColorado
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+1.615
state
Token state
Feature activation+3.306
with
Token with
Feature activation+3.687
a
Token a
Feature activation+3.836
medical
Token medical
Feature activation+0.589
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
es
Tokenes
Feature activation+0.000
'
Token'
Feature activation+0.000
second
Token second
Feature activation+2.164
fight
Token fight
Feature activation+2.974
in
Token in
Feature activation+4.070
the
Token the
Feature activation+3.679
2016
Token 2016
Feature activation+3.262
calendar
Token calendar
Feature activation+2.332
.
Token.
Feature activation+0.118
Fernand
Token Fernand
Feature activation+0.000
es
Tokenes
Feature activation+0.000

Top DFA by src position
MAX = 4.944

Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ph
TokenPh
Feature activation-0.008
Top resid features:
o
Tokeno
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
third
Token third
Feature activation+4.944
Top resid features:
person
Token person
Feature activation+0.074
Top resid features:
working
Token working
Feature activation+0.054
Top resid features:
for
Token for
Feature activation+0.117
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
NSA
Token NSA
Feature activation-0.072
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ph
TokenPh
Feature activation-0.005
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
third
Token third
Feature activation+4.931
Top resid features:
person
Token person
Feature activation+0.040
Top resid features:
working
Token working
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
NSA
Token NSA
Feature activation-0.013
Top resid features:
ata
Tokenata
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
city
Token city
Feature activation+0.002
Top resid features:
's
Token's
Feature activation-0.034
Top resid features:
fourth
Token fourth
Feature activation+4.523
Top resid features:
city
Token city
Feature activation+0.093
Top resid features:
manager
Token manager
Feature activation+0.312
Top resid features:
since
Token since
Feature activation+0.053
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Colorado
TokenColorado
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
third
Token third
Feature activation+4.692
Top resid features:
state
Token state
Feature activation+0.043
Top resid features:
with
Token with
Feature activation+0.106
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
medical
Token medical
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
this
Token this
Feature activation+0.015
Top resid features:
will
Token will
Feature activation-0.002
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
third
Token third
Feature activation+4.823
Top resid features:
election
Token election
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.134
Top resid features:
a
Token a
Feature activation-0.015
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ph
TokenPh
Feature activation-0.005
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
third
Token third
Feature activation+4.560
Top resid features:
person
Token person
Feature activation+0.093
Top resid features:
working
Token working
Feature activation+0.021
Top resid features:
for
Token for
Feature activation+0.144
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
NSA
Token NSA
Feature activation+0.099
Top resid features:
morning
Token morning
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
It
Token It
Feature activation-0.019
Top resid features:
was
Token was
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
second
Token second
Feature activation+4.570
Top resid features:
derail
Token derail
Feature activation+0.109
Top resid features:
ment
Tokenment
Feature activation+0.135
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
busy
Token busy
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.006
Top resid features:
marks
Token marks
Feature activation+0.018
Top resid features:
Fernand
Token Fernand
Feature activation-0.026
Top resid features:
es
Tokenes
Feature activation+0.010
Top resid features:
'
Token'
Feature activation+0.064
Top resid features:
second
Token second
Feature activation+4.207
Top resid features:
fight
Token fight
Feature activation+0.260
Top resid features:
in
Token in
Feature activation+0.155
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
2016
Token 2016
Feature activation+0.000
Top resid features:
calendar
Token calendar
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
this
Token this
Feature activation+0.014
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
third
Token third
Feature activation+4.669
Top resid features:
election
Token election
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.091
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
O
TokenO
Feature activation-0.003
Top resid features:
w
Tokenw
Feature activation+0.003
Top resid features:
ens
Tokenens
Feature activation-0.001
Top resid features:
became
Token became
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.021
Top resid features:
seventh
Token seventh
Feature activation+4.228
Top resid features:
referee
Token referee
Feature activation+0.024
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
second
Token second
Feature activation+0.083
Top resid features:
Welsh
Token Welsh
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Colorado
TokenColorado
Feature activation-0.005
Top resid features:
is
Token is
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
third
Token third
Feature activation+4.246
Top resid features:
state
Token state
Feature activation+0.097
Top resid features:
with
Token with
Feature activation+0.157
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
medical
Token medical
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
aw
Tokenaw
Feature activation-0.003
Top resid features:
ary
Tokenary
Feature activation+0.001
Top resid features:
u
Tokenu
Feature activation-0.001
Top resid features:
represents
Token represents
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
second
Token second
Feature activation+4.012
Top resid features:
complete
Token complete
Feature activation+0.038
Top resid features:
dinosaur
Token dinosaur
Feature activation+0.094
Top resid features:
skeleton
Token skeleton
Feature activation+0.269
Top resid features:
unearthed
Token unearthed
Feature activation+0.076
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
departure
Token departure
Feature activation+0.034
Top resid features:
is
Token is
Feature activation-0.036
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
second
Token second
Feature activation+4.122
Top resid features:
high
Token high
Feature activation+0.019
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
profile
Tokenprofile
Feature activation+0.011
Top resid features:
transfer
Token transfer
Feature activation+0.015
Top resid features:
for
Token for
Feature activation+0.123
Top resid features:
morning
Token morning
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
It
Token It
Feature activation-0.022
Top resid features:
was
Token was
Feature activation+0.073
Top resid features:
the
Token the
Feature activation-0.072
Top resid features:
second
Token second
Feature activation+4.538
Top resid features:
derail
Token derail
Feature activation+0.000
Top resid features:
ment
Tokenment
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
busy
Token busy
Feature activation+0.000
Top resid features:
morning
Token morning
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
It
Token It
Feature activation-0.012
Top resid features:
was
Token was
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
second
Token second
Feature activation+4.093
Top resid features:
derail
Token derail
Feature activation+0.091
Top resid features:
ment
Tokenment
Feature activation+0.079
Top resid features:
at
Token at
Feature activation+0.253
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
busy
Token busy
Feature activation+0.000
Top resid features:
morning
Token morning
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.043
Top resid features:
It
Token It
Feature activation-0.025
Top resid features:
was
Token was
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
second
Token second
Feature activation+4.375
Top resid features:
derail
Token derail
Feature activation+0.154
Top resid features:
ment
Tokenment
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
busy
Token busy
Feature activation+0.000
Top resid features:
But
Token But
Feature activation-0.029
Top resid features:
since
Token since
Feature activation-0.007
Top resid features:
this
Token this
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
sixth
Token sixth
Feature activation+3.684
Top resid features:
member
Token member
Feature activation+0.160
Top resid features:
of
Token of
Feature activation+0.095
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
3
Token 3
Feature activation+0.040
Top resid features:
DS
TokenDS
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
He
Token He
Feature activation-0.034
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
only
Token only
Feature activation-0.056
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
second
Token second
Feature activation+4.146
Top resid features:
Leafs
Token Leafs
Feature activation+0.033
Top resid features:
goaltender
Token goaltender
Feature activation+0.220
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
record
Token record
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Colorado
TokenColorado
Feature activation-0.014
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
third
Token third
Feature activation+4.270
Top resid features:
state
Token state
Feature activation+0.068
Top resid features:
with
Token with
Feature activation+0.036
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
medical
Token medical
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
marks
Token marks
Feature activation+0.016
Top resid features:
Fernand
Token Fernand
Feature activation-0.022
Top resid features:
es
Tokenes
Feature activation+0.008
Top resid features:
'
Token'
Feature activation+0.043
Top resid features:
second
Token second
Feature activation+3.988
Top resid features:
fight
Token fight
Feature activation+0.114
Top resid features:
in
Token in
Feature activation+0.121
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
2016
Token 2016
Feature activation+0.000
Top resid features:
calendar
Token calendar
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.47

Head 2: 0.02

Head 3: 0.04

Head 4: 0.02

Head 5: 0.08

Head 6: 0.05

Head 7: 0.09

Head 8: 0.02

Head 9: 0.06

Head 10: 0.02

Head 11: 0.09

Positive logits

surveyed1.36

ever1.25

secut1.23

nationwide1.20

consecutive1.19

pires1.17

consecut1.16

imaginable1.16

clusive1.15

icipated1.14

ivalent1.13

veyard1.13

whiff1.12

approvals1.12

scrimmage1.12

anniversary1.11

phthal1.11

IEEE1.10

ird1.09

mish1.09

Negative logits

luaj-1.33

=#-1.28

adders-1.27

olor-1.24

ADRA-1.23

Versions-1.23

Daddy-1.20

ahime-1.19

zek-1.17

DX-1.16

tle-1.14

ufact-1.13

behav-1.12

terness-1.10

Pub-1.09

aff-1.08

Stability-1.08

adeon-1.07

tnc-1.07

-1.07

INTERVAL 4.052 - 4.502
CONTAINS 0.001%

working
Token working
Feature activation+2.940
for
Token for
Feature activation+0.163
the
Token the
Feature activation+1.489
NSA
Token NSA
Feature activation+0.759
to
Token to
Feature activation+4.163
be
Token be
Feature activation+4.502
arrested
Token arrested
Feature activation+3.021
for
Token for
Feature activation+0.030
removing
Token removing
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
medical
Token medical
Feature activation+0.589
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+1.421
to
Token to
Feature activation+4.237
ask
Token ask
Feature activation+1.262
the
Token the
Feature activation+0.000
DEA
Token DEA
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
city
Token city
Feature activation+0.000
's
Token's
Feature activation+0.000
fourth
Token fourth
Feature activation+1.593
city
Token city
Feature activation+0.986
manager
Token manager
Feature activation+2.116
since
Token since
Feature activation+4.256
2009
Token 2009
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
arrested
Token arrested
Feature activation+3.021
for
Token for
Feature activation+0.030
removing
Token removing
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
since
Token since
Feature activation+4.448
October
Token October
Feature activation+0.000
of
Token of
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Fernand
Token Fernand
Feature activation+0.000
es
Tokenes
Feature activation+0.000
'
Token'
Feature activation+0.000
second
Token second
Feature activation+2.164
fight
Token fight
Feature activation+2.974
in
Token in
Feature activation+4.070
the
Token the
Feature activation+3.679
2016
Token 2016
Feature activation+3.262
calendar
Token calendar
Feature activation+2.332
.
Token.
Feature activation+0.118
Fernand
Token Fernand
Feature activation+0.000

INTERVAL 3.601 - 4.052
CONTAINS 0.001%

isl
Tokenisl
Feature activation+0.000
ava
Tokenava
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+1.236
time
Token time
Feature activation+3.644
now
Token now
Feature activation+1.541
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
gathered
Token gathered
Feature activation+0.000
some
Token some
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.871
election
Token election
Feature activation+3.309
in
Token in
Feature activation+4.027
a
Token a
Feature activation+4.191
row
Token row
Feature activation+3.182
in
Token in
Feature activation+3.075
which
Token which
Feature activation+2.909
Democrats
Token Democrats
Feature activation+0.000
and
Token and
Feature activation+0.000
second
Token second
Feature activation+0.075
Welsh
Token Welsh
Feature activation+2.794
man
Tokenman
Feature activation+2.744
,
Token,
Feature activation+0.030
to
Token to
Feature activation+3.853
take
Token take
Feature activation+3.496
charge
Token charge
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.028
Rugby
Token Rugby
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
complete
Token complete
Feature activation+2.121
dinosaur
Token dinosaur
Feature activation+0.879
skeleton
Token skeleton
Feature activation+2.172
unearthed
Token unearthed
Feature activation+3.785
in
Token in
Feature activation+1.622
Japan
Token Japan
Feature activation+0.172
after
Token after
Feature activation+0.713
Fuk
Token Fuk
Feature activation+0.000
u
Tokenu
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+3.769
derail
Token derail
Feature activation+3.750
ment
Tokenment
Feature activation+4.093
at
Token at
Feature activation+3.402
the
Token the
Feature activation+3.761
busy
Token busy
Feature activation+0.481
Manhattan
Token Manhattan
Feature activation+0.000
hub
Token hub
Feature activation+0.000
in
Token in
Feature activation+3.284
11
Token 11
Feature activation+2.862

INTERVAL 3.151 - 3.601
CONTAINS 0.002%

sixth
Token sixth
Feature activation+1.531
player
Token player
Feature activation+2.359
in
Token in
Feature activation+2.278
Ot
Token Ot
Feature activation+0.221
ters
Tokenters
Feature activation+0.871
history
Token history
Feature activation+3.246
to
Token to
Feature activation+3.454
reach
Token reach
Feature activation+2.856
100
Token 100
Feature activation+0.000
points
Token points
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+1.668
Israel
Token Israel
Feature activation+2.624
-
Token-
Feature activation+0.030
related
Tokenrelated
Feature activation+0.436
scandal
Token scandal
Feature activation+3.154
tied
Token tied
Feature activation+3.615
to
Token to
Feature activation+1.661
Georgia
Token Georgia
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
.
Token.
Feature activation+0.313
'
Token'
Feature activation+0.000
second
Token second
Feature activation+2.164
fight
Token fight
Feature activation+2.974
in
Token in
Feature activation+4.070
the
Token the
Feature activation+3.679
2016
Token 2016
Feature activation+3.262
calendar
Token calendar
Feature activation+2.332
.
Token.
Feature activation+0.118
Fernand
Token Fernand
Feature activation+0.000
es
Tokenes
Feature activation+0.000
'
Token'
Feature activation+0.000
3
Token 3
Feature activation+0.623
DS
TokenDS
Feature activation+0.142
family
Token family
Feature activation+0.082
released
Token released
Feature activation+3.748
in
Token in
Feature activation+2.446
as
Token as
Feature activation+3.505
many
Token many
Feature activation+2.211
years
Token years
Feature activation+1.274
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
busy
Token busy
Feature activation+0.481
Manhattan
Token Manhattan
Feature activation+0.000
hub
Token hub
Feature activation+0.000
in
Token in
Feature activation+3.284
11
Token 11
Feature activation+2.862
days
Token days
Feature activation+3.235
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
involved
Token involved
Feature activation+0.000
an
Token an
Feature activation+0.329

INTERVAL 2.701 - 3.151
CONTAINS 0.004%

election
Token election
Feature activation+3.309
in
Token in
Feature activation+4.027
a
Token a
Feature activation+4.191
row
Token row
Feature activation+3.182
in
Token in
Feature activation+3.075
which
Token which
Feature activation+2.909
Democrats
Token Democrats
Feature activation+0.000
prevailed
Token prevailed
Feature activation+0.000
with
Token with
Feature activation+0.000
young
Token young
Feature activation+0.000
voters
Token voters
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.871
election
Token election
Feature activation+3.309
in
Token in
Feature activation+4.027
a
Token a
Feature activation+4.191
row
Token row
Feature activation+3.182
in
Token in
Feature activation+3.075
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
year
Token year
Feature activation+2.816
in
Token in
Feature activation+0.766
a
Token a
Feature activation+3.040
row
Token row
Feature activation+3.066
the
Token the
Feature activation+0.000
Lamar
Token Lamar
Feature activation+0.000
Hunt
Token Hunt
Feature activation+0.000
US
Token US
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Tigers
Token Tigers
Feature activation+0.000
'
Token'
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
win
Token win
Feature activation+2.566
in
Token in
Feature activation+2.908
five
Token five
Feature activation+2.690
games
Token games
Feature activation+0.858
drew
Token drew
Feature activation+0.000
them
Token them
Feature activation+0.000
back
Token back
Feature activation+0.000
its
Token its
Feature activation+0.000
third
Token third
Feature activation+0.458
national
Token national
Feature activation+2.555
championship
Token championship
Feature activation+2.658
in
Token in
Feature activation+2.897
four
Token four
Feature activation+2.910
years
Token years
Feature activation+3.250
.
Token.
Feature activation+0.000
Ann
Token Ann
Feature activation+0.000
ika
Tokenika
Feature activation+0.000
D
Token D
Feature activation+0.000

INTERVAL 2.251 - 2.701
CONTAINS 0.004%

s
Tokens
Feature activation+0.000
departure
Token departure
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+2.283
high
Token high
Feature activation+2.435
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+2.417
transfer
Token transfer
Feature activation+3.094
for
Token for
Feature activation+3.042
the
Token the
Feature activation+1.944
value
Token value
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
second
Token second
Feature activation+1.035
full
Token full
Feature activation+2.424
season
Token season
Feature activation+0.769
with
Token with
Feature activation+1.671
Minnesota
Token Minnesota
Feature activation+0.000
,
Token,
Feature activation+0.000
P
Token P
Feature activation+0.000
O
TokenO
Feature activation+0.000
w
Tokenw
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
became
Token became
Feature activation+0.000
the
Token the
Feature activation+0.000
seventh
Token seventh
Feature activation+2.574
referee
Token referee
Feature activation+0.704
,
Token,
Feature activation+0.590
and
Token and
Feature activation+0.000
second
Token second
Feature activation+0.075
Welsh
Token Welsh
Feature activation+2.794
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
such
Token such
Feature activation+1.303
discovery
Token discovery
Feature activation+2.727
in
Token in
Feature activation+2.769
the
Token the
Feature activation+2.685
world
Token world
Feature activation+2.273
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
complete
Token complete
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Tigers
Token Tigers
Feature activation+0.000
'
Token'
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
win
Token win
Feature activation+2.566
in
Token in
Feature activation+2.908
five
Token five
Feature activation+2.690
games
Token games
Feature activation+0.858
drew
Token drew
Feature activation+0.000
them
Token them
Feature activation+0.000

INTERVAL 1.801 - 2.251
CONTAINS 0.004%

trial
Token trial
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
fifth
Token fifth
Feature activation+1.592
week
Token week
Feature activation+2.224
.
Token.
Feature activation+0.000
Jury
Token Jury
Feature activation+0.000
deliberations
Token deliberations
Feature activation+0.000
could
Token could
Feature activation+0.000
begin
Token begin
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
Maurice
Token Maurice
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
second
Token second
Feature activation+1.743
international
Token international
Feature activation+2.231
goal
Token goal
Feature activation+2.106
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
On
TokenOn
Feature activation+0.000
his
Token his
Feature activation+0.000
fourth
Token fourth
Feature activation+0.215
full
Token full
Feature activation+2.500
day
Token day
Feature activation+2.165
in
Token in
Feature activation+1.523
office
Token office
Feature activation+0.000
,
Token,
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
to
Token to
Feature activation+3.689
record
Token record
Feature activation+2.157
a
Token a
Feature activation+1.716
shut
Token shut
Feature activation+0.000
out
Tokenout
Feature activation+0.000
in
Token in
Feature activation+2.065
his
Token his
Feature activation+0.096
debut
Token debut
Feature activation+0.000
,
Token,
Feature activation+0.000
following
Token following
Feature activation+0.000
in
Token in
Feature activation+0.000
represents
Token represents
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
complete
Token complete
Feature activation+2.121
dinosaur
Token dinosaur
Feature activation+0.879
skeleton
Token skeleton
Feature activation+2.172
unearthed
Token unearthed
Feature activation+3.785
in
Token in
Feature activation+1.622
Japan
Token Japan
Feature activation+0.172
after
Token after
Feature activation+0.713
Fuk
Token Fuk
Feature activation+0.000

INTERVAL 1.351 - 1.801
CONTAINS 0.008%

E
TokenE
Feature activation+0.000
akin
Tokenakin
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+2.428
Supreme
Token Supreme
Feature activation+1.761
Court
Token Court
Feature activation+2.058
justice
Token justice
Feature activation+3.382
caught
Token caught
Feature activation+2.913
up
Token up
Feature activation+0.000
in
Token in
Feature activation+1.132
their
Token their
Feature activation+0.000
10
Token 10
Feature activation+0.000
th
Tokenth
Feature activation+0.000
loss
Token loss
Feature activation+0.667
in
Token in
Feature activation+0.868
12
Token 12
Feature activation+1.433
games
Token games
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
18
Token 18
Feature activation+0.000
th
Tokenth
Feature activation+0.000
make
Token make
Feature activation+0.000
magic
Token magic
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
second
Token second
Feature activation+0.961
weekend
Token weekend
Feature activation+1.409
,
Token,
Feature activation+0.000
gross
Token gross
Feature activation+0.000
ing
Tokening
Feature activation+0.000
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000
a
Token a
Feature activation+3.836
medical
Token medical
Feature activation+0.589
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+1.421
to
Token to
Feature activation+4.237
ask
Token ask
Feature activation+1.262
the
Token the
Feature activation+0.000
DEA
Token DEA
Feature activation+0.000
to
Token to
Feature activation+0.000
second
Token second
Feature activation+0.000
Leafs
Token Leafs
Feature activation+0.914
goaltender
Token goaltender
Feature activation+1.425
to
Token to
Feature activation+3.689
record
Token record
Feature activation+2.157
a
Token a
Feature activation+1.716
shut
Token shut
Feature activation+0.000
out
Tokenout
Feature activation+0.000
in
Token in
Feature activation+2.065
his
Token his
Feature activation+0.096
debut
Token debut
Feature activation+0.000

INTERVAL 0.900 - 1.351
CONTAINS 0.010%

"
Token"
Feature activation+0.000
A
TokenA
Feature activation+0.000
third
Token third
Feature activation+0.000
of
Token of
Feature activation+2.180
all
Token all
Feature activation+1.548
the
Token the
Feature activation+1.302
83
Token 83
Feature activation+0.000
plastic
Token plastic
Feature activation+0.000
products
Token products
Feature activation+0.000
and
Token and
Feature activation+0.000
synthetic
Token synthetic
Feature activation+0.000
Solo
Token Solo
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
third
Token third
Feature activation+0.000
portable
Token portable
Feature activation+0.985
release
Token release
Feature activation+1.931
for
Token for
Feature activation+1.280
the
Token the
Feature activation+1.950
Canadian
Token Canadian
Feature activation+0.601
manufacturer
Token manufacturer
Feature activation+0.608
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
s
Tokens
Feature activation+0.000
second
Token second
Feature activation+0.000
anniversary
Token anniversary
Feature activation+0.087
in
Token in
Feature activation+1.056
India
Token India
Feature activation+0.119
is
Token is
Feature activation+0.000
coming
Token coming
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+0.000
th
Tokenth
Feature activation+0.441
President
Token President
Feature activation+1.941
of
Token of
Feature activation+1.679
the
Token the
Feature activation+1.764
United
Token United
Feature activation+0.216
States
Token States
Feature activation+1.129
upon
Token upon
Feature activation+0.333
the
Token the
Feature activation+0.084
assassination
Token assassination
Feature activation+0.000
and
Token and
Feature activation+0.000
death
Token death
Feature activation+0.000
s
Tokens
Feature activation+0.000
10
Token 10
Feature activation+0.000
th
Tokenth
Feature activation+0.000
solo
Token solo
Feature activation+1.395
studio
Token studio
Feature activation+0.068
album
Token album
Feature activation+0.990
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
for
Token for
Feature activation+0.000
five
Token five
Feature activation+0.000

INTERVAL 0.450 - 0.900
CONTAINS 0.018%

the
Token the
Feature activation+0.000
fifth
Token fifth
Feature activation+0.000
priest
Token priest
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.149
uncovered
Token uncovered
Feature activation+0.738
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
investigative
Token investigative
Feature activation+0.000
project
Token project
Feature activation+0.000
,
Token,
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
,
Token,
Feature activation+0.000
41
Token 41
Feature activation+0.000
st
Tokenst
Feature activation+0.000
President
Token President
Feature activation+0.000
of
Token of
Feature activation+0.701
the
Token the
Feature activation+1.154
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.057
[
Token [
Feature activation+0.000
15
Token15
Feature activation+0.000
selected
Token selected
Feature activation+0.000
second
Token second
Feature activation+0.000
in
Token in
Feature activation+0.282
the
Token the
Feature activation+1.190
2016
Token 2016
Feature activation+0.079
NBA
Token NBA
Feature activation+0.477
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
rookie
Token rookie
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
PV
Token PV
Feature activation+0.000
installations
Token installations
Feature activation+0.064
to
Token to
Feature activation+0.615
attempt
Token attempt
Feature activation+0.737
to
Token to
Feature activation+0.000
represent
Token represent
Feature activation+0.000
animals
Token animals
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
9
Token 9
Feature activation+0.000
th
Tokenth
Feature activation+0.000
year
Token year
Feature activation+1.813
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.665
row
Token row
Feature activation+0.323
!
Token!
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
launched
Token launched
Feature activation+0.000

INTERVAL 0.000 - 0.450
CONTAINS 99.949%

of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
single
Token single
Feature activation+0.000
species
Token species
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
coolest
Token coolest
Feature activation+0.000
thing
Token thing
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+0.000
literally
Token literally
Feature activation+0.000
roll
Token roll
Feature activation+0.000
toward
Token toward
Feature activation+0.000
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
their
Token their
Feature activation+0.000
sideways
Token sideways
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Tokenhave
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
top
Token top
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
group
Token group
Feature activation+0.000
in
Token in
Feature activation+0.000
Alabama
Token Alabama
Feature activation+0.000
is
Token is
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
stepped
Token stepped
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
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
the
Token the
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
minister
Token minister
Feature activation+0.000
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
it
Token it
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
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 H4.1: (feature 1514)

TOP ACTIVATIONS
MAX = 4.399

combined
Token combined
Feature activation+0.000
vote
Token vote
Feature activation+1.782
for
Token for
Feature activation+3.754
N
Token N
Feature activation+1.606
ader
Tokenader
Feature activation+0.000
and
Token and
Feature activation+4.161
Green
Token Green
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
since
Token since
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
surrounded
Token surrounded
Feature activation+0.000
by
Token by
Feature activation+0.000
combined
Token combined
Feature activation+0.000
British
Token British
Feature activation+4.074
and
Token and
Feature activation+3.217
German
Token German
Feature activation+0.000
forces
Token forces
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
combined
Token combined
Feature activation+0.000
ingestion
Token ingestion
Feature activation+1.564
of
Token of
Feature activation+4.007
ket
Token ket
Feature activation+3.353
amine
Tokenamine
Feature activation+4.399
(
Token (
Feature activation+0.740
K
TokenK
Feature activation+0.000
et
Tokenet
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
combined
Token combined
Feature activation+0.000
vote
Token vote
Feature activation+1.782
for
Token for
Feature activation+3.754
N
Token N
Feature activation+1.606
ader
Tokenader
Feature activation+0.000
and
Token and
Feature activation+4.161
Green
Token Green
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
P
Token P
Feature activation+0.000
isky
Tokenisky
Feature activation+0.000
,
Token,
Feature activation+0.000
combined
Token combined
Feature activation+0.000
Russian
Token Russian
Feature activation+2.599
-
Token-
Feature activation+3.753
separ
Tokensepar
Feature activation+0.004
at
Tokenat
Feature activation+0.000
ist
Tokenist
Feature activation+2.994
forces
Token forces
Feature activation+0.228
violate
Token violate
Feature activation+0.000
The
TokenThe
Feature activation+0.000
authoritative
Token authoritative
Feature activation+0.000
joint
Token joint
Feature activation+0.000
study
Token study
Feature activation+2.042
,
Token,
Feature activation+1.079
by
Token by
Feature activation+3.528
Stanford
Token Stanford
Feature activation+1.411
and
Token and
Feature activation+1.717
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Universities
Token Universities
Feature activation+0.000
an
Token an
Feature activation+0.000
April
Token April
Feature activation+0.000
22
Token 22
Feature activation+0.000
joint
Token joint
Feature activation+0.000
presentation
Token presentation
Feature activation+0.705
by
Token by
Feature activation+3.461
ID
Token ID
Feature activation+0.769
OT
TokenOT
Feature activation+0.512
and
Token and
Feature activation+3.176
the
Token the
Feature activation+0.000
C
Token C
Feature activation+0.000
efficiency
Token efficiency
Feature activation+1.132
of
Token of
Feature activation+1.932
prote
Token prote
Feature activation+0.497
oly
Tokenoly
Feature activation+0.459
sis
Tokensis
Feature activation+1.984
and
Token and
Feature activation+3.317
heat
Token heat
Feature activation+0.125
shock
Token shock
Feature activation+0.181
response
Token response
Feature activation+0.000
systems
Token systems
Feature activation+0.000
,
Token,
Feature activation+0.280
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
combined
Token combined
Feature activation+0.000
efforts
Token efforts
Feature activation+0.516
of
Token of
Feature activation+2.120
the
Token the
Feature activation+3.314
City
Token City
Feature activation+1.941
Council
Token Council
Feature activation+3.231
and
Token and
Feature activation+2.820
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.068
combined
Token combined
Feature activation+0.000
efforts
Token efforts
Feature activation+0.516
of
Token of
Feature activation+2.120
the
Token the
Feature activation+3.314
City
Token City
Feature activation+1.941
Council
Token Council
Feature activation+3.231
and
Token and
Feature activation+2.820
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.068
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
was
Token was
Feature activation+0.000
surrounded
Token surrounded
Feature activation+0.000
by
Token by
Feature activation+0.000
combined
Token combined
Feature activation+0.000
British
Token British
Feature activation+4.074
and
Token and
Feature activation+3.217
German
Token German
Feature activation+0.000
forces
Token forces
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
joint
Token joint
Feature activation+0.000
presentation
Token presentation
Feature activation+0.705
by
Token by
Feature activation+3.461
ID
Token ID
Feature activation+0.769
OT
TokenOT
Feature activation+0.512
and
Token and
Feature activation+3.176
the
Token the
Feature activation+0.000
C
Token C
Feature activation+0.000
TA
TokenTA
Feature activation+0.185
at
Token at
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
a
Token a
Feature activation+0.000
near
Token near
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
blend
Token blend
Feature activation+0.000
of
Token of
Feature activation+1.362
tactical
Token tactical
Feature activation+3.068
and
Token and
Feature activation+2.535
practical
Token practical
Feature activation+0.180
that
Token that
Feature activation+0.008
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
solution
Token solution
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
combines
Token combines
Feature activation+0.000
video
Token video
Feature activation+1.594
management
Token management
Feature activation+3.005
,
Token,
Feature activation+0.208
access
Token access
Feature activation+0.000
control
Token control
Feature activation+0.000
,
Token,
Feature activation+0.000
video
Token video
Feature activation+0.000
combined
Token combined
Feature activation+0.000
Russian
Token Russian
Feature activation+2.599
-
Token-
Feature activation+3.753
separ
Tokensepar
Feature activation+0.004
at
Tokenat
Feature activation+0.000
ist
Tokenist
Feature activation+2.994
forces
Token forces
Feature activation+0.228
violate
Token violate
Feature activation+0.000
the
Token the
Feature activation+0.000
cease
Token cease
Feature activation+0.000
-
Token-
Feature activation+0.000
win
Token win
Feature activation+2.309
-
Token-
Feature activation+2.041
loss
Tokenloss
Feature activation+0.526
record
Token record
Feature activation+0.045
of
Token of
Feature activation+1.449
the
Token the
Feature activation+2.945
teams
Token teams
Feature activation+0.000
you
Token you
Feature activation+0.000
've
Token've
Feature activation+0.000
beaten
Token beaten
Feature activation+0.000
,
Token,
Feature activation+0.160
a
Token a
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
population
Token population
Feature activation+0.128
of
Token of
Feature activation+1.895
slave
Token slave
Feature activation+2.350
and
Token and
Feature activation+2.929
free
Token free
Feature activation+0.000
in
Token in
Feature activation+0.000
Roman
Token Roman
Feature activation+0.000
-
Token-
Feature activation+0.072
r
Tokenr
Feature activation+0.000
unified
Token unified
Feature activation+0.000
solution
Token solution
Feature activation+0.000
that
Token that
Feature activation+0.000
combines
Token combines
Feature activation+0.037
video
Token video
Feature activation+1.285
management
Token management
Feature activation+2.927
,
Token,
Feature activation+0.552
access
Token access
Feature activation+0.000
control
Token control
Feature activation+0.000
,
Token,
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
WC
TokenWC
Feature activation+0.000
)
Token)
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
joint
Token joint
Feature activation+0.000
United
Token United
Feature activation+2.884
States
Token States
Feature activation+2.777
Navy
Token Navy
Feature activation+1.176
âĢĵ
Token âĢĵ
Feature activation+1.240
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
efforts
Token efforts
Feature activation+0.516
of
Token of
Feature activation+2.120
the
Token the
Feature activation+3.314
City
Token City
Feature activation+1.941
Council
Token Council
Feature activation+3.231
and
Token and
Feature activation+2.820
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.068
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Rent
Token Rent
Feature activation+0.000

Top DFA by src position
MAX = 5.032

Al
Token Al
Feature activation-0.006
Top resid features:
Gore
Token Gore
Feature activation-0.046
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation-0.011
Top resid features:
combined
Token combined
Feature activation+4.688
Top resid features:
vote
Token vote
Feature activation+0.100
Top resid features:
for
Token for
Feature activation+0.094
Top resid features:
N
Token N
Feature activation-0.015
Top resid features:
ader
Tokenader
Feature activation+0.060
Top resid features:
and
Token and
Feature activation-0.143
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.111
Top resid features:
,
Token,
Feature activation-0.119
Top resid features:
was
Token was
Feature activation-0.017
Top resid features:
surrounded
Token surrounded
Feature activation-0.052
Top resid features:
by
Token by
Feature activation-0.204
Top resid features:
combined
Token combined
Feature activation+5.032
Top resid features:
British
Token British
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
German
Token German
Feature activation+0.000
Top resid features:
forces
Token forces
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation-0.002
Top resid features:
'm
Token'm
Feature activation-0.001
Top resid features:
very
Token very
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation-0.043
Top resid features:
combined
Token combined
Feature activation+4.832
Top resid features:
ingestion
Token ingestion
Feature activation-0.096
Top resid features:
of
Token of
Feature activation-0.143
Top resid features:
ket
Token ket
Feature activation+0.000
Top resid features:
amine
Tokenamine
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Al
Token Al
Feature activation-0.004
Top resid features:
Gore
Token Gore
Feature activation-0.022
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
(
Token (
Feature activation-0.016
Top resid features:
The
TokenThe
Feature activation-0.040
Top resid features:
combined
Token combined
Feature activation+4.344
Top resid features:
vote
Token vote
Feature activation+0.143
Top resid features:
for
Token for
Feature activation-0.077
Top resid features:
N
Token N
Feature activation+0.000
Top resid features:
ader
Tokenader
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
In
TokenIn
Feature activation-0.003
Top resid features:
P
Token P
Feature activation-0.016
Top resid features:
isky
Tokenisky
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
combined
Token combined
Feature activation+4.314
Top resid features:
Russian
Token Russian
Feature activation+0.189
Top resid features:
-
Token-
Feature activation-0.130
Top resid features:
separ
Tokensepar
Feature activation+0.000
Top resid features:
at
Tokenat
Feature activation+0.000
Top resid features:
ist
Tokenist
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-0.012
Top resid features:
The
TokenThe
Feature activation-0.056
Top resid features:
authoritative
Token authoritative
Feature activation-0.009
Top resid features:
joint
Token joint
Feature activation+4.289
Top resid features:
study
Token study
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.166
Top resid features:
by
Token by
Feature activation-0.012
Top resid features:
Stanford
Token Stanford
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
displayed
Token displayed
Feature activation-0.054
Top resid features:
at
Token at
Feature activation+0.010
Top resid features:
an
Token an
Feature activation-0.011
Top resid features:
April
Token April
Feature activation+0.026
Top resid features:
22
Token 22
Feature activation+0.021
Top resid features:
joint
Token joint
Feature activation+4.042
Top resid features:
presentation
Token presentation
Feature activation-0.064
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
ID
Token ID
Feature activation+0.000
Top resid features:
OT
TokenOT
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
constant
Token constant
Feature activation+0.004
Top resid features:
c
Token c
Feature activation-0.001
Top resid features:
reflects
Token reflects
Feature activation+0.023
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
combined
Token combined
Feature activation+3.732
Top resid features:
efficiency
Token efficiency
Feature activation-0.020
Top resid features:
of
Token of
Feature activation+0.127
Top resid features:
prote
Token prote
Feature activation-0.013
Top resid features:
oly
Tokenoly
Feature activation-0.076
Top resid features:
sis
Tokensis
Feature activation+0.082
Top resid features:
our
Token our
Feature activation-0.022
Top resid features:
housing
Token housing
Feature activation+0.003
Top resid features:
stock
Token stock
Feature activation+0.009
Top resid features:
through
Token through
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
combined
Token combined
Feature activation+3.808
Top resid features:
efforts
Token efforts
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.121
Top resid features:
the
Token the
Feature activation-0.058
Top resid features:
City
Token City
Feature activation+0.000
Top resid features:
Council
Token Council
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.021
Top resid features:
housing
Token housing
Feature activation-0.002
Top resid features:
stock
Token stock
Feature activation+0.011
Top resid features:
through
Token through
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
combined
Token combined
Feature activation+3.394
Top resid features:
efforts
Token efforts
Feature activation+0.109
Top resid features:
of
Token of
Feature activation+0.250
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
City
Token City
Feature activation+0.255
Top resid features:
Council
Token Council
Feature activation-0.221
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.125
Top resid features:
,
Token,
Feature activation-0.062
Top resid features:
was
Token was
Feature activation-0.011
Top resid features:
surrounded
Token surrounded
Feature activation-0.044
Top resid features:
by
Token by
Feature activation-0.147
Top resid features:
combined
Token combined
Feature activation+3.846
Top resid features:
British
Token British
Feature activation+0.343
Top resid features:
and
Token and
Feature activation-0.164
Top resid features:
German
Token German
Feature activation+0.000
Top resid features:
forces
Token forces
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
displayed
Token displayed
Feature activation-0.008
Top resid features:
at
Token at
Feature activation+0.016
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
April
Token April
Feature activation+0.024
Top resid features:
22
Token 22
Feature activation+0.008
Top resid features:
joint
Token joint
Feature activation+3.520
Top resid features:
presentation
Token presentation
Feature activation+0.014
Top resid features:
by
Token by
Feature activation+0.038
Top resid features:
ID
Token ID
Feature activation+0.019
Top resid features:
OT
TokenOT
Feature activation+0.077
Top resid features:
and
Token and
Feature activation-0.036
Top resid features:
7
Token7
Feature activation+0.002
Top resid features:
achieves
Token achieves
Feature activation-0.021
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
near
Token near
Feature activation+0.005
Top resid features:
perfect
Token perfect
Feature activation-0.002
Top resid features:
blend
Token blend
Feature activation+3.472
Top resid features:
of
Token of
Feature activation+0.165
Top resid features:
tactical
Token tactical
Feature activation-0.053
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
practical
Token practical
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
IP
Token IP
Feature activation+0.017
Top resid features:
security
Token security
Feature activation-0.005
Top resid features:
solution
Token solution
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
It
Token It
Feature activation+0.010
Top resid features:
combines
Token combines
Feature activation+3.202
Top resid features:
video
Token video
Feature activation+0.310
Top resid features:
management
Token management
Feature activation-0.090
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
access
Token access
Feature activation+0.000
Top resid features:
control
Token control
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
In
TokenIn
Feature activation-0.006
Top resid features:
P
Token P
Feature activation-0.008
Top resid features:
isky
Tokenisky
Feature activation-0.013
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
combined
Token combined
Feature activation+3.501
Top resid features:
Russian
Token Russian
Feature activation+0.003
Top resid features:
-
Token-
Feature activation-0.077
Top resid features:
separ
Tokensepar
Feature activation+0.052
Top resid features:
at
Tokenat
Feature activation+0.163
Top resid features:
ist
Tokenist
Feature activation-0.080
Top resid features:
victory
Token victory
Feature activation-0.015
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
which
Token which
Feature activation-0.003
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
combined
Token combined
Feature activation+3.424
Top resid features:
win
Token win
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.009
Top resid features:
loss
Tokenloss
Feature activation-0.012
Top resid features:
record
Token record
Feature activation+0.045
Top resid features:
of
Token of
Feature activation+0.201
Top resid features:
man
Token man
Feature activation-0.010
Top resid features:
um
Tokenum
Feature activation-0.010
Top resid features:
ission
Tokenission
Feature activation-0.013
Top resid features:
produced
Token produced
Feature activation-0.047
Top resid features:
a
Token a
Feature activation-0.028
Top resid features:
mixed
Token mixed
Feature activation+3.211
Top resid features:
population
Token population
Feature activation+0.042
Top resid features:
of
Token of
Feature activation+0.220
Top resid features:
slave
Token slave
Feature activation+0.077
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
free
Token free
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
unified
Token unified
Feature activation+0.060
Top resid features:
solution
Token solution
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
combines
Token combines
Feature activation+3.121
Top resid features:
video
Token video
Feature activation+0.325
Top resid features:
management
Token management
Feature activation-0.118
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
access
Token access
Feature activation+0.000
Top resid features:
control
Token control
Feature activation+0.000
Top resid features:
T
TokenT
Feature activation+0.008
Top resid features:
WC
TokenWC
Feature activation-0.003
Top resid features:
)
Token)
Feature activation+0.010
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
a
Token a
Feature activation+0.066
Top resid features:
joint
Token joint
Feature activation+3.322
Top resid features:
United
Token United
Feature activation+0.032
Top resid features:
States
Token States
Feature activation+0.000
Top resid features:
Navy
Token Navy
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
United
Token United
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.024
Top resid features:
housing
Token housing
Feature activation-0.003
Top resid features:
stock
Token stock
Feature activation+0.009
Top resid features:
through
Token through
Feature activation-0.020
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
combined
Token combined
Feature activation+3.003
Top resid features:
efforts
Token efforts
Feature activation+0.190
Top resid features:
of
Token of
Feature activation+0.393
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
City
Token City
Feature activation+0.002
Top resid features:
Council
Token Council
Feature activation-0.103
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.47

Head 2: 0.03

Head 3: 0.04

Head 4: 0.03

Head 5: 0.05

Head 6: 0.05

Head 7: 0.07

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.08

Positive logits

&1.40

plus1.40

ochond1.30

minus1.25

AND1.24

Asians1.24

WF1.23

synonymous1.19

cx1.17

versus1.14

Cyp1.12

othing1.11

+1.11

POW1.10

phe1.10

Chatt1.10

Siber1.09

seq1.09

zees1.09

Physicians1.09

Negative logits

��-1.56

��極-1.52

agos-1.45

otine-1.43

clerosis-1.41

��-1.32

��-1.31

Shape-1.30

��-1.24

notice-1.24

Subst-1.22

フォ-1.22

ank-1.21

Copyright-1.21

Demon-1.16

-1.14

Ore-1.13

ixtape-1.13

izza-1.12

ydia-1.11

INTERVAL 3.959 - 4.399
CONTAINS 0.000%

,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
surrounded
Token surrounded
Feature activation+0.000
by
Token by
Feature activation+0.000
combined
Token combined
Feature activation+0.000
British
Token British
Feature activation+4.074
and
Token and
Feature activation+3.217
German
Token German
Feature activation+0.000
forces
Token forces
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
combined
Token combined
Feature activation+0.000
vote
Token vote
Feature activation+1.782
for
Token for
Feature activation+3.754
N
Token N
Feature activation+1.606
ader
Tokenader
Feature activation+0.000
and
Token and
Feature activation+4.161
Green
Token Green
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
since
Token since
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
has
Token has
Feature activation+0.000
very
Token very
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
combined
Token combined
Feature activation+0.000
ingestion
Token ingestion
Feature activation+1.564
of
Token of
Feature activation+4.007
ket
Token ket
Feature activation+3.353
amine
Tokenamine
Feature activation+4.399
(
Token (
Feature activation+0.740
K
TokenK
Feature activation+0.000
et
Tokenet
Feature activation+0.000

INTERVAL 3.519 - 3.959
CONTAINS 0.000%

.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
combined
Token combined
Feature activation+0.000
vote
Token vote
Feature activation+1.782
for
Token for
Feature activation+3.754
N
Token N
Feature activation+1.606
ader
Tokenader
Feature activation+0.000
and
Token and
Feature activation+4.161
Green
Token Green
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
The
TokenThe
Feature activation+0.000
authoritative
Token authoritative
Feature activation+0.000
joint
Token joint
Feature activation+0.000
study
Token study
Feature activation+2.042
,
Token,
Feature activation+1.079
by
Token by
Feature activation+3.528
Stanford
Token Stanford
Feature activation+1.411
and
Token and
Feature activation+1.717
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Universities
Token Universities
Feature activation+0.000
P
Token P
Feature activation+0.000
isky
Tokenisky
Feature activation+0.000
,
Token,
Feature activation+0.000
combined
Token combined
Feature activation+0.000
Russian
Token Russian
Feature activation+2.599
-
Token-
Feature activation+3.753
separ
Tokensepar
Feature activation+0.004
at
Tokenat
Feature activation+0.000
ist
Tokenist
Feature activation+2.994
forces
Token forces
Feature activation+0.228
violate
Token violate
Feature activation+0.000

INTERVAL 3.079 - 3.519
CONTAINS 0.001%

combined
Token combined
Feature activation+0.000
efforts
Token efforts
Feature activation+0.516
of
Token of
Feature activation+2.120
the
Token the
Feature activation+3.314
City
Token City
Feature activation+1.941
Council
Token Council
Feature activation+3.231
and
Token and
Feature activation+2.820
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.068
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
combined
Token combined
Feature activation+0.000
efforts
Token efforts
Feature activation+0.516
of
Token of
Feature activation+2.120
the
Token the
Feature activation+3.314
City
Token City
Feature activation+1.941
Council
Token Council
Feature activation+3.231
and
Token and
Feature activation+2.820
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.068
an
Token an
Feature activation+0.000
April
Token April
Feature activation+0.000
22
Token 22
Feature activation+0.000
joint
Token joint
Feature activation+0.000
presentation
Token presentation
Feature activation+0.705
by
Token by
Feature activation+3.461
ID
Token ID
Feature activation+0.769
OT
TokenOT
Feature activation+0.512
and
Token and
Feature activation+3.176
the
Token the
Feature activation+0.000
C
Token C
Feature activation+0.000
joint
Token joint
Feature activation+0.000
presentation
Token presentation
Feature activation+0.705
by
Token by
Feature activation+3.461
ID
Token ID
Feature activation+0.769
OT
TokenOT
Feature activation+0.512
and
Token and
Feature activation+3.176
the
Token the
Feature activation+0.000
C
Token C
Feature activation+0.000
TA
TokenTA
Feature activation+0.185
at
Token at
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
was
Token was
Feature activation+0.000
surrounded
Token surrounded
Feature activation+0.000
by
Token by
Feature activation+0.000
combined
Token combined
Feature activation+0.000
British
Token British
Feature activation+4.074
and
Token and
Feature activation+3.217
German
Token German
Feature activation+0.000
forces
Token forces
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.639 - 3.079
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ambition
Token ambition
Feature activation+0.000
in
Token in
Feature activation+0.000
mixing
Token mixing
Feature activation+0.000
fantasy
Token fantasy
Feature activation+2.733
and
Token and
Feature activation+1.396
politics
Token politics
Feature activation+0.000
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
combined
Token combined
Feature activation+0.000
Russian
Token Russian
Feature activation+2.599
-
Token-
Feature activation+3.753
separ
Tokensepar
Feature activation+0.004
at
Tokenat
Feature activation+0.000
ist
Tokenist
Feature activation+2.994
forces
Token forces
Feature activation+0.228
violate
Token violate
Feature activation+0.000
the
Token the
Feature activation+0.000
cease
Token cease
Feature activation+0.000
-
Token-
Feature activation+0.000
Target
Token Target
Feature activation+0.000
used
Token used
Feature activation+0.000
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.502
legal
Token legal
Feature activation+2.795
and
Token and
Feature activation+1.209
illegal
Token illegal
Feature activation+0.000
tactics
Token tactics
Feature activation+0.415
to
Token to
Feature activation+0.000
scare
Token scare
Feature activation+0.000
)
Token)
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
joint
Token joint
Feature activation+0.000
United
Token United
Feature activation+2.884
States
Token States
Feature activation+2.777
Navy
Token Navy
Feature activation+1.176
âĢĵ
Token âĢĵ
Feature activation+1.240
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
Air
Token Air
Feature activation+0.000
a
Token a
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
population
Token population
Feature activation+0.128
of
Token of
Feature activation+1.895
slave
Token slave
Feature activation+2.350
and
Token and
Feature activation+2.929
free
Token free
Feature activation+0.000
in
Token in
Feature activation+0.000
Roman
Token Roman
Feature activation+0.000
-
Token-
Feature activation+0.072
r
Tokenr
Feature activation+0.000

INTERVAL 2.200 - 2.639
CONTAINS 0.002%

1945
Token 1945
Feature activation+0.000
a
Token a
Feature activation+0.000
joint
Token joint
Feature activation+0.000
New
Token New
Feature activation+1.617
Zealand
Token Zealand
Feature activation+2.674
,
Token,
Feature activation+2.351
Australian
Token Australian
Feature activation+0.201
and
Token and
Feature activation+1.443
British
Token British
Feature activation+0.000
trustees
Token trustees
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
combined
Token combined
Feature activation+0.000
win
Token win
Feature activation+2.309
-
Token-
Feature activation+2.041
loss
Tokenloss
Feature activation+0.526
record
Token record
Feature activation+0.045
of
Token of
Feature activation+1.449
the
Token the
Feature activation+2.945
enterprise
Token enterprise
Feature activation+0.000
,
Token,
Feature activation+0.436
67
Token 67
Feature activation+0.000
percent
Token percent
Feature activation+0.000
owned
Token owned
Feature activation+0.000
by
Token by
Feature activation+2.518
Fiat
Token Fiat
Feature activation+0.000
and
Token and
Feature activation+1.267
33
Token 33
Feature activation+0.000
percent
Token percent
Feature activation+0.000
by
Token by
Feature activation+0.000
to
Token to
Feature activation+0.000
balance
Token balance
Feature activation+0.000
the
Token the
Feature activation+0.000
rapid
Token rapid
Feature activation+2.532
redevelopment
Token redevelopment
Feature activation+1.322
of
Token of
Feature activation+2.300
the
Token the
Feature activation+0.589
greater
Token greater
Feature activation+1.704
downtown
Token downtown
Feature activation+0.000
with
Token with
Feature activation+0.000
due
Token due
Feature activation+0.000
am
Token am
Feature activation+0.000
enjoying
Token enjoying
Feature activation+0.000
the
Token the
Feature activation+0.000
blend
Token blend
Feature activation+0.000
of
Token of
Feature activation+1.450
historical
Token historical
Feature activation+2.223
and
Token and
Feature activation+1.936
fantasy
Token fantasy
Feature activation+0.382
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000

INTERVAL 1.760 - 2.200
CONTAINS 0.004%

financed
Token financed
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.313
private
Token private
Feature activation+2.131
SE
Token SE
Feature activation+1.320
IS
TokenIS
Feature activation+0.000
/
Token/
Feature activation+0.490
E
TokenE
Feature activation+0.000
IS
TokenIS
Feature activation+0.000
combined
Token combined
Feature activation+0.098
efficiency
Token efficiency
Feature activation+1.132
of
Token of
Feature activation+1.932
prote
Token prote
Feature activation+0.497
oly
Tokenoly
Feature activation+0.459
sis
Tokensis
Feature activation+1.984
and
Token and
Feature activation+3.317
heat
Token heat
Feature activation+0.125
shock
Token shock
Feature activation+0.181
response
Token response
Feature activation+0.000
systems
Token systems
Feature activation+0.000
became
Token became
Feature activation+0.000
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.000
political
Token political
Feature activation+1.731
theater
Token theater
Feature activation+2.037
,
Token,
Feature activation+0.912
rec
Token rec
Feature activation+0.000
rim
Tokenrim
Feature activation+0.000
inations
Tokeninations
Feature activation+0.000
and
Token and
Feature activation+0.000
enjoying
Token enjoying
Feature activation+0.000
the
Token the
Feature activation+0.000
blend
Token blend
Feature activation+0.000
of
Token of
Feature activation+1.450
historical
Token historical
Feature activation+2.223
and
Token and
Feature activation+1.936
fantasy
Token fantasy
Feature activation+0.382
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
combined
Token combined
Feature activation+0.000
diet
Token diet
Feature activation+1.780
and
Token and
Feature activation+2.001
exercise
Token exercise
Feature activation+0.000
gained
Token gained
Feature activation+0.000
back
Token back
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.320 - 1.760
CONTAINS 0.007%

are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Do
Token Do
Feature activation+0.000
not
Token not
Feature activation+0.000
confuse
Token confuse
Feature activation+0.000
conformity
Token conformity
Feature activation+1.342
with
Token with
Feature activation+0.055
superficial
Token superficial
Feature activation+0.559
ity
Tokenity
Feature activation+0.000
or
Token or
Feature activation+0.000
ignorance
Token ignorance
Feature activation+0.000
industries
Token industries
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
combination
Token combination
Feature activation+0.000
of
Token of
Feature activation+0.000
high
Token high
Feature activation+1.330
taxes
Token taxes
Feature activation+1.113
and
Token and
Feature activation+0.406
unfair
Token unfair
Feature activation+0.000
competition
Token competition
Feature activation+0.000
.
Token.
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
combination
Token combination
Feature activation+0.000
of
Token of
Feature activation+0.000
falling
Token falling
Feature activation+1.625
precipitation
Token precipitation
Feature activation+0.732
;
Token;
Feature activation+0.219
the
Token the
Feature activation+0.000
inf
Token inf
Feature activation+0.000
low
Tokenlow
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
combined
Token combined
Feature activation+0.000
vote
Token vote
Feature activation+1.782
for
Token for
Feature activation+3.754
N
Token N
Feature activation+1.606
ader
Tokenader
Feature activation+0.000
and
Token and
Feature activation+4.161
Green
Token Green
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
since
Token since
Feature activation+0.000
distance
Token distance
Feature activation+0.000
driver
Token driver
Feature activation+0.000
that
Token that
Feature activation+0.000
blends
Token blends
Feature activation+0.102
the
Token the
Feature activation+0.681
graceful
Token graceful
Feature activation+1.476
long
Token long
Feature activation+0.996
turn
Token turn
Feature activation+0.162
of
Token of
Feature activation+1.572
the
Token the
Feature activation+0.823
Kat
Token Kat
Feature activation+0.029

INTERVAL 0.880 - 1.320
CONTAINS 0.011%

have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.000
Hero
Token Hero
Feature activation+0.560
,
Token,
Feature activation+1.010
Vill
Token Vill
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
and
Token and
Feature activation+0.000
Neutral
Token Neutral
Feature activation+0.000
characters
Token characters
Feature activation+0.000
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.655
classic
Token classic
Feature activation+1.796
addictive
Token addictive
Feature activation+1.874
game
Token game
Feature activation+1.044
play
Token play
Feature activation+0.594
ideas
Token ideas
Feature activation+0.511
but
Token but
Feature activation+0.000
taking
Token taking
Feature activation+0.000
them
Token them
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Joint
Token Joint
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.296
Hard
Token Hard
Feature activation+0.633
Rock
Token Rock
Feature activation+0.000
Casino
Token Casino
Feature activation+0.814
&
Token &
Feature activation+0.833
Hotel
Token Hotel
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+0.000
transportation
Token transportation
Feature activation+0.000
coupled
Token coupled
Feature activation+0.000
with
Token with
Feature activation+1.059
unrel
Token unrel
Feature activation+0.000
iability
Tokeniability
Feature activation+0.000
currently
Token currently
Feature activation+0.000
discour
Token discour
Feature activation+0.000
ages
Tokenages
Feature activation+0.000
corruption
Token corruption
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Mix
TokenMix
Feature activation+0.000
ing
Tokening
Feature activation+0.000
protein
Token protein
Feature activation+0.881
powd
Token powd
Feature activation+0.232
ers
Tokeners
Feature activation+0.579
,
Token,
Feature activation+0.014
fish
Token fish
Feature activation+0.000
oils
Token oils
Feature activation+0.000

INTERVAL 0.440 - 0.880
CONTAINS 0.026%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Am
TokenAm
Feature activation+0.000
sterdam
Tokensterdam
Feature activation+0.000
Releases
Token Releases
Feature activation+0.000
Pair
Token Pair
Feature activation+0.000
of
Token of
Feature activation+0.503
Adventure
Token Adventure
Feature activation+0.554
Brew
Token Brew
Feature activation+0.000
s
Tokens
Feature activation+0.000
at
Token at
Feature activation+0.000
Retail
Token Retail
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
conf
Token conf
Feature activation+0.000
lation
Tokenlation
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.585
ľ
Tokenľ
Feature activation+0.018
sc
Tokensc
Feature activation+0.000
ared
Tokenared
Feature activation+0.254
stiff
Token stiff
Feature activation+0.994
âĢ
TokenâĢ
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
murky
Token murky
Feature activation+0.000
nexus
Token nexus
Feature activation+0.000
of
Token of
Feature activation+0.720
business
Token business
Feature activation+0.582
and
Token and
Feature activation+0.287
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
bolster
Token bolster
Feature activation+0.000
its
Token its
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+0.630
interest
Tokeninterest
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
default
Token default
Feature activation+0.000
.
Token.
Feature activation+0.000
Mix
Token Mix
Feature activation+0.000
in
Token in
Feature activation+0.000
injuries
Token injuries
Feature activation+2.221
,
Token,
Feature activation+0.450
an
Token an
Feature activation+0.000
imminent
Token imminent
Feature activation+0.000
31
Token 31
Feature activation+0.000
st
Tokenst
Feature activation+0.000
birthday
Token birthday
Feature activation+0.000

INTERVAL 0.000 - 0.440
CONTAINS 99.948%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
could
Token could
Feature activation+0.000
risk
Token risk
Feature activation+0.000
a
Token a
Feature activation+0.000
belie
Token belie
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
St
TokenSt
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
also
Token also
Feature activation+0.000
confronted
Token confronted
Feature activation+0.000
vex
Token vex
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
agg
Tokenagg
Feature activation+0.000
i
Tokeni
Feature activation+0.000
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.000
for
Token for
Feature activation+0.000
its
Token its
Feature activation+0.000
tag
Token tag
Feature activation+0.000
line
Tokenline
Feature activation+0.000
just
Token just
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+0.000
.
Token.
Feature activation+0.000
Working
Token Working
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
state
Token state
Feature activation+0.000
and
Token and
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
stand
Token stand
Feature activation+0.000
among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.000
hottest
Token hottest
Feature activation+0.000
European
Token European
Feature activation+0.000
thr
Token thr
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
metal
Token metal
Feature activation+0.000
bands
Token bands
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