H6.7 top features

Top feature 0 in H6.7: (feature 13208)

TOP ACTIVATIONS
MAX = 5.562

and
Token and
Feature activation+0.000
Orange
Token Orange
Feature activation+0.000
counties
Token counties
Feature activation+0.127
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
summer
Token summer
Feature activation+0.000
quarter
Token quarter
Feature activation+0.167
,
Token,
Feature activation+0.466
counties
Token counties
Feature activation+0.127
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
summer
Token summer
Feature activation+0.000
quarter
Token quarter
Feature activation+0.167
out
Token out
Feature activation+0.072
bound
Tokenbound
Feature activation+0.000
moves
Token moves
Feature activation+0.637
making
Token making
Feature activation+0.117
up
Token up
Feature activation+1.090
63
Token 63
Feature activation+4.942
percent
Token percent
Feature activation+4.736
of
Token of
Feature activation+1.662
all
Token all
Feature activation+0.000
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+0.137
bound
Tokenbound
Feature activation+0.000
moves
Token moves
Feature activation+0.637
making
Token making
Feature activation+0.117
up
Token up
Feature activation+1.090
63
Token 63
Feature activation+4.942
percent
Token percent
Feature activation+4.736
of
Token of
Feature activation+1.662
all
Token all
Feature activation+0.000
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+0.137
Ċ
TokenĊ
Feature activation+0.000
matchup
Token matchup
Feature activation+2.550
was
Token was
Feature activation+0.146
8
Token 8
Feature activation+2.180
.
Token.
Feature activation+2.152
78
Token78
Feature activation+3.723
%
Token%
Feature activation+4.517
possible
Token possible
Feature activation+0.289
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
the
Token the
Feature activation+0.000
were
Token were
Feature activation+1.309
responsible
Token responsible
Feature activation+1.223
for
Token for
Feature activation+0.466
0
Token 0
Feature activation+0.349
·
Token·
Feature activation+1.074
86
Token86
Feature activation+4.283
%
Token%
Feature activation+3.237
(
Token (
Feature activation+0.967
0
Token0
Feature activation+0.143
·
Token·
Feature activation+0.263
84
Token84
Feature activation+2.223
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224
to
Token to
Feature activation+0.000
cast
Token cast
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224
Edmonton
Token Edmonton
Feature activation+1.142
matchup
Token matchup
Feature activation+2.550
was
Token was
Feature activation+0.146
8
Token 8
Feature activation+2.180
.
Token.
Feature activation+2.152
78
Token78
Feature activation+3.723
%
Token%
Feature activation+4.517
possible
Token possible
Feature activation+0.289
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
French
Token French
Feature activation+0.000
and
Token and
Feature activation+0.429
10
Token 10
Feature activation+2.652
%
Token%
Feature activation+3.440
in
Token in
Feature activation+0.074
German
Token German
Feature activation+0.000
;
Token;
Feature activation+0.385
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
produced
Token produced
Feature activation+0.000
26
Token 26
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.433
%
Token%
Feature activation+0.936
and
Token and
Feature activation+3.332
17
Token 17
Feature activation+0.549
.
Token.
Feature activation+0.000
4
Token4
Feature activation+1.933
%
Token%
Feature activation+2.097
increase
Token increase
Feature activation+0.720
about
Token about
Feature activation+0.412
$
Token $
Feature activation+0.389
150
Token150
Feature activation+0.622
,
Token,
Feature activation+1.886
000
Token000
Feature activation+1.280
,
Token,
Feature activation+3.278
$
Token $
Feature activation+0.000
151
Token151
Feature activation+0.309
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.684
and
Token and
Feature activation+1.490
responsible
Token responsible
Feature activation+1.223
for
Token for
Feature activation+0.466
0
Token 0
Feature activation+0.349
·
Token·
Feature activation+1.074
86
Token86
Feature activation+4.283
%
Token%
Feature activation+3.237
(
Token (
Feature activation+0.967
0
Token0
Feature activation+0.143
·
Token·
Feature activation+0.263
84
Token84
Feature activation+2.223
âĢĵ
TokenâĢĵ
Feature activation+0.000
Blockchain
Token Blockchain
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Republicans
TokenRepublicans
Feature activation+0.000
and
Token and
Feature activation+0.000
Democrats
Token Democrats
Feature activation+3.218
don
Token don
Feature activation+2.141
âĢ
TokenâĢ
Feature activation+0.128
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.381
entirely
Token entirely
Feature activation+0.729
France
Token France
Feature activation+0.000
and
Token and
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.399
and
Token and
Feature activation+0.674
into
Token into
Feature activation+0.657
sixth
Token sixth
Feature activation+3.093
place
Token place
Feature activation+1.859
behind
Token behind
Feature activation+0.354
the
Token the
Feature activation+0.267
United
Token United
Feature activation+0.027
Kingdom
Token Kingdom
Feature activation+0.000
the
Token the
Feature activation+0.000
Iraqi
Token Iraqi
Feature activation+0.000
and
Token and
Feature activation+0.000
Kurdish
Token Kurdish
Feature activation+1.764
security
Token security
Feature activation+1.892
forces
Token forces
Feature activation+3.047
,
Token,
Feature activation+0.592
and
Token and
Feature activation+0.757
the
Token the
Feature activation+0.416
provision
Token provision
Feature activation+0.008
of
Token of
Feature activation+0.029

Top DFA by src position
MAX = 5.896

Own
TokenOwn
Feature activation+0.012
Top resid features:
ership
Tokenership
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
Los
Token Los
Feature activation+0.010
Top resid features:
Angeles
Token Angeles
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+5.896
Top resid features:
Orange
Token Orange
Feature activation+0.016
Top resid features:
counties
Token counties
Feature activation+0.029
Top resid features:
fell
Token fell
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
46
Token 46
Feature activation+0.054
Top resid features:
Own
TokenOwn
Feature activation+0.012
Top resid features:
ership
Tokenership
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
Los
Token Los
Feature activation+0.014
Top resid features:
Angeles
Token Angeles
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+5.700
Top resid features:
Orange
Token Orange
Feature activation+0.014
Top resid features:
counties
Token counties
Feature activation+0.029
Top resid features:
fell
Token fell
Feature activation-0.013
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
46
Token 46
Feature activation+0.027
Top resid features:
Own
TokenOwn
Feature activation+0.019
Top resid features:
ership
Tokenership
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
Los
Token Los
Feature activation+0.012
Top resid features:
Angeles
Token Angeles
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+5.540
Top resid features:
Orange
Token Orange
Feature activation+0.010
Top resid features:
counties
Token counties
Feature activation+0.022
Top resid features:
fell
Token fell
Feature activation-0.019
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
46
Token 46
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
New
TokenNew
Feature activation+0.002
Top resid features:
Jersey
Token Jersey
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+5.334
Top resid features:
Illinois
Token Illinois
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
like
Token like
Feature activation+0.004
Top resid features:
New
Token New
Feature activation+0.001
Top resid features:
York
Token York
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
New
TokenNew
Feature activation+0.002
Top resid features:
Jersey
Token Jersey
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+5.134
Top resid features:
Illinois
Token Illinois
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
like
Token like
Feature activation-0.000
Top resid features:
New
Token New
Feature activation+0.001
Top resid features:
York
Token York
Feature activation-0.002
Top resid features:
simulator
Token simulator
Feature activation+0.007
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
Calgary
Token Calgary
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+4.877
Top resid features:
Edmonton
Token Edmonton
Feature activation+0.020
Top resid features:
matchup
Token matchup
Feature activation+0.043
Top resid features:
was
Token was
Feature activation+0.018
Top resid features:
8
Token 8
Feature activation+0.057
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
·
Token·
Feature activation-0.003
Top resid features:
44
Token44
Feature activation-0.004
Top resid features:
).
Token).
Feature activation+0.028
Top resid features:
Extreme
Token Extreme
Feature activation-0.001
Top resid features:
cold
Token cold
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+4.635
Top resid features:
hot
Token hot
Feature activation+0.010
Top resid features:
temperatures
Token temperatures
Feature activation+0.004
Top resid features:
were
Token were
Feature activation-0.006
Top resid features:
responsible
Token responsible
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
votes
Token votes
Feature activation-0.002
Top resid features:
cast
Token cast
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
His
Token His
Feature activation-0.002
Top resid features:
Democratic
Token Democratic
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+3.550
Top resid features:
Republican
Token Republican
Feature activation+0.047
Top resid features:
challengers
Token challengers
Feature activation+0.012
Top resid features:
received
Token received
Feature activation+0.014
Top resid features:
33
Token 33
Feature activation+0.039
Top resid features:
and
Token and
Feature activation+1.152
Top resid features:
votes
Token votes
Feature activation-0.002
Top resid features:
cast
Token cast
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
His
Token His
Feature activation+0.012
Top resid features:
Democratic
Token Democratic
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+3.190
Top resid features:
Republican
Token Republican
Feature activation+0.032
Top resid features:
challengers
Token challengers
Feature activation-0.004
Top resid features:
received
Token received
Feature activation+0.009
Top resid features:
33
Token 33
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+1.392
Top resid features:
votes
Token votes
Feature activation-0.047
Top resid features:
cast
Token cast
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
His
Token His
Feature activation+0.001
Top resid features:
Democratic
Token Democratic
Feature activation-0.019
Top resid features:
and
Token and
Feature activation+4.653
Top resid features:
Republican
Token Republican
Feature activation+0.037
Top resid features:
challengers
Token challengers
Feature activation+0.000
Top resid features:
received
Token received
Feature activation+0.000
Top resid features:
33
Token 33
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
votes
Token votes
Feature activation+0.001
Top resid features:
cast
Token cast
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
His
Token His
Feature activation-0.007
Top resid features:
Democratic
Token Democratic
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+2.432
Top resid features:
Republican
Token Republican
Feature activation+0.027
Top resid features:
challengers
Token challengers
Feature activation+0.003
Top resid features:
received
Token received
Feature activation+0.005
Top resid features:
33
Token 33
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+1.981
Top resid features:
votes
Token votes
Feature activation-0.004
Top resid features:
cast
Token cast
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
His
Token His
Feature activation+0.000
Top resid features:
Democratic
Token Democratic
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+2.823
Top resid features:
Republican
Token Republican
Feature activation+0.014
Top resid features:
challengers
Token challengers
Feature activation+0.004
Top resid features:
received
Token received
Feature activation+0.030
Top resid features:
33
Token 33
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+1.329
Top resid features:
simulator
Token simulator
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
Calgary
Token Calgary
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+4.168
Top resid features:
Edmonton
Token Edmonton
Feature activation+0.005
Top resid features:
matchup
Token matchup
Feature activation+0.053
Top resid features:
was
Token was
Feature activation+0.017
Top resid features:
8
Token 8
Feature activation+0.057
Top resid features:
.
Token.
Feature activation-0.058
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
6
Token 6
Feature activation+0.003
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.161
Top resid features:
French
Token French
Feature activation+0.029
Top resid features:
and
Token and
Feature activation+4.083
Top resid features:
10
Token 10
Feature activation+0.025
Top resid features:
%
Token%
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
German
Token German
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
discrete
Token discrete
Feature activation+0.006
Top resid features:
NA
Token NA
Feature activation-0.005
Top resid features:
c
Tokenc
Feature activation+0.000
Top resid features:
core
Token core
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+2.480
Top resid features:
shell
Token shell
Feature activation+0.014
Top resid features:
lesions
Token lesions
Feature activation+0.034
Top resid features:
produced
Token produced
Feature activation+0.021
Top resid features:
26
Token 26
Feature activation-0.078
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Main
Token Main
Feature activation-0.000
Top resid features:
Line
Token Line
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
Brook
Token Brook
Feature activation+0.011
Top resid features:
line
Tokenline
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+3.715
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
Upper
Token Upper
Feature activation+0.005
Top resid features:
East
Token East
Feature activation+0.002
Top resid features:
Side
Token Side
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.007
Top resid features:
·
Token·
Feature activation+0.000
Top resid features:
44
Token44
Feature activation-0.001
Top resid features:
).
Token).
Feature activation+0.036
Top resid features:
Extreme
Token Extreme
Feature activation-0.001
Top resid features:
cold
Token cold
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+3.608
Top resid features:
hot
Token hot
Feature activation+0.020
Top resid features:
temperatures
Token temperatures
Feature activation+0.004
Top resid features:
were
Token were
Feature activation-0.012
Top resid features:
responsible
Token responsible
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Blockchain
Token Blockchain
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.008
Top resid features:
Republicans
TokenRepublicans
Feature activation+0.059
Top resid features:
and
Token and
Feature activation+3.729
Top resid features:
Democrats
Token Democrats
Feature activation+0.016
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
world
Token world
Feature activation-0.003
Top resid features:
rankings
Token rankings
Feature activation+0.051
Top resid features:
ahead
Token ahead
Feature activation+0.021
Top resid features:
of
Token of
Feature activation-0.015
Top resid features:
France
Token France
Feature activation+0.048
Top resid features:
and
Token and
Feature activation+3.025
Top resid features:
Brazil
Token Brazil
Feature activation+0.037
Top resid features:
and
Token and
Feature activation+0.474
Top resid features:
into
Token into
Feature activation-0.034
Top resid features:
sixth
Token sixth
Feature activation+0.027
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.097
Top resid features:
equ
Token equ
Feature activation+0.009
Top resid features:
ipping
Tokenipping
Feature activation-0.018
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
Iraqi
Token Iraqi
Feature activation+0.134
Top resid features:
and
Token and
Feature activation+3.081
Top resid features:
Kurdish
Token Kurdish
Feature activation+0.133
Top resid features:
security
Token security
Feature activation+0.122
Top resid features:
forces
Token forces
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.03

Head 5: 0.08

Head 6: 0.05

Head 7: 0.48

Head 8: 0.09

Head 9: 0.02

Head 10: 0.01

Head 11: 0.04

Positive logits

respectively5.83

alike3.83

mutually3.50

respective3.26

Together3.19

Both3.13

together3.12

apiece3.01

Both2.96

jointly2.93

simultaneously2.82

interchange2.75

both2.66

Together2.65

together2.62

toget2.60

concurrently2.59

separately2.52

combined2.50

collide2.49

Negative logits

aroo-2.18

bot-1.82

nil-1.78

enance-1.77

lies-1.75

zar-1.67

msg-1.67

Maduro-1.66

ertodd-1.61

ASON-1.58

proof-1.57

ody-1.57

folk-1.55

outine-1.55

iever-1.54

zsche-1.53

pletion-1.52

DERR-1.52

maid-1.52

mud-1.51

INTERVAL 5.006 - 5.562
CONTAINS 0.000%

and
Token and
Feature activation+0.000
Orange
Token Orange
Feature activation+0.000
counties
Token counties
Feature activation+0.127
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
counties
Token counties
Feature activation+0.127
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
summer
Token summer
Feature activation+0.000
quarter
Token quarter
Feature activation+0.167
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
summer
Token summer
Feature activation+0.000
quarter
Token quarter
Feature activation+0.167
,
Token,
Feature activation+0.466

INTERVAL 4.450 - 5.006
CONTAINS 0.000%

matchup
Token matchup
Feature activation+2.550
was
Token was
Feature activation+0.146
8
Token 8
Feature activation+2.180
.
Token.
Feature activation+2.152
78
Token78
Feature activation+3.723
%
Token%
Feature activation+4.517
possible
Token possible
Feature activation+0.289
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
the
Token the
Feature activation+0.000
out
Token out
Feature activation+0.072
bound
Tokenbound
Feature activation+0.000
moves
Token moves
Feature activation+0.637
making
Token making
Feature activation+0.117
up
Token up
Feature activation+1.090
63
Token 63
Feature activation+4.942
percent
Token percent
Feature activation+4.736
of
Token of
Feature activation+1.662
all
Token all
Feature activation+0.000
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+0.137
bound
Tokenbound
Feature activation+0.000
moves
Token moves
Feature activation+0.637
making
Token making
Feature activation+0.117
up
Token up
Feature activation+1.090
63
Token 63
Feature activation+4.942
percent
Token percent
Feature activation+4.736
of
Token of
Feature activation+1.662
all
Token all
Feature activation+0.000
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+0.137
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.894 - 4.450
CONTAINS 0.001%

were
Token were
Feature activation+1.309
responsible
Token responsible
Feature activation+1.223
for
Token for
Feature activation+0.466
0
Token 0
Feature activation+0.349
·
Token·
Feature activation+1.074
86
Token86
Feature activation+4.283
%
Token%
Feature activation+3.237
(
Token (
Feature activation+0.967
0
Token0
Feature activation+0.143
·
Token·
Feature activation+0.263
84
Token84
Feature activation+2.223
cast
Token cast
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
and
Token and
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224
to
Token to
Feature activation+0.000
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.337 - 3.894
CONTAINS 0.000%

Edmonton
Token Edmonton
Feature activation+1.142
matchup
Token matchup
Feature activation+2.550
was
Token was
Feature activation+0.146
8
Token 8
Feature activation+2.180
.
Token.
Feature activation+2.152
78
Token78
Feature activation+3.723
%
Token%
Feature activation+4.517
possible
Token possible
Feature activation+0.289
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
French
Token French
Feature activation+0.000
and
Token and
Feature activation+0.429
10
Token 10
Feature activation+2.652
%
Token%
Feature activation+3.440
in
Token in
Feature activation+0.074
German
Token German
Feature activation+0.000
;
Token;
Feature activation+0.385
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
Republican
Token Republican
Feature activation+4.039
challengers
Token challengers
Feature activation+0.477
received
Token received
Feature activation+0.191
33
Token 33
Feature activation+2.900
and
Token and
Feature activation+4.252
24
Token 24
Feature activation+3.742
percent
Token percent
Feature activation+4.125
,
Token,
Feature activation+3.980
respectively
Token respectively
Feature activation+0.739
,
Token,
Feature activation+0.641
according
Token according
Feature activation+0.224

INTERVAL 2.781 - 3.337
CONTAINS 0.001%

ability
Tokenability
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.505
5
Token 5
Feature activation+0.879
.
Token.
Feature activation+0.807
6
Token6
Feature activation+2.868
on
Token on
Feature activation+0.000
Quality
Token Quality
Feature activation+0.000
of
Token of
Feature activation+0.000
Life
Token Life
Feature activation+0.000
,
Token,
Feature activation+0.954
Blockchain
Token Blockchain
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Republicans
TokenRepublicans
Feature activation+0.000
and
Token and
Feature activation+0.000
Democrats
Token Democrats
Feature activation+3.218
don
Token don
Feature activation+2.141
âĢ
TokenâĢ
Feature activation+0.128
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.381
entirely
Token entirely
Feature activation+0.729
the
Token the
Feature activation+0.000
Iraqi
Token Iraqi
Feature activation+0.000
and
Token and
Feature activation+0.000
Kurdish
Token Kurdish
Feature activation+1.764
security
Token security
Feature activation+1.892
forces
Token forces
Feature activation+3.047
,
Token,
Feature activation+0.592
and
Token and
Feature activation+0.757
the
Token the
Feature activation+0.416
provision
Token provision
Feature activation+0.008
of
Token of
Feature activation+0.029
Orange
Token Orange
Feature activation+0.000
counties
Token counties
Feature activation+0.127
fell
Token fell
Feature activation+0.572
to
Token to
Feature activation+1.157
46
Token 46
Feature activation+5.562
.
Token.
Feature activation+2.879
6
Token6
Feature activation+5.073
percent
Token percent
Feature activation+5.278
in
Token in
Feature activation+0.617
the
Token the
Feature activation+0.554
summer
Token summer
Feature activation+0.000
France
Token France
Feature activation+0.000
and
Token and
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.399
and
Token and
Feature activation+0.674
into
Token into
Feature activation+0.657
sixth
Token sixth
Feature activation+3.093
place
Token place
Feature activation+1.859
behind
Token behind
Feature activation+0.354
the
Token the
Feature activation+0.267
United
Token United
Feature activation+0.027
Kingdom
Token Kingdom
Feature activation+0.000

INTERVAL 2.225 - 2.781
CONTAINS 0.002%

6
Token 6
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
French
Token French
Feature activation+0.000
and
Token and
Feature activation+0.429
10
Token 10
Feature activation+2.652
%
Token%
Feature activation+3.440
in
Token in
Feature activation+0.074
German
Token German
Feature activation+0.000
;
Token;
Feature activation+0.385
this
Token this
Feature activation+0.000
Sunderland
Token Sunderland
Feature activation+0.000
and
Token and
Feature activation+0.068
Gr
Token Gr
Feature activation+0.000
ims
Tokenims
Feature activation+0.000
by
Tokenby
Feature activation+0.281
met
Token met
Feature activation+2.462
in
Token in
Feature activation+0.035
a
Token a
Feature activation+0.462
group
Token group
Feature activation+0.000
H
Token H
Feature activation+0.000
Check
Token Check
Feature activation+0.000
and
Token and
Feature activation+0.353
Hak
Token Hak
Feature activation+0.000
ush
Tokenush
Feature activation+0.000
u
Tokenu
Feature activation+0.013
whisk
Token whisk
Feature activation+1.813
ies
Tokenies
Feature activation+2.516
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
tensions
Token tensions
Feature activation+0.000
continued
Token continued
Feature activation+0.000
for
Token for
Feature activation+0.000
reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000
British
Token British
Feature activation+0.000
and
Token and
Feature activation+0.000
US
Token US
Feature activation+0.327
intelligence
Token intelligence
Feature activation+2.334
agencies
Token agencies
Feature activation+1.998
had
Token had
Feature activation+0.408
a
Token a
Feature activation+0.775
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.000
c
Tokenc
Feature activation+0.000
and
Token and
Feature activation+0.000
Skype
Token Skype
Feature activation+0.074
by
Token by
Feature activation+0.936
describing
Token describing
Feature activation+2.327
Lyn
Token Lyn
Feature activation+0.000
c
Tokenc
Feature activation+0.393
as
Token as
Feature activation+1.020
Microsoft
Token Microsoft
Feature activation+0.000
's
Token's
Feature activation+0.609

INTERVAL 1.669 - 2.225
CONTAINS 0.010%

and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
systems
Token systems
Feature activation+0.000
hit
Token hit
Feature activation+0.000
$
Token $
Feature activation+2.145
840
Token840
Feature activation+2.115
million
Token million
Feature activation+2.366
in
Token in
Feature activation+0.100
March
Token March
Feature activation+0.440
,
Token,
Feature activation+0.063
In
Token In
Feature activation+0.000
Spanish
Token Spanish
Feature activation+0.000
and
Token and
Feature activation+0.000
French
Token French
Feature activation+0.000
you
Token you
Feature activation+1.675
have
Token have
Feature activation+1.927
the
Token the
Feature activation+1.066
word
Token word
Feature activation+0.174
'
Token '
Feature activation+0.006
Lib
TokenLib
Feature activation+0.000
re
Tokenre
Feature activation+0.000
play
Token play
Feature activation+0.000
the
Token the
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
and
Token and
Feature activation+0.000
Leeds
Token Leeds
Feature activation+0.900
festivals
Token festivals
Feature activation+2.168
last
Token last
Feature activation+0.042
year
Token year
Feature activation+0.294
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
India
Token India
Feature activation+0.000
and
Token and
Feature activation+0.000
China
Token China
Feature activation+0.893
will
Token will
Feature activation+0.806
negotiate
Token negotiate
Feature activation+2.205
for
Token for
Feature activation+0.109
a
Token a
Feature activation+0.600
treaty
Token treaty
Feature activation+1.179
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
5
Token5
Feature activation+0.433
%
Token%
Feature activation+0.936
and
Token and
Feature activation+3.332
17
Token 17
Feature activation+0.549
.
Token.
Feature activation+0.000
4
Token4
Feature activation+1.933
%
Token%
Feature activation+2.097
increase
Token increase
Feature activation+0.720
in
Token in
Feature activation+0.182
total
Token total
Feature activation+0.000
wake
Token wake
Feature activation+0.000

INTERVAL 1.112 - 1.669
CONTAINS 0.025%

in
Tokenin
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.954
second
Token second
Feature activation+1.269
round
Token round
Feature activation+0.525
draft
Token draft
Feature activation+1.189
pick
Token pick
Feature activation+1.133
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
still
Token still
Feature activation+0.000
had
Token had
Feature activation+0.000
-
Token-
Feature activation+0.000
Water
TokenWater
Feature activation+0.000
loo
Tokenloo
Feature activation+0.000
and
Token and
Feature activation+0.072
London
Token London
Feature activation+0.000
,
Token,
Feature activation+1.446
and
Token and
Feature activation+0.957
the
Token the
Feature activation+0.753
âĢ
Token âĢ
Feature activation+0.321
ľ
Tokenľ
Feature activation+0.035
missing
Tokenmissing
Feature activation+0.280
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.000
inger
Tokeninger
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+1.333
per
Token per
Feature activation+1.328
cent
Token cent
Feature activation+1.746
supporting
Token supporting
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
R
Token R
Feature activation+0.000
million
Token million
Feature activation+0.000
and
Token and
Feature activation+0.252
$
Token $
Feature activation+0.000
25
Token25
Feature activation+0.000
million
Token million
Feature activation+0.993
,
Token,
Feature activation+1.261
from
Token from
Feature activation+0.000
U
Token U
Feature activation+0.000
BS
TokenBS
Feature activation+0.000
Real
Token Real
Feature activation+0.000
Estate
Token Estate
Feature activation+0.000
and
Token and
Feature activation+0.000
V
Token V
Feature activation+0.000
MS
TokenMS
Feature activation+0.000
Eve
Token Eve
Feature activation+0.542
test
Token test
Feature activation+0.695
flights
Token flights
Feature activation+1.485
are
Token are
Feature activation+0.067
completed
Token completed
Feature activation+0.000
,
Token,
Feature activation+0.000
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.000

INTERVAL 0.556 - 1.112
CONTAINS 0.104%

alternating
Token alternating
Feature activation+0.000
raised
Token raised
Feature activation+0.000
and
Token and
Feature activation+0.000
lowered
Token lowered
Feature activation+0.000
rid
Token rid
Feature activation+0.000
ges
Tokenges
Feature activation+0.882
along
Token along
Feature activation+0.000
the
Token the
Feature activation+0.000
outer
Token outer
Feature activation+0.000
rim
Token rim
Feature activation+0.000
which
Token which
Feature activation+0.000
and
Token and
Feature activation+0.000
Derek
Token Derek
Feature activation+0.000
New
Token New
Feature activation+0.000
berry
Tokenberry
Feature activation+0.000
,
Token,
Feature activation+0.000
Ph
Token Ph
Feature activation+0.707
.
Token.
Feature activation+0.000
D
TokenD
Feature activation+0.309
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tayyip
Token Tayyip
Feature activation+0.000
Erdogan
Token Erdogan
Feature activation+0.000
and
Token and
Feature activation+0.000
Indonesian
Token Indonesian
Feature activation+0.000
President
Token President
Feature activation+0.866
J
Token J
Feature activation+0.849
oko
Tokenoko
Feature activation+0.248
Wid
Token Wid
Feature activation+0.000
odo
Tokenodo
Feature activation+0.000
in
Token in
Feature activation+0.282
a
Token a
Feature activation+0.040
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
and
Token and
Feature activation+0.000
British
Token British
Feature activation+1.504
had
Token had
Feature activation+0.937
broken
Token broken
Feature activation+0.426
out
Token out
Feature activation+0.732
of
Token of
Feature activation+0.201
their
Token their
Feature activation+0.133
beach
Token beach
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Palin
Token Palin
Feature activation+0.000
and
Token and
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
Bruce
Token Bruce
Feature activation+0.050
aren
Token aren
Feature activation+0.986
't
Token't
Feature activation+0.605
your
Token your
Feature activation+0.703
favourites
Token favourites
Feature activation+1.676
.
Token.
Feature activation+0.135
Ċ
TokenĊ
Feature activation+0.002

INTERVAL 0.000 - 0.556
CONTAINS 99.857%

ates
Tokenates
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
credit
Token credit
Feature activation+0.000
rating
Token rating
Feature activation+0.000
reflects
Token reflects
Feature activation+0.000
their
Token their
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
debtor
Token debtor
Feature activation+0.000
leader
Tokenleader
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
after
Token after
Feature activation+0.000
commenting
Token commenting
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
party
Token party
Feature activation+0.000
conference
Token conference
Feature activation+0.000
,
Token,
Feature activation+0.000
Burn
Token Burn
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
"
Token "
Feature activation+0.000
evidence
Tokenevidence
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
none
Token none
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
limit
Token limit
Feature activation+0.000
increase
Token increase
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
contingent
Token contingent
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
towards
Token towards
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
with
Token with
Feature activation+0.000
Maine
Token Maine
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 1 in H6.7: (feature 4639)

TOP ACTIVATIONS
MAX = 2.281

on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
son
Tokenson
Feature activation+0.000
before
Token before
Feature activation+1.041
handc
Token handc
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
son
Tokenson
Feature activation+0.000
before
Token before
Feature activation+1.041
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.111
Ŀ
TokenĿ
Feature activation+1.091
he
Token he
Feature activation+1.514
explained
Token explained
Feature activation+2.070
during
Token during
Feature activation+1.201
the
Token the
Feature activation+0.462
meeting
Token meeting
Feature activation+0.166
in
Token in
Feature activation+0.162
Montreal
Token Montreal
Feature activation+0.000
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+1.490
Judge
Token Judge
Feature activation+1.196
Carm
Token Carm
Feature activation+0.678
ody
Tokenody
Feature activation+0.863
said
Token said
Feature activation+1.947
.
Token.
Feature activation+0.435
Ċ
TokenĊ
Feature activation+0.283
Ċ
TokenĊ
Feature activation+0.126
This
TokenThis
Feature activation+0.000
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
bond
Token bond
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
'll
Token'll
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
,"
Token,"
Feature activation+0.579
Trump
Token Trump
Feature activation+0.350
told
Token told
Feature activation+1.919
voters
Token voters
Feature activation+0.272
during
Token during
Feature activation+0.083
an
Token an
Feature activation+0.000
evening
Token evening
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.332
Matt
Token Matt
Feature activation+0.123
,''
Token,''
Feature activation+1.468
he
Token he
Feature activation+1.459
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
.
Token.
Feature activation+1.503
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,"
Token,"
Feature activation+1.158
Kasich
Token Kasich
Feature activation+0.711
told
Token told
Feature activation+1.763
his
Token his
Feature activation+0.000
kickoff
Token kickoff
Feature activation+0.000
rally
Token rally
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,''
Token,''
Feature activation+1.623
I
Token I
Feature activation+1.214
said
Token said
Feature activation+1.746
,
Token,
Feature activation+1.090
st
Token st
Feature activation+0.317
uttering
Tokenuttering
Feature activation+0.199
.
Token.
Feature activation+0.590
''
Token ''
Feature activation+0.209
those
Token those
Feature activation+0.000
caucuses
Token caucuses
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
,"
Token,"
Feature activation+1.734
he
Token he
Feature activation+1.455
impl
Token impl
Feature activation+0.417
ored
Tokenored
Feature activation+1.072
the
Token the
Feature activation+0.224
crowd
Token crowd
Feature activation+0.000
Mr
Token Mr
Feature activation+0.071
.
Token.
Feature activation+0.000
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,''
Token,''
Feature activation+1.623
I
Token I
Feature activation+1.214
said
Token said
Feature activation+1.746
,
Token,
Feature activation+1.090
st
Token st
Feature activation+0.317
uttering
Tokenuttering
Feature activation+0.199
love
Token love
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.111
Ŀ
TokenĿ
Feature activation+1.091
he
Token he
Feature activation+1.514
explained
Token explained
Feature activation+2.070
during
Token during
Feature activation+1.201
the
Token the
Feature activation+0.462
meeting
Token meeting
Feature activation+0.166
in
Token in
Feature activation+0.162
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
.
Token.
Feature activation+1.503
''
Token ''
Feature activation+0.000
Listen
TokenListen
Feature activation+0.000
,''
Token,''
Feature activation+0.544
he
Token he
Feature activation+0.456
told
Token told
Feature activation+1.192
pray
Token pray
Feature activation+0.000
,"
Token,"
Feature activation+0.858
Kam
Token Kam
Feature activation+0.000
y
Tokeny
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
told
Token told
Feature activation+1.495
me
Token me
Feature activation+0.085
.
Token.
Feature activation+0.387
Ċ
TokenĊ
Feature activation+0.320
Ċ
TokenĊ
Feature activation+0.223
Buzz
TokenBuzz
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
,
Token,
Feature activation+0.000
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+1.490
Judge
Token Judge
Feature activation+1.196
Carm
Token Carm
Feature activation+0.678
ody
Tokenody
Feature activation+0.863
said
Token said
Feature activation+1.947
.
Token.
Feature activation+0.435
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.332
Matt
Token Matt
Feature activation+0.123
,''
Token,''
Feature activation+1.468
he
Token he
Feature activation+1.459
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
meet
Token meet
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.332
Matt
Token Matt
Feature activation+0.123
,''
Token,''
Feature activation+1.468
he
Token he
Feature activation+1.459
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
caucuses
Token caucuses
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
,"
Token,"
Feature activation+1.734
he
Token he
Feature activation+1.455
impl
Token impl
Feature activation+0.417
ored
Tokenored
Feature activation+1.072
the
Token the
Feature activation+0.224
crowd
Token crowd
Feature activation+0.000
.
Token.
Feature activation+0.353
just
Token just
Feature activation+0.044
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
!'
Token!'
Feature activation+1.360
Carter
Token Carter
Feature activation+0.654
wrote
Token wrote
Feature activation+1.173
in
Token in
Feature activation+1.183
one
Token one
Feature activation+0.028
message
Token message
Feature activation+0.207
Are
TokenAre
Feature activation+0.000
you
Token you
Feature activation+0.000
ready
Token ready
Feature activation+0.000
now
Token now
Feature activation+0.121
?"
Token?"
Feature activation+0.780
Ċ
TokenĊ
Feature activation+1.353
Ċ
TokenĊ
Feature activation+0.910
Am
TokenAm
Feature activation+0.000
anda
Tokenanda
Feature activation+0.000
omin
Token omin
Feature activation+0.000
ously
Tokenously
Feature activation+0.000

Top DFA by src position
MAX = 2.441

"
Token"
Feature activation-0.000
Top resid features:
Let
TokenLet
Feature activation+0.070
Top resid features:
me
Token me
Feature activation+0.054
Top resid features:
see
Token see
Feature activation+0.194
Top resid features:
if
Token if
Feature activation+0.154
Top resid features:
you
Token you
Feature activation+2.257
Top resid features:
can
Token can
Feature activation+0.046
Top resid features:
bond
Token bond
Feature activation+0.033
Top resid features:
off
Token off
Feature activation+0.010
Top resid features:
on
Token on
Feature activation+0.011
Top resid features:
this
Token this
Feature activation+0.015
Top resid features:
"
Token"
Feature activation-0.007
Top resid features:
Let
TokenLet
Feature activation+0.060
Top resid features:
me
Token me
Feature activation+0.057
Top resid features:
see
Token see
Feature activation+0.285
Top resid features:
if
Token if
Feature activation+0.080
Top resid features:
you
Token you
Feature activation+2.111
Top resid features:
can
Token can
Feature activation+0.086
Top resid features:
bond
Token bond
Feature activation+0.058
Top resid features:
off
Token off
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.016
Top resid features:
this
Token this
Feature activation+0.021
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
We
TokenWe
Feature activation+0.085
Top resid features:
love
Token love
Feature activation+0.167
Top resid features:
death
Token death
Feature activation-0.004
Top resid features:
like
Token like
Feature activation-0.006
Top resid features:
you
Token you
Feature activation+2.351
Top resid features:
love
Token love
Feature activation+0.015
Top resid features:
life
Token life
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+0.127
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ŀ
TokenĿ
Feature activation+0.032
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
childhood
Token childhood
Feature activation+0.002
Top resid features:
abuse
Token abuse
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
"
Token "
Feature activation+0.002
Top resid features:
Your
TokenYour
Feature activation+2.441
Top resid features:
prospects
Token prospects
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
rehabilitation
Token rehabilitation
Feature activation+0.009
Top resid features:
are
Token are
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
"
Token"
Feature activation-0.030
Top resid features:
Let
TokenLet
Feature activation+0.066
Top resid features:
me
Token me
Feature activation+0.181
Top resid features:
see
Token see
Feature activation+0.312
Top resid features:
if
Token if
Feature activation+0.161
Top resid features:
you
Token you
Feature activation+1.562
Top resid features:
can
Token can
Feature activation+0.048
Top resid features:
bond
Token bond
Feature activation+0.032
Top resid features:
off
Token off
Feature activation+0.024
Top resid features:
on
Token on
Feature activation+0.015
Top resid features:
this
Token this
Feature activation+0.044
Top resid features:
reported
Token reported
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
"
Token"
Feature activation+0.002
Top resid features:
You
TokenYou
Feature activation+2.288
Top resid features:
know
Token know
Feature activation+0.047
Top resid features:
Bernie
Token Bernie
Feature activation+0.015
Top resid features:
wanted
Token wanted
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
debate
Token debate
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
''
Token''
Feature activation-0.069
Top resid features:
Nice
TokenNice
Feature activation+0.117
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
meet
Token meet
Feature activation+0.244
Top resid features:
you
Token you
Feature activation+1.548
Top resid features:
,
Token,
Feature activation+0.458
Top resid features:
Matt
Token Matt
Feature activation+0.036
Top resid features:
,''
Token,''
Feature activation+0.167
Top resid features:
he
Token he
Feature activation-0.109
Top resid features:
said
Token said
Feature activation-0.030
Top resid features:
I
TokenI
Feature activation+0.013
Top resid features:
am
Token am
Feature activation+0.031
Top resid features:
here
Token here
Feature activation+0.078
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
ask
Token ask
Feature activation+0.026
Top resid features:
you
Token you
Feature activation+1.764
Top resid features:
for
Token for
Feature activation+0.073
Top resid features:
your
Token your
Feature activation+0.090
Top resid features:
prayers
Token prayers
Feature activation+0.126
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
Uh
TokenUh
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
I
Token I
Feature activation+0.047
Top resid features:
know
Token know
Feature activation+0.034
Top resid features:
who
Token who
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+1.520
Top resid features:
are
Token are
Feature activation+0.342
Top resid features:
,
Token,
Feature activation+0.138
Top resid features:
Mr
Token Mr
Feature activation+0.144
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Mat
Token Mat
Feature activation+0.010
Top resid features:
states
Token states
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
"
Token"
Feature activation-0.032
Top resid features:
Your
TokenYour
Feature activation+1.649
Top resid features:
caucus
Token caucus
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
your
Token your
Feature activation+0.029
Top resid features:
voice
Token voice
Feature activation+0.012
Top resid features:
will
Token will
Feature activation+0.065
Top resid features:
Uh
TokenUh
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.165
Top resid features:
I
Token I
Feature activation+0.101
Top resid features:
know
Token know
Feature activation+0.059
Top resid features:
who
Token who
Feature activation+0.030
Top resid features:
you
Token you
Feature activation+0.755
Top resid features:
are
Token are
Feature activation+0.522
Top resid features:
,
Token,
Feature activation+0.162
Top resid features:
Mr
Token Mr
Feature activation+0.219
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
Mat
Token Mat
Feature activation+0.020
Top resid features:
ľ
Tokenľ
Feature activation+0.008
Top resid features:
We
TokenWe
Feature activation+0.174
Top resid features:
love
Token love
Feature activation+0.315
Top resid features:
death
Token death
Feature activation-0.002
Top resid features:
like
Token like
Feature activation-0.010
Top resid features:
you
Token you
Feature activation+1.317
Top resid features:
love
Token love
Feature activation+0.026
Top resid features:
life
Token life
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.198
Top resid features:
âĢ
TokenâĢ
Feature activation+0.054
Top resid features:
Ŀ
TokenĿ
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
''
Token''
Feature activation-0.111
Top resid features:
Nice
TokenNice
Feature activation+0.060
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
meet
Token meet
Feature activation+0.181
Top resid features:
you
Token you
Feature activation+1.759
Top resid features:
,
Token,
Feature activation+0.243
Top resid features:
Matt
Token Matt
Feature activation+0.047
Top resid features:
,''
Token,''
Feature activation+0.048
Top resid features:
he
Token he
Feature activation-0.050
Top resid features:
said
Token said
Feature activation-0.029
Top resid features:
wer
Tokenwer
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
I
Token I
Feature activation+0.011
Top resid features:
feel
Token feel
Feature activation-0.000
Top resid features:
like
Token like
Feature activation-0.010
Top resid features:
you
Token you
Feature activation+1.525
Top resid features:
guys
Token guys
Feature activation+0.454
Top resid features:
used
Token used
Feature activation+0.006
Top resid features:
me
Token me
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
he
Token he
Feature activation+0.039
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
childhood
Token childhood
Feature activation+0.001
Top resid features:
abuse
Token abuse
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
"
Token "
Feature activation-0.036
Top resid features:
Your
TokenYour
Feature activation+1.915
Top resid features:
prospects
Token prospects
Feature activation+0.035
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
rehabilitation
Token rehabilitation
Feature activation+0.010
Top resid features:
are
Token are
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
''
Token''
Feature activation-0.123
Top resid features:
Nice
TokenNice
Feature activation+0.198
Top resid features:
to
Token to
Feature activation+0.066
Top resid features:
meet
Token meet
Feature activation+0.291
Top resid features:
you
Token you
Feature activation+1.104
Top resid features:
,
Token,
Feature activation+0.359
Top resid features:
Matt
Token Matt
Feature activation+0.081
Top resid features:
,''
Token,''
Feature activation+0.043
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
''
Token''
Feature activation-0.083
Top resid features:
Nice
TokenNice
Feature activation+0.173
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
meet
Token meet
Feature activation+0.196
Top resid features:
you
Token you
Feature activation+0.957
Top resid features:
,
Token,
Feature activation+0.435
Top resid features:
Matt
Token Matt
Feature activation+0.062
Top resid features:
,''
Token,''
Feature activation+0.205
Top resid features:
he
Token he
Feature activation-0.006
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
states
Token states
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
"
Token"
Feature activation-0.020
Top resid features:
Your
TokenYour
Feature activation+1.372
Top resid features:
caucus
Token caucus
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
your
Token your
Feature activation+0.034
Top resid features:
voice
Token voice
Feature activation+0.008
Top resid features:
will
Token will
Feature activation+0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
'
Token'
Feature activation-0.019
Top resid features:
I
TokenI
Feature activation+0.052
Top resid features:
thought
Token thought
Feature activation-0.024
Top resid features:
you
Token you
Feature activation+1.073
Top resid features:
wanted
Token wanted
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
do
Token do
Feature activation+0.022
Top resid features:
this
Token this
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.180
Top resid features:
Victoria
Token Victoria
Feature activation+0.022
Top resid features:
says
Token says
Feature activation+0.055
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
"
Token "
Feature activation+0.003
Top resid features:
Are
TokenAre
Feature activation+0.083
Top resid features:
you
Token you
Feature activation+0.458
Top resid features:
ready
Token ready
Feature activation+0.329
Top resid features:
now
Token now
Feature activation+0.361
Top resid features:
?"
Token?"
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.04

Head 3: 0.06

Head 4: 0.08

Head 5: 0.10

Head 6: 0.06

Head 7: 0.43

Head 8: 0.05

Head 9: 0.02

Head 10: 0.04

Head 11: 0.05

Positive logits

greeting3.11

greet2.66

handshake2.60

exchanged2.47

tatt2.41

attm2.39

verbally2.35

swearing2.34

salute2.29

kissing2.28

kiss2.27

kisses2.26

insulted2.26

taunt2.25

reply2.24

convers2.20

Pledge2.19

politely2.18

insulting2.18

Instr2.16

Negative logits

developments-2.32

omics-2.13

Epidem-2.05

NTS-2.04

Architects-2.03

deregulation-2.01

Analysis-2.00

iland-1.99

structural-1.98

Recommend-1.95

ogeneity-1.95

limitations-1.92

trends-1.92

NCT-1.89

regress-1.88

PB-1.86

Analysis-1.86

ipel-1.85

opathy-1.82

htaking-1.80

INTERVAL 2.053 - 2.281
CONTAINS 0.000%

life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.111
Ŀ
TokenĿ
Feature activation+1.091
he
Token he
Feature activation+1.514
explained
Token explained
Feature activation+2.070
during
Token during
Feature activation+1.201
the
Token the
Feature activation+0.462
meeting
Token meeting
Feature activation+0.166
in
Token in
Feature activation+0.162
Montreal
Token Montreal
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
son
Tokenson
Feature activation+0.000
before
Token before
Feature activation+1.041
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
son
Tokenson
Feature activation+0.000
before
Token before
Feature activation+1.041
handc
Token handc
Feature activation+0.000

INTERVAL 1.824 - 2.053
CONTAINS 0.000%

can
Token can
Feature activation+0.000
bond
Token bond
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
,"
Token,"
Feature activation+1.944
Watts
Token Watts
Feature activation+0.640
said
Token said
Feature activation+2.148
to
Token to
Feature activation+2.281
G
Token G
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
'll
Token'll
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
,"
Token,"
Feature activation+0.579
Trump
Token Trump
Feature activation+0.350
told
Token told
Feature activation+1.919
voters
Token voters
Feature activation+0.272
during
Token during
Feature activation+0.083
an
Token an
Feature activation+0.000
evening
Token evening
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+1.490
Judge
Token Judge
Feature activation+1.196
Carm
Token Carm
Feature activation+0.678
ody
Tokenody
Feature activation+0.863
said
Token said
Feature activation+1.947
.
Token.
Feature activation+0.435
Ċ
TokenĊ
Feature activation+0.283
Ċ
TokenĊ
Feature activation+0.126
This
TokenThis
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.596 - 1.824
CONTAINS 0.001%

those
Token those
Feature activation+0.000
caucuses
Token caucuses
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
,"
Token,"
Feature activation+1.734
he
Token he
Feature activation+1.455
impl
Token impl
Feature activation+0.417
ored
Tokenored
Feature activation+1.072
the
Token the
Feature activation+0.224
crowd
Token crowd
Feature activation+0.000
Mr
Token Mr
Feature activation+0.071
.
Token.
Feature activation+0.000
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,''
Token,''
Feature activation+1.623
I
Token I
Feature activation+1.214
said
Token said
Feature activation+1.746
,
Token,
Feature activation+1.090
st
Token st
Feature activation+0.317
uttering
Tokenuttering
Feature activation+0.199
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,''
Token,''
Feature activation+1.623
I
Token I
Feature activation+1.214
said
Token said
Feature activation+1.746
,
Token,
Feature activation+1.090
st
Token st
Feature activation+0.317
uttering
Tokenuttering
Feature activation+0.199
.
Token.
Feature activation+0.590
''
Token ''
Feature activation+0.209
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.332
Matt
Token Matt
Feature activation+0.123
,''
Token,''
Feature activation+1.468
he
Token he
Feature activation+1.459
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
.
Token.
Feature activation+1.503
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,"
Token,"
Feature activation+1.158
Kasich
Token Kasich
Feature activation+0.711
told
Token told
Feature activation+1.763
his
Token his
Feature activation+0.000
kickoff
Token kickoff
Feature activation+0.000
rally
Token rally
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.368 - 1.596
CONTAINS 0.001%

said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
.
Token.
Feature activation+1.503
''
Token ''
Feature activation+0.000
Listen
TokenListen
Feature activation+0.000
,''
Token,''
Feature activation+0.544
he
Token he
Feature activation+0.456
told
Token told
Feature activation+1.192
love
Token love
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.111
Ŀ
TokenĿ
Feature activation+1.091
he
Token he
Feature activation+1.514
explained
Token explained
Feature activation+2.070
during
Token during
Feature activation+1.201
the
Token the
Feature activation+0.462
meeting
Token meeting
Feature activation+0.166
in
Token in
Feature activation+0.162
meet
Token meet
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.332
Matt
Token Matt
Feature activation+0.123
,''
Token,''
Feature activation+1.468
he
Token he
Feature activation+1.459
said
Token said
Feature activation+1.776
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.484
firm
Token firm
Feature activation+0.402
handshake
Token handshake
Feature activation+0.309
caucuses
Token caucuses
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
,"
Token,"
Feature activation+1.734
he
Token he
Feature activation+1.455
impl
Token impl
Feature activation+0.417
ored
Tokenored
Feature activation+1.072
the
Token the
Feature activation+0.224
crowd
Token crowd
Feature activation+0.000
.
Token.
Feature activation+0.353
pray
Token pray
Feature activation+0.000
,"
Token,"
Feature activation+0.858
Kam
Token Kam
Feature activation+0.000
y
Tokeny
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
told
Token told
Feature activation+1.495
me
Token me
Feature activation+0.085
.
Token.
Feature activation+0.387
Ċ
TokenĊ
Feature activation+0.320
Ċ
TokenĊ
Feature activation+0.223
Buzz
TokenBuzz
Feature activation+0.000

INTERVAL 1.140 - 1.368
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,''
Token,''
Feature activation+1.623
I
Token I
Feature activation+1.214
said
Token said
Feature activation+1.746
,
Token,
Feature activation+1.090
st
Token st
Feature activation+0.317
uttering
Tokenuttering
Feature activation+0.199
.
Token.
Feature activation+0.590
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
ality
Tokenality
Feature activation+0.000
,"
Token,"
Feature activation+1.155
Victoria
Token Victoria
Feature activation+0.043
says
Token says
Feature activation+1.210
.
Token.
Feature activation+0.286
"
Token "
Feature activation+0.000
Are
TokenAre
Feature activation+0.000
you
Token you
Feature activation+0.000
ready
Token ready
Feature activation+0.000
groin
Token groin
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.232
Ŀ
TokenĿ
Feature activation+0.134
Ċ
TokenĊ
Feature activation+1.268
Ċ
TokenĊ
Feature activation+0.884
I
TokenI
Feature activation+0.246
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
love
Token love
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.673
Ċ
TokenĊ
Feature activation+1.347
Ċ
TokenĊ
Feature activation+0.609
<
Token<
Feature activation+0.375
3
Token3
Feature activation+0.206
Barbara
Token Barbara
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+1.503
''
Token ''
Feature activation+0.000
Listen
TokenListen
Feature activation+0.000
,''
Token,''
Feature activation+0.544
he
Token he
Feature activation+0.456
told
Token told
Feature activation+1.192
me
Token me
Feature activation+0.306
,
Token,
Feature activation+0.219
as
Token as
Feature activation+0.000
if
Token if
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 0.912 - 1.140
CONTAINS 0.003%

please
Token please
Feature activation+0.293
,
Token,
Feature activation+0.171
âĢ
TokenâĢ
Feature activation+0.863
Ŀ
TokenĿ
Feature activation+0.892
I
Token I
Feature activation+0.911
said
Token said
Feature activation+0.992
,
Token,
Feature activation+0.747
and
Token and
Feature activation+0.392
then
Token then
Feature activation+0.000
he
Token he
Feature activation+0.156
left
Token left
Feature activation+0.000
,"
Token,"
Feature activation+1.139
offered
Token offered
Feature activation+1.325
B
Token B
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
an
Tokenan
Feature activation+0.655
.
Token.
Feature activation+0.994
And
Token And
Feature activation+0.701
so
Token so
Feature activation+0.827
he
Token he
Feature activation+0.839
did
Token did
Feature activation+0.808
.
Token.
Feature activation+0.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Introdu
TokenIntrodu
Feature activation+0.000
cing
Tokencing
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
is
Token is
Feature activation+1.061
also
Token also
Feature activation+0.365
quite
Token quite
Feature activation+0.433
important
Token important
Feature activation+0.484
in
Token in
Feature activation+0.533
the
Token the
Feature activation+0.146
you
Token you
Feature activation+0.000
in
Token in
Feature activation+0.000
small
Token small
Feature activation+0.000
kids
Token kids
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
?"
Token?"
Feature activation+1.070
was
Token was
Feature activation+0.925
the
Token the
Feature activation+0.630
first
Token first
Feature activation+0.249
response
Token response
Feature activation+0.890
of
Token of
Feature activation+0.519
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.211
Ŀ
TokenĿ
Feature activation+0.212
Br
Token Br
Feature activation+0.224
onson
Tokenonson
Feature activation+0.511
told
Token told
Feature activation+1.020
his
Token his
Feature activation+0.000
employees
Token employees
Feature activation+0.137
.
Token.
Feature activation+0.208
Ċ
TokenĊ
Feature activation+0.161
Ċ
TokenĊ
Feature activation+0.154

INTERVAL 0.684 - 0.912
CONTAINS 0.006%

Santa
Token Santa
Feature activation+0.000
,
Token,
Feature activation+0.000
please
Token please
Feature activation+0.000
bring
Token bring
Feature activation+0.000
me
Token me
Feature activation+0.000
..."
Token ..."
Feature activation+0.883
(
Token (
Feature activation+0.615
1
Token1
Feature activation+0.057
.
Token.
Feature activation+0.079
16
Token16
Feature activation+0.000
)
Token)
Feature activation+0.199
,
Token,
Feature activation+0.094
âĢ
TokenâĢ
Feature activation+0.641
Ŀ
TokenĿ
Feature activation+0.655
the
Token the
Feature activation+0.840
man
Token man
Feature activation+0.633
says
Token says
Feature activation+0.876
âĢĶ
TokenâĢĶ
Feature activation+0.074
and
Tokenand
Feature activation+0.073
then
Token then
Feature activation+0.000
just
Token just
Feature activation+0.000
like
Token like
Feature activation+0.000
of
Token of
Feature activation+0.000
luck
Token luck
Feature activation+0.000
,
Token,
Feature activation+0.094
âĢ
TokenâĢ
Feature activation+0.641
Ŀ
TokenĿ
Feature activation+0.655
the
Token the
Feature activation+0.840
man
Token man
Feature activation+0.633
says
Token says
Feature activation+0.876
âĢĶ
TokenâĢĶ
Feature activation+0.074
and
Tokenand
Feature activation+0.073
then
Token then
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.349
Ŀ
TokenĿ
Feature activation+0.385
Ċ
TokenĊ
Feature activation+0.661
Ċ
TokenĊ
Feature activation+0.600
Me
TokenMe
Feature activation+0.078
:
Token:
Feature activation+0.798
*
Token *
Feature activation+0.154
gr
Tokengr
Feature activation+0.000
inning
Tokeninning
Feature activation+0.000
but
Token but
Feature activation+0.000
saying
Token saying
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
an
Tokenan
Feature activation+0.655
.
Token.
Feature activation+0.994
And
Token And
Feature activation+0.701
so
Token so
Feature activation+0.827
he
Token he
Feature activation+0.839
did
Token did
Feature activation+0.808
.
Token.
Feature activation+0.904
Ċ
TokenĊ
Feature activation+0.873
Ċ
TokenĊ
Feature activation+0.581
There
TokenThere
Feature activation+0.235

INTERVAL 0.456 - 0.684
CONTAINS 0.014%

homosexuality
Token homosexuality
Feature activation+0.000
too
Token too
Feature activation+0.000
?
Token?
Feature activation+0.272
âĢ
TokenâĢ
Feature activation+0.624
Ŀ
TokenĿ
Feature activation+0.248
Ram
Token Ram
Feature activation+0.511
id
Tokenid
Feature activation+0.000
asked
Token asked
Feature activation+0.567
.
Token.
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.096
Ċ
TokenĊ
Feature activation+0.000
eviction
Token eviction
Feature activation+0.000
notice
Token notice
Feature activation+0.000
is
Token is
Feature activation+0.000
served
Token served
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.590
Ŀ
TokenĿ
Feature activation+0.420
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
6
Token 6
Feature activation+0.000
-
Token-
Feature activation+0.000
boyfriend
Token boyfriend
Feature activation+0.000
or
Token or
Feature activation+0.000
girlfriend
Token girlfriend
Feature activation+0.000
left
Token left
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.582
and
Token and
Feature activation+0.672
now
Token now
Feature activation+0.041
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
beating
Token beating
Feature activation+0.000
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
in
Token in
Feature activation+0.000
DC
Token DC
Feature activation+0.000
!
Token!
Feature activation+0.000
Posted
Token Posted
Feature activation+0.537
by
Token by
Feature activation+0.205
Bob
Token Bob
Feature activation+0.000
Young
Token Young
Feature activation+0.000
,
Token,
Feature activation+0.042
Jr
Token Jr
Feature activation+0.000
f
Token f
Feature activation+0.000
***
Token***
Feature activation+0.000
ing
Tokening
Feature activation+0.000
connectors
Token connectors
Feature activation+0.000
!
Token!
Feature activation+0.143
âĢ
TokenâĢ
Feature activation+0.537
Ŀ
TokenĿ
Feature activation+0.437
Ċ
TokenĊ
Feature activation+0.714
Ċ
TokenĊ
Feature activation+0.473
Me
TokenMe
Feature activation+0.000
:
Token:
Feature activation+0.510

INTERVAL 0.228 - 0.456
CONTAINS 0.040%

have
Token have
Feature activation+0.000
Ebola
Token Ebola
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.109
Ŀ
TokenĿ
Feature activation+0.138
according
Token according
Feature activation+0.418
to
Token to
Feature activation+0.281
authorities
Token authorities
Feature activation+0.000
.
Token.
Feature activation+0.034
Ċ
TokenĊ
Feature activation+0.366
Ċ
TokenĊ
Feature activation+0.119
message
Tokenmessage
Feature activation+0.000
_
Token_
Feature activation+0.000
id
Tokenid
Feature activation+0.000
"]
Token"]
Feature activation+0.000
;
Token;
Feature activation+0.000
3
Token 3
Feature activation+0.273
$
Token $
Feature activation+0.000
upload
Tokenupload
Feature activation+0.000
_
Token_
Feature activation+0.000
dir
Tokendir
Feature activation+0.000
=
Token =
Feature activation+0.000
way
Token way
Feature activation+0.000
in
Token in
Feature activation+0.000
there
Token there
Feature activation+0.000
;
Token ;
Feature activation+0.238
-)
Token-)
Feature activation+0.095
Ċ
TokenĊ
Feature activation+0.379
Ċ
TokenĊ
Feature activation+0.107
A
TokenA
Feature activation+0.000
comment
Token comment
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
it
Token it
Feature activation+0.000
out
Token out
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.389
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.308
âĢ
TokenâĢ
Feature activation+0.035
Ŀ
TokenĿ
Feature activation+0.118
Ċ
TokenĊ
Feature activation+0.442
Ċ
TokenĊ
Feature activation+0.238
However
TokenHowever
Feature activation+0.239
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
with
Token with
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.142
She
Token She
Feature activation+0.239
tells
Token tells
Feature activation+0.000
him
Token him
Feature activation+0.000
she
Token she
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000

INTERVAL 0.000 - 0.228
CONTAINS 99.932%

the
Token the
Feature activation+0.000
chair
Token chair
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
s
Token s
Feature activation+0.000
ifting
Tokenifting
Feature activation+0.000
of
Token of
Feature activation+0.000
white
Token white
Feature activation+0.000
has
Token has
Feature activation+0.000
completely
Token completely
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
were
Token were
Feature activation+0.000
sent
Token sent
Feature activation+0.000
home
Token home
Feature activation+0.000
early
Token early
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
officers
Token officers
Feature activation+0.000
first
Token first
Feature activation+0.000
a
Token a
Feature activation+0.000
Univ
Token Univ
Feature activation+0.000
ision
Tokenision
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
data
Token data
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
of
Token of
Feature activation+0.000
peer
Token peer
Feature activation+0.000
review
Token review
Feature activation+0.000
for
Token for
Feature activation+0.000
grant
Token grant
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
.
Token.
Feature activation+0.000
Science
Token Science
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
crew
Token crew
Feature activation+0.000
--
Token --
Feature activation+0.000
which
Token which
Feature activation+0.000
shot
Token shot
Feature activation+0.000
all
Token all
Feature activation+0.000
but
Token but
Feature activation+0.000
seven
Token seven
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
in
Token in
Feature activation+0.000
Oregon
Token Oregon
Feature activation+0.000
and
Token and
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H6.7: (feature 5505)

TOP ACTIVATIONS
MAX = 1.863

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
its
Tokenits
Feature activation+0.000
Falling
Token Falling
Feature activation+1.424
Ċ
TokenĊ
Feature activation+1.863
Ċ
TokenĊ
Feature activation+1.335
Netflix
TokenNetflix
Feature activation+0.000
posted
Token posted
Feature activation+0.003
a
Token a
Feature activation+0.069
91
Token 91
Feature activation+0.266
epidemic
Token epidemic
Feature activation+0.000
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.000
financial
Token financial
Feature activation+0.000
ramifications
Token ramifications
Feature activation+1.485
for
Token for
Feature activation+1.821
the
Token the
Feature activation+1.089
institutions
Token institutions
Feature activation+0.000
that
Token that
Feature activation+0.000
must
Token must
Feature activation+0.017
treat
Token treat
Feature activation+0.000
The
Token The
Feature activation+0.000
Gym
Token Gym
Feature activation+0.000
.
Token.
Feature activation+0.000
Prices
Token Prices
Feature activation+0.000
vary
Token vary
Feature activation+0.386
in
Token in
Feature activation+1.570
locations
Token locations
Feature activation+0.488
around
Token around
Feature activation+0.417
London
Token London
Feature activation+0.000
but
Token but
Feature activation+0.218
it
Token it
Feature activation+0.107
This
Token This
Feature activation+0.000
epidemic
Token epidemic
Feature activation+0.000
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.000
financial
Token financial
Feature activation+0.000
ramifications
Token ramifications
Feature activation+1.485
for
Token for
Feature activation+1.821
the
Token the
Feature activation+1.089
institutions
Token institutions
Feature activation+0.000
that
Token that
Feature activation+0.000
must
Token must
Feature activation+0.017
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
its
Tokenits
Feature activation+0.000
Falling
Token Falling
Feature activation+1.424
Ċ
TokenĊ
Feature activation+1.863
Ċ
TokenĊ
Feature activation+1.335
Netflix
TokenNetflix
Feature activation+0.000
posted
Token posted
Feature activation+0.003
a
Token a
Feature activation+0.069
very
Token very
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
for
Token for
Feature activation+0.161
the
Token the
Feature activation+0.496
state
Token state
Feature activation+0.000
.
Token.
Feature activation+1.412
Homeless
Token Homeless
Feature activation+0.000
shelters
Token shelters
Feature activation+0.000
cost
Token cost
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.338
Pistol
Token Pistol
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
tag
Token tag
Feature activation+0.280
.
Token.
Feature activation+1.397
At
Token At
Feature activation+0.545
just
Token just
Feature activation+0.053
$
Token $
Feature activation+0.000
8
Token8
Feature activation+0.000
49
Token49
Feature activation+0.000
and
Token and
Feature activation+0.000
pay
Token pay
Feature activation+0.000
-
Token-
Feature activation+0.326
to
Tokento
Feature activation+0.192
-
Token-
Feature activation+0.388
play
Tokenplay
Feature activation+1.386
songs
Token songs
Feature activation+0.430
are
Token are
Feature activation+0.645
added
Token added
Feature activation+0.422
to
Token to
Feature activation+0.106
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
was
Token was
Feature activation+0.000
simply
Token simply
Feature activation+0.000
financial
Token financial
Feature activation+0.000
.
Token.
Feature activation+1.374
Until
Token Until
Feature activation+0.933
the
Token the
Feature activation+0.181
French
Token French
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
,
Token,
Feature activation+0.073
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
costs
Token costs
Feature activation+0.000
taxpayers
Token taxpayers
Feature activation+0.000
money
Token money
Feature activation+0.499
.
Token.
Feature activation+1.348
Curious
Token Curious
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
chance
Token chance
Feature activation+0.000
of
Token of
Feature activation+0.000
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
profit
Token profit
Feature activation+0.072
with
Token with
Feature activation+1.339
your
Token your
Feature activation+0.808
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
betting
Token betting
Feature activation+0.000
this
Token this
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
monthly
Token monthly
Feature activation+0.000
fee
Token fee
Feature activation+0.641
which
Token which
Feature activation+0.988
makes
Token makes
Feature activation+1.339
them
Token them
Feature activation+1.022
a
Token a
Feature activation+0.763
luxury
Token luxury
Feature activation+0.559
during
Token during
Feature activation+0.665
that
Token that
Feature activation+0.174
Ċ
TokenĊ
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
its
Tokenits
Feature activation+0.000
Falling
Token Falling
Feature activation+1.424
Ċ
TokenĊ
Feature activation+1.863
Ċ
TokenĊ
Feature activation+1.335
Netflix
TokenNetflix
Feature activation+0.000
posted
Token posted
Feature activation+0.003
a
Token a
Feature activation+0.069
91
Token 91
Feature activation+0.266
%
Token%
Feature activation+0.000
his
Token his
Feature activation+0.000
side
Token side
Feature activation+0.000
gig
Token gig
Feature activation+0.000
was
Token was
Feature activation+0.080
lucrative
Token lucrative
Feature activation+0.079
,
Token,
Feature activation+1.319
only
Token only
Feature activation+0.827
to
Token to
Feature activation+0.916
realize
Token realize
Feature activation+0.705
he
Token he
Feature activation+0.516
was
Token was
Feature activation+0.148
high
Token high
Feature activation+0.000
price
Token price
Feature activation+0.000
of
Token of
Feature activation+0.505
the
Token the
Feature activation+0.177
drink
Token drink
Feature activation+0.000
.
Token.
Feature activation+1.231
The
Token The
Feature activation+0.633
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
trial
Token trial
Feature activation+0.000
s
Tokens
Feature activation+0.000
super
Token super
Feature activation+0.000
du
Token du
Feature activation+0.000
per
Tokenper
Feature activation+0.000
cheap
Token cheap
Feature activation+0.151
.
Token .
Feature activation+1.218
Literally
Token Literally
Feature activation+0.235
,
Token,
Feature activation+0.165
penn
Token penn
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
per
Token per
Feature activation+0.243
lifestyle
Token lifestyle
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
not
Token not
Feature activation+0.000
money
Token money
Feature activation+0.000
reasons
Token reasons
Feature activation+1.215
.
Token.
Feature activation+0.113
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
great
Token great
Feature activation+0.000
a
Token a
Feature activation+0.000
sum
Token sum
Feature activation+0.000
of
Token of
Feature activation+0.058
money
Token money
Feature activation+0.279
which
Token which
Feature activation+0.413
he
Token he
Feature activation+1.190
claimed
Token claimed
Feature activation+1.041
the
Token the
Feature activation+0.485
King
Token King
Feature activation+0.311
had
Token had
Feature activation+0.393
once
Token once
Feature activation+0.043
would
Token would
Feature activation+0.000
come
Token come
Feature activation+0.000
with
Token with
Feature activation+0.000
costs
Token costs
Feature activation+0.000
as
Token as
Feature activation+0.901
well
Token well
Feature activation+1.170
as
Token as
Feature activation+0.318
rewards
Token rewards
Feature activation+0.227
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
paid
Token paid
Feature activation+0.000
for
Token for
Feature activation+0.000
somehow
Token somehow
Feature activation+0.509
.
Token.
Feature activation+1.155
By
Token By
Feature activation+0.460
gaining
Token gaining
Feature activation+0.000
visibility
Token visibility
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 2.270

company
Token company
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Prof
TokenProf
Feature activation+0.005
Top resid features:
its
Tokenits
Feature activation+2.199
Top resid features:
Falling
Token Falling
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Netflix
TokenNetflix
Feature activation+0.000
Top resid features:
posted
Token posted
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
This
Token This
Feature activation+0.004
Top resid features:
epidemic
Token epidemic
Feature activation-0.010
Top resid features:
also
Token also
Feature activation-0.033
Top resid features:
has
Token has
Feature activation+0.003
Top resid features:
financial
Token financial
Feature activation+2.270
Top resid features:
ramifications
Token ramifications
Feature activation+0.061
Top resid features:
for
Token for
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
institutions
Token institutions
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.004
Top resid features:
check
Token check
Feature activation-0.000
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
Gym
Token Gym
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Prices
Token Prices
Feature activation+1.943
Top resid features:
vary
Token vary
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
locations
Token locations
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
London
Token London
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
This
Token This
Feature activation+0.007
Top resid features:
epidemic
Token epidemic
Feature activation-0.041
Top resid features:
also
Token also
Feature activation-0.053
Top resid features:
has
Token has
Feature activation+0.008
Top resid features:
financial
Token financial
Feature activation+1.948
Top resid features:
ramifications
Token ramifications
Feature activation+0.035
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
institutions
Token institutions
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Prof
TokenProf
Feature activation+0.001
Top resid features:
its
Tokenits
Feature activation+1.779
Top resid features:
Falling
Token Falling
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Netflix
TokenNetflix
Feature activation+0.000
Top resid features:
posted
Token posted
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Such
TokenSuch
Feature activation+0.049
Top resid features:
people
Token people
Feature activation-0.048
Top resid features:
are
Token are
Feature activation-0.020
Top resid features:
very
Token very
Feature activation-0.019
Top resid features:
expensive
Token expensive
Feature activation+1.516
Top resid features:
for
Token for
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
state
Token state
Feature activation+0.330
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Homeless
Token Homeless
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Scorpion
Token Scorpion
Feature activation-0.017
Top resid features:
Pistol
Token Pistol
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
price
Token price
Feature activation+1.175
Top resid features:
tag
Token tag
Feature activation+0.656
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
At
Token At
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
play
Tokenplay
Feature activation+0.001
Top resid features:
mobile
Token mobile
Feature activation+0.065
Top resid features:
game
Token game
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
pay
Token pay
Feature activation+0.640
Top resid features:
-
Token-
Feature activation+0.206
Top resid features:
to
Tokento
Feature activation+0.389
Top resid features:
-
Token-
Feature activation+0.203
Top resid features:
play
Tokenplay
Feature activation+0.134
Top resid features:
songs
Token songs
Feature activation+0.000
Top resid features:
forms
Token forms
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
One
Token One
Feature activation-0.012
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
simply
Token simply
Feature activation+0.047
Top resid features:
financial
Token financial
Feature activation+1.688
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Until
Token Until
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
French
Token French
Feature activation+0.000
Top resid features:
Revolution
Token Revolution
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
sometimes
Token sometimes
Feature activation+0.022
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
costs
Token costs
Feature activation+0.210
Top resid features:
taxpayers
Token taxpayers
Feature activation+0.875
Top resid features:
money
Token money
Feature activation+0.577
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Curious
Token Curious
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
great
Token great
Feature activation+0.001
Top resid features:
chance
Token chance
Feature activation+0.063
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
making
Token making
Feature activation+0.070
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
profit
Token profit
Feature activation+1.568
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
Premier
Token Premier
Feature activation+0.000
Top resid features:
League
Token League
Feature activation+0.000
Top resid features:
betting
Token betting
Feature activation+0.000
Top resid features:
normally
Token normally
Feature activation+0.003
Top resid features:
come
Token come
Feature activation+0.038
Top resid features:
with
Token with
Feature activation+0.046
Top resid features:
a
Token a
Feature activation+0.032
Top resid features:
monthly
Token monthly
Feature activation+0.339
Top resid features:
fee
Token fee
Feature activation+1.143
Top resid features:
which
Token which
Feature activation+0.075
Top resid features:
makes
Token makes
Feature activation-0.015
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
luxury
Token luxury
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Prof
TokenProf
Feature activation+0.007
Top resid features:
its
Tokenits
Feature activation+1.613
Top resid features:
Falling
Token Falling
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Netflix
TokenNetflix
Feature activation+0.000
Top resid features:
posted
Token posted
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.018
Top resid features:
his
Token his
Feature activation+0.017
Top resid features:
side
Token side
Feature activation-0.010
Top resid features:
gig
Token gig
Feature activation+0.082
Top resid features:
was
Token was
Feature activation+0.041
Top resid features:
lucrative
Token lucrative
Feature activation+1.345
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
realize
Token realize
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
main
Token main
Feature activation-0.010
Top resid features:
drawback
Token drawback
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
high
Token high
Feature activation+0.032
Top resid features:
price
Token price
Feature activation+1.359
Top resid features:
of
Token of
Feature activation+0.232
Top resid features:
the
Token the
Feature activation+0.082
Top resid features:
drink
Token drink
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
super
Token super
Feature activation-0.002
Top resid features:
du
Token du
Feature activation+0.004
Top resid features:
per
Tokenper
Feature activation-0.003
Top resid features:
cheap
Token cheap
Feature activation+1.715
Top resid features:
.
Token .
Feature activation-0.021
Top resid features:
Literally
Token Literally
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
penn
Token penn
Feature activation+0.000
Top resid features:
ies
Tokenies
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.037
Top resid features:
lifestyle
Token lifestyle
Feature activation+0.046
Top resid features:
reasons
Token reasons
Feature activation-0.045
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.065
Top resid features:
not
Token not
Feature activation+0.063
Top resid features:
money
Token money
Feature activation+1.464
Top resid features:
reasons
Token reasons
Feature activation-0.045
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.025
Top resid features:
him
Token him
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.065
Top resid features:
sum
Token sum
Feature activation+0.491
Top resid features:
of
Token of
Feature activation+0.044
Top resid features:
money
Token money
Feature activation+0.630
Top resid features:
which
Token which
Feature activation+0.200
Top resid features:
he
Token he
Feature activation+0.005
Top resid features:
claimed
Token claimed
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
proposing
Token proposing
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
come
Token come
Feature activation+0.017
Top resid features:
with
Token with
Feature activation+0.024
Top resid features:
costs
Token costs
Feature activation+1.526
Top resid features:
as
Token as
Feature activation+0.106
Top resid features:
well
Token well
Feature activation-0.003
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
rewards
Token rewards
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
services
Token services
Feature activation+0.028
Top resid features:
ultimately
Token ultimately
Feature activation+0.031
Top resid features:
have
Token have
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.021
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
paid
Token paid
Feature activation+0.976
Top resid features:
for
Token for
Feature activation+0.326
Top resid features:
somehow
Token somehow
Feature activation+0.045
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
By
Token By
Feature activation+0.000
Top resid features:
gaining
Token gaining
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.05

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.08

Head 6: 0.06

Head 7: 0.42

Head 8: 0.09

Head 9: 0.01

Head 10: 0.03

Head 11: 0.07

Positive logits

PayPal3.41

payout3.32

monet3.30

bribe3.28

payments3.22

reimburse3.22

VAT3.21

bribes3.19

extortion3.18

repayment3.18

lucrative3.14

payable3.12

payment3.11

cash3.05

subsid3.05

fees2.97

casinos2.97

invoice2.92

earnings2.92

payday2.91

Negative logits

inct-2.21

peat-2.08

Lens-2.01

Winged-2.01

OLOGY-1.98

obl-1.98

Scientists-1.95

hene-1.95

osis-1.94

RNA-1.92

Sequ-1.89

ocamp-1.87

QUI-1.85

icol-1.84

Syn-1.84

enne-1.84

Peaks-1.83

ensis-1.81

Map-1.80

Function-1.79

INTERVAL 1.677 - 1.863
CONTAINS 0.000%

epidemic
Token epidemic
Feature activation+0.000
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.000
financial
Token financial
Feature activation+0.000
ramifications
Token ramifications
Feature activation+1.485
for
Token for
Feature activation+1.821
the
Token the
Feature activation+1.089
institutions
Token institutions
Feature activation+0.000
that
Token that
Feature activation+0.000
must
Token must
Feature activation+0.017
treat
Token treat
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
its
Tokenits
Feature activation+0.000
Falling
Token Falling
Feature activation+1.424
Ċ
TokenĊ
Feature activation+1.863
Ċ
TokenĊ
Feature activation+1.335
Netflix
TokenNetflix
Feature activation+0.000
posted
Token posted
Feature activation+0.003
a
Token a
Feature activation+0.069
91
Token 91
Feature activation+0.266

INTERVAL 1.491 - 1.677
CONTAINS 0.000%

The
Token The
Feature activation+0.000
Gym
Token Gym
Feature activation+0.000
.
Token.
Feature activation+0.000
Prices
Token Prices
Feature activation+0.000
vary
Token vary
Feature activation+0.386
in
Token in
Feature activation+1.570
locations
Token locations
Feature activation+0.488
around
Token around
Feature activation+0.417
London
Token London
Feature activation+0.000
but
Token but
Feature activation+0.218
it
Token it
Feature activation+0.107

INTERVAL 1.304 - 1.491
CONTAINS 0.001%

Pistol
Token Pistol
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
tag
Token tag
Feature activation+0.280
.
Token.
Feature activation+1.397
At
Token At
Feature activation+0.545
just
Token just
Feature activation+0.053
$
Token $
Feature activation+0.000
8
Token8
Feature activation+0.000
49
Token49
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
monthly
Token monthly
Feature activation+0.000
fee
Token fee
Feature activation+0.641
which
Token which
Feature activation+0.988
makes
Token makes
Feature activation+1.339
them
Token them
Feature activation+1.022
a
Token a
Feature activation+0.763
luxury
Token luxury
Feature activation+0.559
during
Token during
Feature activation+0.665
that
Token that
Feature activation+0.174
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
was
Token was
Feature activation+0.000
simply
Token simply
Feature activation+0.000
financial
Token financial
Feature activation+0.000
.
Token.
Feature activation+1.374
Until
Token Until
Feature activation+0.933
the
Token the
Feature activation+0.181
French
Token French
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
,
Token,
Feature activation+0.073
very
Token very
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
for
Token for
Feature activation+0.161
the
Token the
Feature activation+0.496
state
Token state
Feature activation+0.000
.
Token.
Feature activation+1.412
Homeless
Token Homeless
Feature activation+0.000
shelters
Token shelters
Feature activation+0.000
cost
Token cost
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.338
chance
Token chance
Feature activation+0.000
of
Token of
Feature activation+0.000
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
profit
Token profit
Feature activation+0.072
with
Token with
Feature activation+1.339
your
Token your
Feature activation+0.808
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
betting
Token betting
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 1.118 - 1.304
CONTAINS 0.001%

from
Token from
Feature activation+0.685
The
Token The
Feature activation+0.000
Nun
Token Nun
Feature activation+0.000
's
Token's
Feature activation+0.000
Story
Token Story
Feature activation+0.175
are
Token are
Feature activation+1.140
langu
Token langu
Feature activation+0.430
ishing
Tokenishing
Feature activation+0.565
un
Token un
Feature activation+0.287
claimed
Tokenclaimed
Feature activation+0.000
because
Token because
Feature activation+0.169
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.287
but
Token but
Feature activation+1.136
my
Token my
Feature activation+1.027
mum
Token mum
Feature activation+0.103
was
Token was
Feature activation+0.179
termin
Token termin
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
kids
Token kids
Feature activation+0.000
were
Token were
Feature activation+0.000
paid
Token paid
Feature activation+0.000
or
Token or
Feature activation+1.130
received
Token received
Feature activation+0.391
âĢ
Token âĢ
Feature activation+0.009
ľ
Tokenľ
Feature activation+0.000
other
Tokenother
Feature activation+0.214
consideration
Token consideration
Feature activation+0.000
a
Token a
Feature activation+0.000
sum
Token sum
Feature activation+0.000
of
Token of
Feature activation+0.058
money
Token money
Feature activation+0.279
which
Token which
Feature activation+0.413
he
Token he
Feature activation+1.190
claimed
Token claimed
Feature activation+1.041
the
Token the
Feature activation+0.485
King
Token King
Feature activation+0.311
had
Token had
Feature activation+0.393
once
Token once
Feature activation+0.043
high
Token high
Feature activation+0.000
price
Token price
Feature activation+0.000
of
Token of
Feature activation+0.505
the
Token the
Feature activation+0.177
drink
Token drink
Feature activation+0.000
.
Token.
Feature activation+1.231
The
Token The
Feature activation+0.633
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
trial
Token trial
Feature activation+0.000

INTERVAL 0.932 - 1.118
CONTAINS 0.003%

rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
ad
Token ad
Feature activation+0.000
revenue
Token revenue
Feature activation+0.217
to
Token to
Feature activation+0.608
keep
Token keep
Feature activation+1.034
the
Token the
Feature activation+0.469
lights
Token lights
Feature activation+0.000
on
Token on
Feature activation+0.079
.
Token.
Feature activation+0.668
Ċ
TokenĊ
Feature activation+0.475
also
Token also
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
his
Token his
Feature activation+0.000
new
Token new
Feature activation+0.000
tax
Token tax
Feature activation+0.000
proposal
Token proposal
Feature activation+1.115
,
Token,
Feature activation+0.006
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
called
Token called
Feature activation+0.000
a
Token a
Feature activation+0.000
100
Token100
Feature activation+0.041
,
Token,
Feature activation+0.091
000
Token000
Feature activation+0.251
a
Token a
Feature activation+0.646
month
Token month
Feature activation+1.019
âĢĶ
Token âĢĶ
Feature activation+1.030
easy
Token easy
Feature activation+0.879
."
Token."
Feature activation+0.605
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
were
Token were
Feature activation+0.630
often
Token often
Feature activation+0.825
quietly
Token quietly
Feature activation+0.961
paid
Token paid
Feature activation+0.574
,
Token,
Feature activation+0.820
with
Token with
Feature activation+1.034
the
Token the
Feature activation+0.768
consumer
Token consumer
Feature activation+0.344
none
Token none
Feature activation+0.744
the
Token the
Feature activation+0.000
wiser
Token wiser
Feature activation+0.194
sheet
Token sheet
Feature activation+0.541
that
Token that
Feature activation+0.397
has
Token has
Feature activation+0.365
to
Token to
Feature activation+0.061
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.980
how
Token how
Feature activation+0.740
much
Token much
Feature activation+0.000
money
Token money
Feature activation+0.029
is
Token is
Feature activation+0.026
in
Token in
Feature activation+0.057

INTERVAL 0.745 - 0.932
CONTAINS 0.011%

in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
and
Token and
Feature activation+0.000
cost
Token cost
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.655
between
Token between
Feature activation+0.768
$
Token $
Feature activation+0.000
80
Token80
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
to
Token to
Feature activation+0.000
heritage
Token heritage
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
money
Token money
Feature activation+0.000
transc
Token transc
Feature activation+0.000
ends
Tokenends
Feature activation+0.754
politics
Token politics
Feature activation+0.000
.
Token.
Feature activation+0.464
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
for
Token for
Feature activation+0.000
disrupting
Token disrupting
Feature activation+0.000
deliveries
Token deliveries
Feature activation+0.000
over
Token over
Feature activation+0.000
payment
Token payment
Feature activation+0.000
issues
Token issues
Feature activation+0.820
since
Token since
Feature activation+0.000
August
Token August
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
millions
Token millions
Feature activation+0.000
spent
Token spent
Feature activation+0.000
on
Token on
Feature activation+0.000
overtime
Token overtime
Feature activation+0.127
pay
Token pay
Feature activation+0.783
.
Token.
Feature activation+0.021
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
expected
Token expected
Feature activation+0.000
that
Token that
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.074
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
,
Token,
Feature activation+0.376
making
Token making
Feature activation+0.776
the
Token the
Feature activation+0.247
technology
Token technology
Feature activation+0.000
user
Token user
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.559 - 0.745
CONTAINS 0.029%

well
Token well
Feature activation+0.000
?
Token?
Feature activation+0.000
With
Token With
Feature activation+0.000
housing
Token housing
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
being
Token being
Feature activation+0.624
cut
Token cut
Feature activation+0.478
as
Token as
Feature activation+0.314
well
Token well
Feature activation+0.304
what
Token what
Feature activation+0.494
are
Token are
Feature activation+0.282
]
Token]
Feature activation+0.000
While
Token While
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
was
Token was
Feature activation+0.084
clearly
Token clearly
Feature activation+0.631
advertised
Token advertised
Feature activation+0.450
as
Token as
Feature activation+0.081
$
Token $
Feature activation+0.000
799
Token799
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
is
Token is
Feature activation+0.554
outrageous
Token outrageous
Feature activation+0.538
.
Token.
Feature activation+0.725
Ċ
TokenĊ
Feature activation+0.131
Ċ
TokenĊ
Feature activation+0.026
Cruz
TokenCruz
Feature activation+0.000
would
Token would
Feature activation+0.000
stand
Token stand
Feature activation+0.000
regions
Token regions
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
financing
Token financing
Feature activation+0.000
levels
Token levels
Feature activation+0.372
are
Token are
Feature activation+0.569
far
Token far
Feature activation+0.652
below
Token below
Feature activation+0.790
those
Token those
Feature activation+0.065
even
Token even
Feature activation+0.000
in
Token in
Feature activation+0.029
their
Token their
Feature activation+0.000
wages
Token wages
Feature activation+0.000
.
Token.
Feature activation+0.712
Some
Token Some
Feature activation+0.480
said
Token said
Feature activation+0.613
they
Token they
Feature activation+0.577
had
Token had
Feature activation+0.555
not
Token not
Feature activation+0.580
been
Token been
Feature activation+0.534
paid
Token paid
Feature activation+0.098
in
Token in
Feature activation+0.318

INTERVAL 0.373 - 0.559
CONTAINS 0.075%

thanks
Token thanks
Feature activation+0.051
to
Token to
Feature activation+0.405
government
Token government
Feature activation+0.109
subsidized
Token subsidized
Feature activation+0.122
building
Token building
Feature activation+0.000
initiatives
Token initiatives
Feature activation+0.412
as
Token as
Feature activation+0.258
well
Token well
Feature activation+0.310
as
Token as
Feature activation+0.115
the
Token the
Feature activation+0.106
demand
Token demand
Feature activation+0.000
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
taxes
Token taxes
Feature activation+0.011
to
Token to
Feature activation+0.512
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.003
,
Token,
Feature activation+0.050
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
one
Token one
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
salary
Token salary
Feature activation+0.001
then
Token then
Feature activation+0.513
would
Token would
Feature activation+0.697
not
Token not
Feature activation+0.603
be
Token be
Feature activation+0.814
enough
Token enough
Feature activation+0.501
to
Token to
Feature activation+0.805
gou
Token gou
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
fees
Token fees
Feature activation+0.000
and
Token and
Feature activation+0.392
their
Token their
Feature activation+0.533
constant
Token constant
Feature activation+0.377
stream
Token stream
Feature activation+0.000
of
Token of
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
and
Token and
Feature activation+0.000
corruption
Token corruption
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
share
Token share
Feature activation+0.471
ratio
Token ratio
Feature activation+0.355
)
Token)
Feature activation+0.238
and
Token and
Feature activation+0.000
Fish
Token Fish
Feature activation+0.039
lamented
Token lamented
Feature activation+0.100

INTERVAL 0.186 - 0.373
CONTAINS 0.214%

:
Token:
Feature activation+0.339
FREE
Token FREE
Feature activation+0.077
!
Token!
Feature activation+0.111
Level
Token Level
Feature activation+0.043
:
Token:
Feature activation+0.484
all
Token all
Feature activation+0.297
.
Token.
Feature activation+0.025
Ċ
TokenĊ
Feature activation+0.152
Ċ
TokenĊ
Feature activation+0.029
Love
TokenLove
Feature activation+0.000
to
Token to
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.043
,
Token,
Feature activation+0.296
but
Token but
Feature activation+0.294
have
Token have
Feature activation+0.280
been
Token been
Feature activation+0.200
far
Token far
Feature activation+0.000
less
Token less
Feature activation+0.003
forthcoming
Token forthcoming
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
sales
Token sales
Feature activation+0.000
are
Token are
Feature activation+0.111
completely
Token completely
Feature activation+0.111
unregulated
Token unregulated
Feature activation+0.000
,
Token,
Feature activation+0.274
meaning
Token meaning
Feature activation+0.250
there
Token there
Feature activation+0.204
are
Token are
Feature activation+0.094
no
Token no
Feature activation+0.054
rules
Token rules
Feature activation+0.000
on
Token on
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
purchases
Token purchases
Feature activation+0.000
with
Token with
Feature activation+0.300
Bitcoin
Token Bitcoin
Feature activation+0.266
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bitcoin
TokenBitcoin
Feature activation+0.000
is
Token is
Feature activation+0.000
customers
Token customers
Feature activation+0.000
of
Token of
Feature activation+0.000
NV
Token NV
Feature activation+0.000
Energy
Token Energy
Feature activation+0.000
.
Token.
Feature activation+0.184
Ċ
TokenĊ
Feature activation+0.206
Ċ
TokenĊ
Feature activation+0.092
B
TokenB
Feature activation+0.000
irt
Tokenirt
Feature activation+0.000
amassed
Token amassed
Feature activation+0.000
50
Token 50
Feature activation+0.000

INTERVAL 0.000 - 0.186
CONTAINS 99.665%

to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
their
Token their
Feature activation+0.000
choice
Token choice
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
after
Token after
Feature activation+0.000
feedback
Token feedback
Feature activation+0.000
on
Token on
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bur
TokenBur
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
neither
Token neither
Feature activation+0.000
a
Token a
Feature activation+0.000
Jessica
Token Jessica
Feature activation+0.000
of
Token of
Feature activation+0.000
Once
Token Once
Feature activation+0.000
Upon
Token Upon
Feature activation+0.000
a
Token a
Feature activation+0.000
Polish
Token Polish
Feature activation+0.000
picked
Token picked
Feature activation+0.000
geometric
Token geometric
Feature activation+0.000
for
Token for
Feature activation+0.000
our
Token our
Feature activation+0.000
art
Token art
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
er
Token er
Feature activation+0.000
st
Tokenst
Feature activation+0.000
while
Tokenwhile
Feature activation+0.000
officials
Token officials
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
A
Token A
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
resource
Token resource
Feature activation+0.000
protection
Token protection
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sadly
TokenSadly
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H6.7: (feature 15065)

TOP ACTIVATIONS
MAX = 1.527

ages
Tokenages
Feature activation+0.000
in
Token in
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
timber
Token timber
Feature activation+0.200
,
Token,
Feature activation+1.527
and
Token and
Feature activation+0.505
wealthy
Token wealthy
Feature activation+0.293
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
the
Token the
Feature activation+0.182
natural
Token natural
Feature activation+0.018
buffers
Token buffers
Feature activation+0.217
to
Token to
Feature activation+0.457
floods
Token floods
Feature activation+0.254
.
Token.
Feature activation+1.433
Sh
Token Sh
Feature activation+0.315
r
Tokenr
Feature activation+0.000
inking
Tokeninking
Feature activation+0.219
the
Token the
Feature activation+0.257
area
Token area
Feature activation+0.517
that
Token that
Feature activation+0.000
destroys
Token destroys
Feature activation+0.000
its
Token its
Feature activation+0.000
soils
Token soils
Feature activation+0.128
,
Token,
Feature activation+0.993
destroys
Token destroys
Feature activation+1.405
itself
Token itself
Feature activation+0.851
,"
Token,"
Feature activation+0.759
historian
Token historian
Feature activation+0.000
Jerry
Token Jerry
Feature activation+0.000
Apps
Token Apps
Feature activation+0.000
roadway
Token roadway
Feature activation+0.000
space
Token space
Feature activation+0.026
to
Token to
Feature activation+0.028
minimize
Token minimize
Feature activation+0.106
tree
Token tree
Feature activation+0.000
removal
Token removal
Feature activation+1.397
.
Token.
Feature activation+0.506
It
Token It
Feature activation+0.161
was
Token was
Feature activation+0.019
built
Token built
Feature activation+0.136
the
Token the
Feature activation+0.151
food
Token food
Feature activation+0.278
security
Token security
Feature activation+0.617
in
Token in
Feature activation+0.807
Africa
Token Africa
Feature activation+0.494
by
Token by
Feature activation+1.184
promoting
Token promoting
Feature activation+1.374
the
Token the
Feature activation+0.628
adoption
Token adoption
Feature activation+0.275
of
Token of
Feature activation+0.811
GM
Token GM
Feature activation+0.000
,
Token,
Feature activation+0.105
up
Token up
Feature activation+0.000
working
Token working
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
soil
Token soil
Feature activation+0.000
scientist
Token scientist
Feature activation+1.303
for
Token for
Feature activation+0.984
the
Token the
Feature activation+0.766
state
Token state
Feature activation+0.386
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
neighbours
Token neighbours
Feature activation+0.000
are
Token are
Feature activation+0.000
largely
Token largely
Feature activation+0.037
agricultural
Token agricultural
Feature activation+0.000
;
Token;
Feature activation+1.196
there
Token there
Feature activation+1.279
is
Token is
Feature activation+0.743
a
Token a
Feature activation+0.439
furniture
Token furniture
Feature activation+0.000
maker
Token maker
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
fertil
Token fertil
Feature activation+0.000
ize
Tokenize
Feature activation+0.231
our
Token our
Feature activation+0.501
fields
Token fields
Feature activation+0.664
so
Token so
Feature activation+1.272
we
Token we
Feature activation+1.257
can
Token can
Feature activation+1.082
grow
Token grow
Feature activation+0.218
the
Token the
Feature activation+0.520
crops
Token crops
Feature activation+0.314
fertil
Token fertil
Feature activation+0.000
ize
Tokenize
Feature activation+0.231
our
Token our
Feature activation+0.501
fields
Token fields
Feature activation+0.664
so
Token so
Feature activation+1.272
we
Token we
Feature activation+1.257
can
Token can
Feature activation+1.082
grow
Token grow
Feature activation+0.218
the
Token the
Feature activation+0.520
crops
Token crops
Feature activation+0.314
that
Token that
Feature activation+0.214
used
Token used
Feature activation+0.097
for
Token for
Feature activation+0.409
grazing
Token grazing
Feature activation+0.334
and
Token and
Feature activation+1.107
cultivation
Token cultivation
Feature activation+0.662
during
Token during
Feature activation+1.202
the
Token the
Feature activation+1.086
dry
Token dry
Feature activation+0.169
season
Token season
Feature activation+0.611
and
Token and
Feature activation+1.023
in
Token in
Feature activation+1.106
My
Token My
Feature activation+0.000
neighbours
Token neighbours
Feature activation+0.000
are
Token are
Feature activation+0.000
largely
Token largely
Feature activation+0.037
agricultural
Token agricultural
Feature activation+0.000
;
Token;
Feature activation+1.196
there
Token there
Feature activation+1.279
is
Token is
Feature activation+0.743
a
Token a
Feature activation+0.439
furniture
Token furniture
Feature activation+0.000
maker
Token maker
Feature activation+0.000
ont
Tokenont
Feature activation+0.000
amin
Tokenamin
Feature activation+0.000
ating
Tokenating
Feature activation+0.167
the
Token the
Feature activation+0.081
soil
Token soil
Feature activation+0.447
,
Token,
Feature activation+1.190
the
Token the
Feature activation+0.660
organizers
Token organizers
Feature activation+0.395
hope
Token hope
Feature activation+0.320
that
Token that
Feature activation+0.468
the
Token the
Feature activation+0.388
providing
Token providing
Feature activation+0.682
food
Token food
Feature activation+0.278
security
Token security
Feature activation+0.617
in
Token in
Feature activation+0.807
Africa
Token Africa
Feature activation+0.494
by
Token by
Feature activation+1.184
promoting
Token promoting
Feature activation+1.374
the
Token the
Feature activation+0.628
adoption
Token adoption
Feature activation+0.275
of
Token of
Feature activation+0.811
GM
Token GM
Feature activation+0.000
forests
Token forests
Feature activation+0.184
provided
Token provided
Feature activation+0.419
a
Token a
Feature activation+0.620
natural
Token natural
Feature activation+0.335
defense
Token defense
Feature activation+0.460
.
Token.
Feature activation+1.164
European
Token European
Feature activation+0.570
antiquity
Token antiquity
Feature activation+0.000
was
Token was
Feature activation+0.053
defined
Token defined
Feature activation+0.103
by
Token by
Feature activation+0.192
equivalent
Token equivalent
Feature activation+0.000
of
Token of
Feature activation+0.000
decades
Token decades
Feature activation+0.000
of
Token of
Feature activation+0.000
planting
Token planting
Feature activation+0.000
and
Token and
Feature activation+1.162
harvesting
Token harvesting
Feature activation+0.930
of
Token of
Feature activation+0.790
energy
Token energy
Feature activation+0.335
crops
Token crops
Feature activation+0.394
over
Token over
Feature activation+0.931
ying
Tokenying
Feature activation+0.000
many
Token many
Feature activation+0.000
wet
Token wet
Feature activation+0.000
land
Tokenland
Feature activation+0.201
sites
Token sites
Feature activation+1.086
across
Token across
Feature activation+1.142
the
Token the
Feature activation+0.526
globe
Token globe
Feature activation+0.873
as
Token as
Feature activation+0.703
T
Token T
Feature activation+0.287
ure
Tokenure
Feature activation+0.000
his
Token his
Feature activation+0.000
soil
Token soil
Feature activation+0.005
so
Token so
Feature activation+0.766
he
Token he
Feature activation+0.868
could
Token could
Feature activation+1.121
build
Token build
Feature activation+1.142
a
Token a
Feature activation+0.732
house
Token house
Feature activation+0.060
.
Token.
Feature activation+0.344
Ċ
TokenĊ
Feature activation+0.230
Ċ
TokenĊ
Feature activation+0.329
the
Token the
Feature activation+1.086
dry
Token dry
Feature activation+0.169
season
Token season
Feature activation+0.611
and
Token and
Feature activation+1.023
in
Token in
Feature activation+1.106
the
Token the
Feature activation+1.141
Nile
Token Nile
Feature activation+0.275
mars
Token mars
Feature activation+0.000
hes
Tokenhes
Feature activation+0.343
during
Token during
Feature activation+0.893
the
Token the
Feature activation+0.800
,
Token,
Feature activation+0.276
planted
Token planted
Feature activation+0.344
71
Token 71
Feature activation+0.783
million
Token million
Feature activation+0.578
trees
Token trees
Feature activation+0.452
,
Token,
Feature activation+1.136
revived
Token revived
Feature activation+0.845
several
Token several
Feature activation+0.306
ponds
Token ponds
Feature activation+0.672
is
Token is
Feature activation+0.564
being
Token being
Feature activation+0.463
hes
Tokenhes
Feature activation+0.343
during
Token during
Feature activation+0.893
the
Token the
Feature activation+0.800
wet
Token wet
Feature activation+0.040
season
Token season
Feature activation+0.352
.
Token.
Feature activation+1.128
There
Token There
Feature activation+0.852
are
Token are
Feature activation+0.761
conflicting
Token conflicting
Feature activation+0.227
reports
Token reports
Feature activation+0.163
over
Token over
Feature activation+0.060

Top DFA by src position
MAX = 1.782

w
Tokenw
Feature activation+0.007
Top resid features:
ages
Tokenages
Feature activation-0.014
Top resid features:
in
Token in
Feature activation+0.048
Top resid features:
jobs
Token jobs
Feature activation-0.063
Top resid features:
cutting
Token cutting
Feature activation+0.201
Top resid features:
timber
Token timber
Feature activation+1.782
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
wealthy
Token wealthy
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
decades
Token decades
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
we
Token we
Feature activation-0.004
Top resid features:
filled
Token filled
Feature activation+0.024
Top resid features:
many
Token many
Feature activation+0.022
Top resid features:
wetlands
Token wetlands
Feature activation+1.049
Top resid features:
that
Token that
Feature activation+0.301
Top resid features:
are
Token are
Feature activation+0.085
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
natural
Token natural
Feature activation+0.055
Top resid features:
buffers
Token buffers
Feature activation+0.113
Top resid features:
a
Tokena
Feature activation-0.010
Top resid features:
nation
Token nation
Feature activation-0.031
Top resid features:
that
Token that
Feature activation-0.072
Top resid features:
destroys
Token destroys
Feature activation+0.012
Top resid features:
its
Token its
Feature activation+0.106
Top resid features:
soils
Token soils
Feature activation+1.635
Top resid features:
,
Token,
Feature activation+0.200
Top resid features:
destroys
Token destroys
Feature activation+0.013
Top resid features:
itself
Token itself
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
historian
Token historian
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation+0.003
Top resid features:
roadway
Token roadway
Feature activation+0.077
Top resid features:
space
Token space
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.044
Top resid features:
minimize
Token minimize
Feature activation+0.066
Top resid features:
tree
Token tree
Feature activation+1.470
Top resid features:
removal
Token removal
Feature activation+0.154
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
built
Token built
Feature activation+0.000
Top resid features:
sustainable
Token sustainable
Feature activation+0.062
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
small
Token small
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
scale
Tokenscale
Feature activation+0.049
Top resid features:
farmers
Token farmers
Feature activation+1.108
Top resid features:
that
Token that
Feature activation+0.096
Top resid features:
are
Token are
Feature activation+0.022
Top resid features:
providing
Token providing
Feature activation+0.032
Top resid features:
food
Token food
Feature activation+0.126
Top resid features:
security
Token security
Feature activation+0.047
Top resid features:
ended
Token ended
Feature activation+0.015
Top resid features:
up
Token up
Feature activation+0.030
Top resid features:
working
Token working
Feature activation+0.025
Top resid features:
as
Token as
Feature activation+0.067
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
soil
Token soil
Feature activation+1.486
Top resid features:
scientist
Token scientist
Feature activation+0.184
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
My
Token My
Feature activation+0.015
Top resid features:
neighbours
Token neighbours
Feature activation+0.094
Top resid features:
are
Token are
Feature activation+0.071
Top resid features:
largely
Token largely
Feature activation+0.078
Top resid features:
agricultural
Token agricultural
Feature activation+1.328
Top resid features:
;
Token;
Feature activation+0.154
Top resid features:
there
Token there
Feature activation+0.046
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
furniture
Token furniture
Feature activation+0.000
Top resid features:
able
Token able
Feature activation-0.016
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
fertil
Token fertil
Feature activation+0.272
Top resid features:
ize
Tokenize
Feature activation+0.311
Top resid features:
our
Token our
Feature activation+0.132
Top resid features:
fields
Token fields
Feature activation+1.171
Top resid features:
so
Token so
Feature activation+0.022
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
grow
Token grow
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
able
Token able
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
fertil
Token fertil
Feature activation+0.292
Top resid features:
ize
Tokenize
Feature activation+0.198
Top resid features:
our
Token our
Feature activation+0.074
Top resid features:
fields
Token fields
Feature activation+1.245
Top resid features:
so
Token so
Feature activation+0.030
Top resid features:
we
Token we
Feature activation-0.010
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
grow
Token grow
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
used
Token used
Feature activation+0.044
Top resid features:
for
Token for
Feature activation+0.096
Top resid features:
grazing
Token grazing
Feature activation+0.648
Top resid features:
and
Token and
Feature activation+0.089
Top resid features:
cultivation
Token cultivation
Feature activation+0.650
Top resid features:
during
Token during
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
dry
Token dry
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
My
Token My
Feature activation+0.017
Top resid features:
neighbours
Token neighbours
Feature activation+0.209
Top resid features:
are
Token are
Feature activation+0.039
Top resid features:
largely
Token largely
Feature activation+0.097
Top resid features:
agricultural
Token agricultural
Feature activation+1.240
Top resid features:
;
Token;
Feature activation+0.088
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
furniture
Token furniture
Feature activation+0.000
Top resid features:
dec
Token dec
Feature activation+0.057
Top resid features:
ont
Tokenont
Feature activation+0.031
Top resid features:
amin
Tokenamin
Feature activation+0.058
Top resid features:
ating
Tokenating
Feature activation+0.217
Top resid features:
the
Token the
Feature activation+0.068
Top resid features:
soil
Token soil
Feature activation+1.161
Top resid features:
,
Token,
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
organizers
Token organizers
Feature activation+0.000
Top resid features:
hope
Token hope
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
sustainable
Token sustainable
Feature activation+0.126
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
scale
Tokenscale
Feature activation+0.037
Top resid features:
farmers
Token farmers
Feature activation+0.687
Top resid features:
that
Token that
Feature activation+0.162
Top resid features:
are
Token are
Feature activation+0.061
Top resid features:
providing
Token providing
Feature activation+0.109
Top resid features:
food
Token food
Feature activation+0.220
Top resid features:
security
Token security
Feature activation+0.108
Top resid features:
productive
Token productive
Feature activation+0.249
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
even
Token even
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
forests
Token forests
Feature activation+0.595
Top resid features:
provided
Token provided
Feature activation+0.060
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
natural
Token natural
Feature activation+0.106
Top resid features:
defense
Token defense
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
equivalent
Token equivalent
Feature activation-0.009
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
decades
Token decades
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
planting
Token planting
Feature activation+1.610
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
harvesting
Token harvesting
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation+0.000
Top resid features:
crops
Token crops
Feature activation+0.000
Top resid features:
By
TokenBy
Feature activation+0.003
Top resid features:
surve
Token surve
Feature activation+0.044
Top resid features:
ying
Tokenying
Feature activation+0.063
Top resid features:
many
Token many
Feature activation+0.016
Top resid features:
wet
Token wet
Feature activation+0.144
Top resid features:
land
Tokenland
Feature activation+0.708
Top resid features:
sites
Token sites
Feature activation+0.648
Top resid features:
across
Token across
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
globe
Token globe
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Robert
Token Robert
Feature activation+0.014
Top resid features:
Warren
Token Warren
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
evaluate
Token evaluate
Feature activation-0.005
Top resid features:
his
Token his
Feature activation+0.014
Top resid features:
soil
Token soil
Feature activation+1.420
Top resid features:
so
Token so
Feature activation+0.025
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
could
Token could
Feature activation+0.004
Top resid features:
build
Token build
Feature activation+0.055
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
cultivation
Token cultivation
Feature activation+0.293
Top resid features:
during
Token during
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
dry
Token dry
Feature activation+0.239
Top resid features:
season
Token season
Feature activation+0.543
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
in
Token in
Feature activation+0.070
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Nile
Token Nile
Feature activation+0.000
Top resid features:
mars
Token mars
Feature activation+0.000
Top resid features:
rivers
Token rivers
Feature activation+0.295
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
planted
Token planted
Feature activation+0.115
Top resid features:
71
Token 71
Feature activation+0.050
Top resid features:
million
Token million
Feature activation+0.059
Top resid features:
trees
Token trees
Feature activation+1.005
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
revived
Token revived
Feature activation+0.000
Top resid features:
several
Token several
Feature activation+0.000
Top resid features:
ponds
Token ponds
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
land
Token land
Feature activation+0.171
Top resid features:
is
Token is
Feature activation+0.052
Top resid features:
used
Token used
Feature activation+0.049
Top resid features:
for
Token for
Feature activation+0.038
Top resid features:
grazing
Token grazing
Feature activation+0.299
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
cultivation
Token cultivation
Feature activation+0.239
Top resid features:
during
Token during
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
dry
Token dry
Feature activation+0.069
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.04

Head 3: 0.06

Head 4: 0.09

Head 5: 0.09

Head 6: 0.06

Head 7: 0.41

Head 8: 0.07

Head 9: 0.01

Head 10: 0.02

Head 11: 0.04

Positive logits

vegetation3.14

irrig3.14

wetlands3.10

forests3.06

groundwater2.97

farmland2.95

gardens2.92

forestry2.88

soils2.87

wastewater2.85

soil2.85

plants2.82

grazing2.82

farmers2.78

farms2.78

greenhouse2.76

deforestation2.75

biomass2.73

irrigation2.73

excav2.72

Negative logits

obin-2.38

FBI-2.27

Schumer-2.12

ossip-2.06

Xbox-2.03

ebin-2.02

Comey-1.99

Spectre-1.95

ounge-1.92

Duff-1.90

Dumbledore-1.89

Marvel-1.87

umbledore-1.87

verbal-1.85

FBI-1.84

UFC-1.83

Abedin-1.81

inbox-1.79

Intelligence-1.77

advertising-1.77

INTERVAL 1.374 - 1.527
CONTAINS 0.001%

ages
Tokenages
Feature activation+0.000
in
Token in
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
timber
Token timber
Feature activation+0.200
,
Token,
Feature activation+1.527
and
Token and
Feature activation+0.505
wealthy
Token wealthy
Feature activation+0.293
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
the
Token the
Feature activation+0.182
natural
Token natural
Feature activation+0.018
buffers
Token buffers
Feature activation+0.217
to
Token to
Feature activation+0.457
floods
Token floods
Feature activation+0.254
.
Token.
Feature activation+1.433
Sh
Token Sh
Feature activation+0.315
r
Tokenr
Feature activation+0.000
inking
Tokeninking
Feature activation+0.219
the
Token the
Feature activation+0.257
area
Token area
Feature activation+0.517
that
Token that
Feature activation+0.000
destroys
Token destroys
Feature activation+0.000
its
Token its
Feature activation+0.000
soils
Token soils
Feature activation+0.128
,
Token,
Feature activation+0.993
destroys
Token destroys
Feature activation+1.405
itself
Token itself
Feature activation+0.851
,"
Token,"
Feature activation+0.759
historian
Token historian
Feature activation+0.000
Jerry
Token Jerry
Feature activation+0.000
Apps
Token Apps
Feature activation+0.000
food
Token food
Feature activation+0.278
security
Token security
Feature activation+0.617
in
Token in
Feature activation+0.807
Africa
Token Africa
Feature activation+0.494
by
Token by
Feature activation+1.184
promoting
Token promoting
Feature activation+1.374
the
Token the
Feature activation+0.628
adoption
Token adoption
Feature activation+0.275
of
Token of
Feature activation+0.811
GM
Token GM
Feature activation+0.000
,
Token,
Feature activation+0.105
roadway
Token roadway
Feature activation+0.000
space
Token space
Feature activation+0.026
to
Token to
Feature activation+0.028
minimize
Token minimize
Feature activation+0.106
tree
Token tree
Feature activation+0.000
removal
Token removal
Feature activation+1.397
.
Token.
Feature activation+0.506
It
Token It
Feature activation+0.161
was
Token was
Feature activation+0.019
built
Token built
Feature activation+0.136
the
Token the
Feature activation+0.151

INTERVAL 1.221 - 1.374
CONTAINS 0.000%

up
Token up
Feature activation+0.000
working
Token working
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
soil
Token soil
Feature activation+0.000
scientist
Token scientist
Feature activation+1.303
for
Token for
Feature activation+0.984
the
Token the
Feature activation+0.766
state
Token state
Feature activation+0.386
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
to
Token to
Feature activation+0.000
fertil
Token fertil
Feature activation+0.000
ize
Tokenize
Feature activation+0.231
our
Token our
Feature activation+0.501
fields
Token fields
Feature activation+0.664
so
Token so
Feature activation+1.272
we
Token we
Feature activation+1.257
can
Token can
Feature activation+1.082
grow
Token grow
Feature activation+0.218
the
Token the
Feature activation+0.520
crops
Token crops
Feature activation+0.314
fertil
Token fertil
Feature activation+0.000
ize
Tokenize
Feature activation+0.231
our
Token our
Feature activation+0.501
fields
Token fields
Feature activation+0.664
so
Token so
Feature activation+1.272
we
Token we
Feature activation+1.257
can
Token can
Feature activation+1.082
grow
Token grow
Feature activation+0.218
the
Token the
Feature activation+0.520
crops
Token crops
Feature activation+0.314
that
Token that
Feature activation+0.214
neighbours
Token neighbours
Feature activation+0.000
are
Token are
Feature activation+0.000
largely
Token largely
Feature activation+0.037
agricultural
Token agricultural
Feature activation+0.000
;
Token;
Feature activation+1.196
there
Token there
Feature activation+1.279
is
Token is
Feature activation+0.743
a
Token a
Feature activation+0.439
furniture
Token furniture
Feature activation+0.000
maker
Token maker
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.069 - 1.221
CONTAINS 0.002%

equivalent
Token equivalent
Feature activation+0.000
of
Token of
Feature activation+0.000
decades
Token decades
Feature activation+0.000
of
Token of
Feature activation+0.000
planting
Token planting
Feature activation+0.000
and
Token and
Feature activation+1.162
harvesting
Token harvesting
Feature activation+0.930
of
Token of
Feature activation+0.790
energy
Token energy
Feature activation+0.335
crops
Token crops
Feature activation+0.394
over
Token over
Feature activation+0.931
surve
Token surve
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
many
Token many
Feature activation+0.000
wet
Token wet
Feature activation+0.000
land
Tokenland
Feature activation+0.201
sites
Token sites
Feature activation+1.086
across
Token across
Feature activation+1.142
the
Token the
Feature activation+0.526
globe
Token globe
Feature activation+0.873
as
Token as
Feature activation+0.703
T
Token T
Feature activation+0.287
used
Token used
Feature activation+0.097
for
Token for
Feature activation+0.409
grazing
Token grazing
Feature activation+0.334
and
Token and
Feature activation+1.107
cultivation
Token cultivation
Feature activation+0.662
during
Token during
Feature activation+1.202
the
Token the
Feature activation+1.086
dry
Token dry
Feature activation+0.169
season
Token season
Feature activation+0.611
and
Token and
Feature activation+1.023
in
Token in
Feature activation+1.106
forests
Token forests
Feature activation+0.184
provided
Token provided
Feature activation+0.419
a
Token a
Feature activation+0.620
natural
Token natural
Feature activation+0.335
defense
Token defense
Feature activation+0.460
.
Token.
Feature activation+1.164
European
Token European
Feature activation+0.570
antiquity
Token antiquity
Feature activation+0.000
was
Token was
Feature activation+0.053
defined
Token defined
Feature activation+0.103
by
Token by
Feature activation+0.192
found
Token found
Feature activation+0.576
that
Token that
Feature activation+0.786
increasing
Token increasing
Feature activation+0.000
yields
Token yields
Feature activation+0.422
could
Token could
Feature activation+0.945
reduce
Token reduce
Feature activation+1.103
emissions
Token emissions
Feature activation+0.027
as
Token as
Feature activation+0.072
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
could
Token could
Feature activation+0.000

INTERVAL 0.916 - 1.069
CONTAINS 0.003%

and
Token and
Feature activation+0.520
found
Token found
Feature activation+0.576
that
Token that
Feature activation+0.786
increasing
Token increasing
Feature activation+0.000
yields
Token yields
Feature activation+0.422
could
Token could
Feature activation+0.945
reduce
Token reduce
Feature activation+1.103
emissions
Token emissions
Feature activation+0.027
as
Token as
Feature activation+0.072
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
trees
Token trees
Feature activation+0.002
grow
Token grow
Feature activation+0.637
from
Token from
Feature activation+0.370
seed
Token seed
Feature activation+0.255
,
Token,
Feature activation+0.990
to
Token to
Feature activation+0.454
sa
Token sa
Feature activation+0.010
pling
Tokenpling
Feature activation+0.018
,
Token,
Feature activation+0.698
to
Token to
Feature activation+0.778
and
Token and
Feature activation+0.198
headed
Token headed
Feature activation+0.072
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
bush
Token bush
Feature activation+0.119
to
Token to
Feature activation+1.003
lie
Token lie
Feature activation+0.161
in
Token in
Feature activation+0.006
wait
Token wait
Feature activation+0.004
.
Token.
Feature activation+0.210
Ċ
TokenĊ
Feature activation+0.000
s
Tokens
Feature activation+0.000
rich
Token rich
Feature activation+0.000
agricultural
Token agricultural
Feature activation+0.000
g
Token g
Feature activation+0.182
iv
Tokeniv
Feature activation+0.000
ings
Tokenings
Feature activation+1.041
,
Token,
Feature activation+0.618
specifically
Token specifically
Feature activation+0.412
to
Token to
Feature activation+0.632
the
Token the
Feature activation+0.501
pear
Token pear
Feature activation+0.000
growth
Tokengrowth
Feature activation+0.154
in
Token in
Feature activation+0.720
the
Token the
Feature activation+0.613
forest
Token forest
Feature activation+0.216
,
Token,
Feature activation+0.916
often
Token often
Feature activation+0.941
appearing
Token appearing
Feature activation+0.666
as
Token as
Feature activation+0.403
a
Token a
Feature activation+0.461
patch
Token patch
Feature activation+0.000
or
Token or
Feature activation+0.581

INTERVAL 0.763 - 0.916
CONTAINS 0.008%

that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
farm
Token farm
Feature activation+0.000
,
Token,
Feature activation+0.832
to
Token to
Feature activation+0.438
allow
Token allow
Feature activation+0.430
the
Token the
Feature activation+0.175
land
Token land
Feature activation+0.000
to
Token to
Feature activation+0.116
plant
Token plant
Feature activation+0.000
vegetables
Token vegetables
Feature activation+0.071
in
Token in
Feature activation+0.494
the
Token the
Feature activation+0.274
garden
Token garden
Feature activation+0.111
,
Token,
Feature activation+0.841
raise
Token raise
Feature activation+0.603
chickens
Token chickens
Feature activation+0.263
,
Token,
Feature activation+0.498
cook
Token cook
Feature activation+0.107
and
Token and
Feature activation+0.029
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
urged
Token urged
Feature activation+0.000
other
Token other
Feature activation+0.000
farmers
Token farmers
Feature activation+0.019
to
Token to
Feature activation+0.851
consider
Token consider
Feature activation+0.609
solar
Token solar
Feature activation+0.000
as
Token as
Feature activation+0.247
they
Token they
Feature activation+0.053
would
Token would
Feature activation+0.086
CLE
TokenCLE
Feature activation+0.000
AN
TokenAN
Feature activation+0.000
W
Token W
Feature activation+0.000
ATER
TokenATER
Feature activation+0.306
R
Token R
Feature activation+0.357
ULE
TokenULE
Feature activation+0.801
Ċ
TokenĊ
Feature activation+0.644
Ċ
TokenĊ
Feature activation+0.346
The
TokenThe
Feature activation+0.126
Environmental
Token Environmental
Feature activation+0.000
Protection
Token Protection
Feature activation+0.000
harvesting
Token harvesting
Feature activation+0.930
of
Token of
Feature activation+0.790
energy
Token energy
Feature activation+0.335
crops
Token crops
Feature activation+0.394
over
Token over
Feature activation+0.931
an
Token an
Feature activation+0.797
area
Token area
Feature activation+0.464
of
Token of
Feature activation+0.320
one
Token one
Feature activation+0.452
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.266

INTERVAL 0.611 - 0.763
CONTAINS 0.024%

hom
Token hom
Feature activation+0.000
estead
Tokenestead
Feature activation+0.000
ing
Tokening
Feature activation+0.346
has
Token has
Feature activation+0.811
been
Token been
Feature activation+0.909
used
Token used
Feature activation+0.631
by
Token by
Feature activation+0.592
governmental
Token governmental
Feature activation+0.082
entities
Token entities
Feature activation+0.000
(
Token (
Feature activation+0.000
eng
Tokeneng
Feature activation+0.000
you
Token you
Feature activation+0.222
reap
Token reap
Feature activation+0.051
what
Token what
Feature activation+0.195
you
Token you
Feature activation+0.220
sow
Token sow
Feature activation+0.210
in
Token in
Feature activation+0.671
life
Token life
Feature activation+0.701
.
Token.
Feature activation+0.583
Ċ
TokenĊ
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.277
Anyway
TokenAnyway
Feature activation+0.000
beauty
Token beauty
Feature activation+0.021
of
Token of
Feature activation+0.243
the
Token the
Feature activation+0.234
mountains
Token mountains
Feature activation+0.225
and
Token and
Feature activation+0.642
the
Token the
Feature activation+0.701
work
Token work
Feature activation+0.103
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.009
doing
Token doing
Feature activation+0.126
,
Token,
Feature activation+0.023
-
Token-
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
farmers
Token farmers
Feature activation+0.090
that
Token that
Feature activation+0.869
are
Token are
Feature activation+0.778
providing
Token providing
Feature activation+0.682
food
Token food
Feature activation+0.278
security
Token security
Feature activation+0.617
in
Token in
Feature activation+0.807
Africa
Token Africa
Feature activation+0.494
by
Token by
Feature activation+1.184
y
Tokeny
Feature activation+0.000
hills
Token hills
Feature activation+0.000
of
Token of
Feature activation+0.000
shr
Token shr
Feature activation+0.000
ubs
Tokenubs
Feature activation+0.083
and
Token and
Feature activation+0.725
chap
Token chap
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ral
Tokenral
Feature activation+0.312
,
Token,
Feature activation+0.586
its
Token its
Feature activation+0.457

INTERVAL 0.458 - 0.611
CONTAINS 0.049%

of
Token of
Feature activation+0.000
energy
Token energy
Feature activation+0.000
from
Token from
Feature activation+0.035
natural
Token natural
Feature activation+0.000
resources
Token resources
Feature activation+0.000
.
Token.
Feature activation+0.604
These
Token These
Feature activation+0.599
activities
Token activities
Feature activation+0.331
include
Token include
Feature activation+0.625
production
Token production
Feature activation+0.087
of
Token of
Feature activation+0.017
er
Token er
Feature activation+0.193
oding
Tokenoding
Feature activation+0.122
.[
Token.[
Feature activation+0.264
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.495
Ċ
TokenĊ
Feature activation+0.490
Ċ
TokenĊ
Feature activation+0.235
Dist
TokenDist
Feature activation+0.000
ances
Tokenances
Feature activation+0.031
Ċ
TokenĊ
Feature activation+0.079
Ċ
TokenĊ
Feature activation+0.006
collection
Token collection
Feature activation+0.523
,
Token,
Feature activation+0.923
sand
Token sand
Feature activation+0.000
and
Token and
Feature activation+0.667
gravel
Token gravel
Feature activation+0.029
mining
Token mining
Feature activation+0.555
and
Token and
Feature activation+0.658
farming
Token farming
Feature activation+0.504
and
Token and
Feature activation+0.625
grazing
Token grazing
Feature activation+0.145
on
Token on
Feature activation+0.545
the
Token the
Feature activation+0.121
Brah
Token Brah
Feature activation+0.000
map
Tokenmap
Feature activation+0.000
utra
Tokenutra
Feature activation+0.057
in
Token in
Feature activation+0.496
its
Token its
Feature activation+0.493
entire
Token entire
Feature activation+0.000
stretch
Token stretch
Feature activation+0.000
in
Token in
Feature activation+0.244
the
Token the
Feature activation+0.176
State
Token State
Feature activation+0.181
onto
Token onto
Feature activation+0.000
dubious
Token dubious
Feature activation+0.000
wind
Token wind
Feature activation+0.000
power
Token power
Feature activation+0.000
projects
Token projects
Feature activation+0.152
and
Token and
Feature activation+0.528
its
Token its
Feature activation+0.284
crippling
Token crippling
Feature activation+0.124
ly
Tokenly
Feature activation+0.000
inefficient
Token inefficient
Feature activation+0.000
Renew
Token Renew
Feature activation+0.000

INTERVAL 0.305 - 0.458
CONTAINS 0.108%

from
Token from
Feature activation+0.158
developing
Token developing
Feature activation+0.000
land
Token land
Feature activation+0.007
right
Token right
Feature activation+0.415
up
Token up
Feature activation+0.330
against
Token against
Feature activation+0.316
the
Token the
Feature activation+0.207
trail
Token trail
Feature activation+0.000
.
Token.
Feature activation+0.417
In
Token In
Feature activation+0.207
Southern
Token Southern
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ump
Tokenump
Feature activation+0.000
Hills
Token Hills
Feature activation+0.000
,
Token,
Feature activation+0.020
this
Token this
Feature activation+0.330
time
Token time
Feature activation+0.429
examining
Token examining
Feature activation+0.411
specific
Token specific
Feature activation+0.000
targets
Token targets
Feature activation+0.000
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
things
Token things
Feature activation+0.000
here
Token here
Feature activation+0.036
.
Token.
Feature activation+0.343
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
in
Token in
Feature activation+0.000
sand
Token sand
Feature activation+0.000
off
Token off
Feature activation+0.239
Cul
Token Cul
Feature activation+0.000
ross
Tokenross
Feature activation+0.097
,
Token,
Feature activation+0.453
where
Token where
Feature activation+0.424
it
Token it
Feature activation+0.053
remained
Token remained
Feature activation+0.000
for
Token for
Feature activation+0.065
80
Token 80
Feature activation+0.096
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
dec
Token dec
Feature activation+0.000
id
Tokenid
Feature activation+0.000
uous
Tokenuous
Feature activation+0.000
material
Token material
Feature activation+0.407
,
Token,
Feature activation+0.239
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.044
sticks
Token sticks
Feature activation+0.000
,
Token,
Feature activation+0.067

INTERVAL 0.153 - 0.305
CONTAINS 0.261%

to
Token to
Feature activation+0.000
produce
Token produce
Feature activation+0.000
electricity
Token electricity
Feature activation+0.000
and
Token and
Feature activation+0.019
heat
Token heat
Feature activation+0.000
,
Token,
Feature activation+0.207
or
Token or
Feature activation+0.120
be
Token be
Feature activation+0.224
scrub
Token scrub
Feature activation+0.000
bed
Tokenbed
Feature activation+0.183
to
Token to
Feature activation+0.120
the
Token the
Feature activation+0.000
le
Token le
Feature activation+0.000
pro
Tokenpro
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
scene
Token scene
Feature activation+0.095
in
Token in
Feature activation+0.174
Pakistan
Token Pakistan
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
1996
Token 1996
Feature activation+0.000
;
Token;
Feature activation+0.000
raids
Token raids
Feature activation+0.000
."
Token."
Feature activation+0.046
Another
TokenAnother
Feature activation+0.018
cottage
Token cottage
Feature activation+0.000
owner
Token owner
Feature activation+0.270
said
Token said
Feature activation+0.302
couples
Token couples
Feature activation+0.000
usually
Token usually
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
depend
Token depend
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
fan
Token fan
Feature activation+0.000
of
Token of
Feature activation+0.000
seed
Token seed
Feature activation+0.000
less
Tokenless
Feature activation+0.174
water
Token water
Feature activation+0.000
melon
Tokenmelon
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
I
Token I
Feature activation+0.203
California
Token California
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
water
Token water
Feature activation+0.000
solutions
Token solutions
Feature activation+0.304
was
Token was
Feature activation+0.760
that
Token that
Feature activation+0.684
it
Token it
Feature activation+0.628
was
Token was
Feature activation+0.373
among
Token among
Feature activation+0.078

INTERVAL 0.000 - 0.153
CONTAINS 99.543%

use
Token use
Feature activation+0.000
popular
Token popular
Feature activation+0.000
Linux
Token Linux
Feature activation+0.000
applications
Token applications
Feature activation+0.000
like
Token like
Feature activation+0.000
Firefox
Token Firefox
Feature activation+0.000
,
Token,
Feature activation+0.000
Thunder
Token Thunder
Feature activation+0.000
bird
Tokenbird
Feature activation+0.000
,
Token,
Feature activation+0.000
Google
Token Google
Feature activation+0.000
anything
Token anything
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
should
Token should
Feature activation+0.000
just
Token just
Feature activation+0.000
kill
Token kill
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
This
Token This
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
suggest
Token suggest
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
Getting
TokenGetting
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Tokens
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
being
Token being
Feature activation+0.000
expected
Token expected
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
months
Token months
Feature activation+0.000
later
Token later
Feature activation+0.000
to
Token to
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H6.7: (feature 12274)

TOP ACTIVATIONS
MAX = 1.866

and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+1.866
with
Token with
Feature activation+0.587
the
Token the
Feature activation+0.661
pair
Token pair
Feature activation+0.228
exiting
Token exiting
Feature activation+0.118
the
Token the
Feature activation+0.000
you
Token you
Feature activation+0.000
be
Token be
Feature activation+0.000
returning
Token returning
Feature activation+0.000
to
Token to
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.377
?
Token?
Feature activation+1.758
Ċ
TokenĊ
Feature activation+0.802
Ċ
TokenĊ
Feature activation+0.552
A
TokenA
Feature activation+0.411
:
Token:
Feature activation+1.337
In
Token In
Feature activation+0.707
they
Token they
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
"
Token "
Feature activation+0.222
but
Tokenbut
Feature activation+1.615
were
Token were
Feature activation+1.093
afraid
Token afraid
Feature activation+0.302
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
,
Token,
Feature activation+0.987
and
Token and
Feature activation+0.944
then
Token then
Feature activation+0.024
he
Token he
Feature activation+0.405
left
Token left
Feature activation+0.145
.
Token.
Feature activation+1.503
Ċ
TokenĊ
Feature activation+0.657
Ċ
TokenĊ
Feature activation+0.553
As
TokenAs
Feature activation+0.000
I
Token I
Feature activation+0.000
step
Token step
Feature activation+0.000
the
Token the
Feature activation+0.000
boys
Token boys
Feature activation+0.000
had
Token had
Feature activation+0.000
returned
Token returned
Feature activation+0.000
home
Token home
Feature activation+0.067
by
Token by
Feature activation+1.432
5
Token 5
Feature activation+0.621
AM
Token AM
Feature activation+0.299
he
Token he
Feature activation+0.177
knew
Token knew
Feature activation+0.039
that
Token that
Feature activation+0.411
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
ride
Token ride
Feature activation+0.000
home
Token home
Feature activation+0.000
must
Token must
Feature activation+1.248
be
Token be
Feature activation+1.374
a
Token a
Feature activation+0.644
lot
Token lot
Feature activation+0.614
of
Token of
Feature activation+0.199
fun
Token fun
Feature activation+0.087
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
right
Token right
Feature activation+0.000
of
Token of
Feature activation+0.000
return
Token return
Feature activation+0.411
for
Token for
Feature activation+1.362
Palestinian
Token Palestinian
Feature activation+0.335
refugees
Token refugees
Feature activation+0.125
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Gir
Token Gir
Feature activation+0.000
one
Tokenone
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.114
for
Token for
Feature activation+1.359
four
Token four
Feature activation+1.039
weeks
Token weeks
Feature activation+0.861
to
Token to
Feature activation+0.439
vote
Token vote
Feature activation+0.000
in
Token in
Feature activation+0.000
guy
Token guy
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
at
Token at
Feature activation+1.346
the
Token the
Feature activation+0.613
right
Token right
Feature activation+0.136
moment
Token moment
Feature activation+0.201
.
Token.
Feature activation+0.321
âĢ
TokenâĢ
Feature activation+0.019
Ukraine
Token Ukraine
Feature activation+0.377
?
Token?
Feature activation+1.758
Ċ
TokenĊ
Feature activation+0.802
Ċ
TokenĊ
Feature activation+0.552
A
TokenA
Feature activation+0.411
:
Token:
Feature activation+1.337
In
Token In
Feature activation+0.707
order
Token order
Feature activation+0.675
to
Token to
Feature activation+0.238
carry
Token carry
Feature activation+0.000
out
Token out
Feature activation+0.238
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
wanting
Token wanting
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
but
Token but
Feature activation+1.328
wanting
Token wanting
Feature activation+0.776
to
Token to
Feature activation+0.007
stay
Token stay
Feature activation+0.000
with
Token with
Feature activation+0.059
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.193
after
Token after
Feature activation+1.298
bringing
Token bringing
Feature activation+0.205
health
Token health
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
ride
Token ride
Feature activation+0.000
home
Token home
Feature activation+0.000
must
Token must
Feature activation+1.248
be
Token be
Feature activation+1.374
a
Token a
Feature activation+0.644
lot
Token lot
Feature activation+0.614
of
Token of
Feature activation+0.199
fun
Token fun
Feature activation+0.087
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
and
Token and
Feature activation+0.555
how
Token how
Feature activation+1.209
to
Token to
Feature activation+0.603
keep
Token keep
Feature activation+0.000
them
Token them
Feature activation+0.000
within
Token within
Feature activation+0.049
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.661
pair
Token pair
Feature activation+0.228
exiting
Token exiting
Feature activation+0.118
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+0.235
quickly
Token quickly
Feature activation+1.192
.
Token.
Feature activation+1.056
Gal
TokenGal
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
back
Token back
Feature activation+0.000
.
Token.
Feature activation+1.190
Their
Token Their
Feature activation+0.196
disappointment
Token disappointment
Feature activation+0.000
was
Token was
Feature activation+0.000
palpable
Token palpable
Feature activation+0.000
.
Token.
Feature activation+0.000
)
Token)
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
home
Token home
Feature activation+0.084
,
Token,
Feature activation+1.175
does
Token does
Feature activation+0.579
he
Token he
Feature activation+0.214
say
Token say
Feature activation+0.188
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
until
Token until
Feature activation+1.168
they
Token they
Feature activation+0.396
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.591
They
Token They
Feature activation+0.383
finally
Token finally
Feature activation+0.352
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
when
Token when
Feature activation+1.161
you
Token you
Feature activation+0.341
want
Token want
Feature activation+0.062
.
Token.
Feature activation+0.000
Plus
Token Plus
Feature activation+0.000
if
Token if
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Getting
TokenGetting
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
normal
Token normal
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.154
Ċ
TokenĊ
Feature activation+1.142
If
TokenIf
Feature activation+0.079
further
Token further
Feature activation+0.000
tests
Token tests
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000

Top DFA by src position
MAX = 2.342

corner
Token corner
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.010
Top resid features:
asked
Token asked
Feature activation+0.015
Top resid features:
them
Token them
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.061
Top resid features:
leave
Token leave
Feature activation+2.342
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pair
Token pair
Feature activation+0.000
Top resid features:
exiting
Token exiting
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.056
Top resid features:
Will
Token Will
Feature activation+0.007
Top resid features:
you
Token you
Feature activation+0.048
Top resid features:
be
Token be
Feature activation+0.073
Top resid features:
returning
Token returning
Feature activation+0.747
Top resid features:
to
Token to
Feature activation+0.998
Top resid features:
Ukraine
Token Ukraine
Feature activation+0.352
Top resid features:
?
Token?
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.040
Top resid features:
they
Token they
Feature activation+0.014
Top resid features:
wanted
Token wanted
Feature activation+0.073
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
return
Token return
Feature activation+2.099
Top resid features:
"
Token "
Feature activation+0.062
Top resid features:
but
Tokenbut
Feature activation-0.004
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
afraid
Token afraid
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
and
Token and
Feature activation-0.036
Top resid features:
then
Token then
Feature activation-0.011
Top resid features:
he
Token he
Feature activation-0.017
Top resid features:
left
Token left
Feature activation+1.402
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
As
TokenAs
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
boys
Token boys
Feature activation+0.006
Top resid features:
had
Token had
Feature activation-0.009
Top resid features:
returned
Token returned
Feature activation+0.427
Top resid features:
home
Token home
Feature activation+1.467
Top resid features:
by
Token by
Feature activation+0.060
Top resid features:
5
Token 5
Feature activation+0.000
Top resid features:
AM
Token AM
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
knew
Token knew
Feature activation+0.000
Top resid features:
help
Token help
Feature activation-0.028
Top resid features:
thinking
Token thinking
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
ride
Token ride
Feature activation+0.195
Top resid features:
home
Token home
Feature activation+1.723
Top resid features:
must
Token must
Feature activation+0.090
Top resid features:
be
Token be
Feature activation+0.012
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
settlements
Token settlements
Feature activation+0.063
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
right
Token right
Feature activation+0.045
Top resid features:
of
Token of
Feature activation+0.034
Top resid features:
return
Token return
Feature activation+1.860
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.000
Top resid features:
refugees
Token refugees
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
ore
Tokenore
Feature activation+0.001
Top resid features:
Gir
Token Gir
Feature activation+0.010
Top resid features:
one
Tokenone
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
return
Token return
Feature activation+0.623
Top resid features:
home
Token home
Feature activation+1.202
Top resid features:
for
Token for
Feature activation+0.075
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
weeks
Token weeks
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
vote
Token vote
Feature activation+0.000
Top resid features:
clever
Token clever
Feature activation-0.017
Top resid features:
guy
Token guy
Feature activation+0.014
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
he
Token he
Feature activation-0.017
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
leave
Token leave
Feature activation+1.983
Top resid features:
at
Token at
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
moment
Token moment
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Q
TokenQ
Feature activation+0.015
Top resid features:
:
Token:
Feature activation+0.013
Top resid features:
Will
Token Will
Feature activation-0.035
Top resid features:
you
Token you
Feature activation+0.041
Top resid features:
be
Token be
Feature activation+0.162
Top resid features:
returning
Token returning
Feature activation+0.833
Top resid features:
to
Token to
Feature activation+0.627
Top resid features:
Ukraine
Token Ukraine
Feature activation+0.121
Top resid features:
?
Token?
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
z
Tokenz
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Not
Token Not
Feature activation+0.012
Top resid features:
wanting
Token wanting
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
leave
Token leave
Feature activation+1.887
Top resid features:
but
Token but
Feature activation+0.008
Top resid features:
wanting
Token wanting
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
stay
Token stay
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
District
Token District
Feature activation-0.003
Top resid features:
told
Token told
Feature activation+0.008
Top resid features:
them
Token them
Feature activation-0.001
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.055
Top resid features:
return
Token return
Feature activation+0.716
Top resid features:
to
Token to
Feature activation+0.680
Top resid features:
the
Token the
Feature activation+0.140
Top resid features:
school
Token school
Feature activation+0.315
Top resid features:
after
Token after
Feature activation+0.037
Top resid features:
bringing
Token bringing
Feature activation+0.000
Top resid features:
help
Token help
Feature activation-0.021
Top resid features:
thinking
Token thinking
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
ride
Token ride
Feature activation+0.164
Top resid features:
home
Token home
Feature activation+1.653
Top resid features:
must
Token must
Feature activation+0.020
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
identify
Token identify
Feature activation-0.023
Top resid features:
who
Token who
Feature activation+0.129
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
about
Token about
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.088
Top resid features:
leave
Token leave
Feature activation+1.637
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
how
Token how
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
keep
Token keep
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
corner
Token corner
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
asked
Token asked
Feature activation-0.000
Top resid features:
them
Token them
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
leave
Token leave
Feature activation+0.763
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
with
Token with
Feature activation+0.023
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
pair
Token pair
Feature activation+0.032
Top resid features:
exiting
Token exiting
Feature activation+0.517
Top resid features:
received
Token received
Feature activation-0.025
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
order
Token order
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
turn
Token turn
Feature activation+0.243
Top resid features:
back
Token back
Feature activation+1.389
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Their
Token Their
Feature activation+0.000
Top resid features:
disappointment
Token disappointment
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
palpable
Token palpable
Feature activation+0.000
Top resid features:
5
Token5
Feature activation-0.008
Top resid features:
)
Token)
Feature activation-0.015
Top resid features:
wants
Token wants
Feature activation+0.073
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
go
Token go
Feature activation+0.446
Top resid features:
home
Token home
Feature activation+1.136
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
won
Token won
Feature activation-0.008
Top resid features:
't
Token't
Feature activation-0.008
Top resid features:
be
Token be
Feature activation+0.016
Top resid features:
allowed
Token allowed
Feature activation-0.007
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
leave
Token leave
Feature activation+1.665
Top resid features:
until
Token until
Feature activation+0.048
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
means
Token means
Feature activation+0.037
Top resid features:
you
Token you
Feature activation+0.012
Top resid features:
are
Token are
Feature activation+0.036
Top resid features:
free
Token free
Feature activation+0.009
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
leave
Token leave
Feature activation+1.739
Top resid features:
when
Token when
Feature activation+0.001
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
want
Token want
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Plus
Token Plus
Feature activation+0.000
Top resid features:
scheduled
Token scheduled
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Getting
TokenGetting
Feature activation+0.042
Top resid features:
back
Token back
Feature activation+0.744
Top resid features:
to
Token to
Feature activation+0.283
Top resid features:
normal
Token normal
Feature activation+0.597
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
If
TokenIf
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.03

Head 3: 0.08

Head 4: 0.06

Head 5: 0.09

Head 6: 0.06

Head 7: 0.41

Head 8: 0.09

Head 9: 0.01

Head 10: 0.02

Head 11: 0.05

Positive logits

goodbye2.21

morrow2.18

waiting2.13

Waiting2.08

quit2.06

leave2.05

impat2.03

oldown1.98

relinqu1.96

Pause1.96

curfew1.93

hitch1.93

esc1.91

remorse1.90

repent1.90

limbo1.87

Goodbye1.87

pause1.87

Cancel1.87

postp1.85

Negative logits

Influ-2.06

aggregate-2.06

prototyp-2.00

predictive-1.95

caric-1.89

aggregation-1.87

innov-1.85

profiling-1.84

refined-1.83

niche-1.82

Trend-1.78

caricature-1.78

sophistication-1.77

otype-1.75

derivatives-1.75

otypes-1.73

acron-1.72

umer-1.72

classification-1.72

Compar-1.72

INTERVAL 1.679 - 1.866
CONTAINS 0.000%

and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+1.866
with
Token with
Feature activation+0.587
the
Token the
Feature activation+0.661
pair
Token pair
Feature activation+0.228
exiting
Token exiting
Feature activation+0.118
the
Token the
Feature activation+0.000
you
Token you
Feature activation+0.000
be
Token be
Feature activation+0.000
returning
Token returning
Feature activation+0.000
to
Token to
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.377
?
Token?
Feature activation+1.758
Ċ
TokenĊ
Feature activation+0.802
Ċ
TokenĊ
Feature activation+0.552
A
TokenA
Feature activation+0.411
:
Token:
Feature activation+1.337
In
Token In
Feature activation+0.707

INTERVAL 1.493 - 1.679
CONTAINS 0.000%

,
Token,
Feature activation+0.987
and
Token and
Feature activation+0.944
then
Token then
Feature activation+0.024
he
Token he
Feature activation+0.405
left
Token left
Feature activation+0.145
.
Token.
Feature activation+1.503
Ċ
TokenĊ
Feature activation+0.657
Ċ
TokenĊ
Feature activation+0.553
As
TokenAs
Feature activation+0.000
I
Token I
Feature activation+0.000
step
Token step
Feature activation+0.000
they
Token they
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
"
Token "
Feature activation+0.222
but
Tokenbut
Feature activation+1.615
were
Token were
Feature activation+1.093
afraid
Token afraid
Feature activation+0.302
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 1.306 - 1.493
CONTAINS 0.001%

and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
right
Token right
Feature activation+0.000
of
Token of
Feature activation+0.000
return
Token return
Feature activation+0.411
for
Token for
Feature activation+1.362
Palestinian
Token Palestinian
Feature activation+0.335
refugees
Token refugees
Feature activation+0.125
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
boys
Token boys
Feature activation+0.000
had
Token had
Feature activation+0.000
returned
Token returned
Feature activation+0.000
home
Token home
Feature activation+0.067
by
Token by
Feature activation+1.432
5
Token 5
Feature activation+0.621
AM
Token AM
Feature activation+0.299
he
Token he
Feature activation+0.177
knew
Token knew
Feature activation+0.039
that
Token that
Feature activation+0.411
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
wanting
Token wanting
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
but
Token but
Feature activation+1.328
wanting
Token wanting
Feature activation+0.776
to
Token to
Feature activation+0.007
stay
Token stay
Feature activation+0.000
with
Token with
Feature activation+0.059
the
Token the
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.377
?
Token?
Feature activation+1.758
Ċ
TokenĊ
Feature activation+0.802
Ċ
TokenĊ
Feature activation+0.552
A
TokenA
Feature activation+0.411
:
Token:
Feature activation+1.337
In
Token In
Feature activation+0.707
order
Token order
Feature activation+0.675
to
Token to
Feature activation+0.238
carry
Token carry
Feature activation+0.000
out
Token out
Feature activation+0.238
guy
Token guy
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
at
Token at
Feature activation+1.346
the
Token the
Feature activation+0.613
right
Token right
Feature activation+0.136
moment
Token moment
Feature activation+0.201
.
Token.
Feature activation+0.321
âĢ
TokenâĢ
Feature activation+0.019

INTERVAL 1.120 - 1.306
CONTAINS 0.001%

)
Token)
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
home
Token home
Feature activation+0.084
,
Token,
Feature activation+1.175
does
Token does
Feature activation+0.579
he
Token he
Feature activation+0.214
say
Token say
Feature activation+0.188
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
when
Token when
Feature activation+1.161
you
Token you
Feature activation+0.341
want
Token want
Feature activation+0.062
.
Token.
Feature activation+0.000
Plus
Token Plus
Feature activation+0.000
if
Token if
Feature activation+0.000
Getting
TokenGetting
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
normal
Token normal
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.154
Ċ
TokenĊ
Feature activation+1.142
If
TokenIf
Feature activation+0.079
further
Token further
Feature activation+0.000
tests
Token tests
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.545
while
Token while
Feature activation+1.120
much
Token much
Feature activation+0.000
needed
Token needed
Feature activation+0.000
repairs
Token repairs
Feature activation+0.000
are
Token are
Feature activation+0.000
carried
Token carried
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.193
after
Token after
Feature activation+1.298
bringing
Token bringing
Feature activation+0.205
health
Token health
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.933 - 1.120
CONTAINS 0.002%

way
Token way
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.023
crisis
Token crisis
Feature activation+0.000
is
Token is
Feature activation+0.997
to
Token to
Feature activation+0.290
implement
Token implement
Feature activation+0.000
an
Token an
Feature activation+0.000
EU
Token EU
Feature activation+0.000
-
Token-
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
released
Token released
Feature activation+0.000
from
Token from
Feature activation+0.000
captivity
Token captivity
Feature activation+0.000
but
Token but
Feature activation+0.626
there
Token there
Feature activation+0.936
was
Token was
Feature activation+0.490
no
Token no
Feature activation+0.188
mention
Token mention
Feature activation+0.187
of
Token of
Feature activation+0.144
any
Token any
Feature activation+0.079
,"
Token,"
Feature activation+0.772
offered
Token offered
Feature activation+0.696
B
Token B
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
an
Tokenan
Feature activation+0.642
.
Token.
Feature activation+1.072
And
Token And
Feature activation+0.461
so
Token so
Feature activation+0.459
he
Token he
Feature activation+0.436
did
Token did
Feature activation+0.632
.
Token.
Feature activation+0.480
"
Token "
Feature activation+0.000
My
TokenMy
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
was
Token was
Feature activation+1.042
my
Token my
Feature activation+0.215
own
Token own
Feature activation+0.000
,"
Token,"
Feature activation+0.020
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.119
one
Tokenone
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.114
for
Token for
Feature activation+1.359
four
Token four
Feature activation+1.039
weeks
Token weeks
Feature activation+0.861
to
Token to
Feature activation+0.439
vote
Token vote
Feature activation+0.000
in
Token in
Feature activation+0.000
last
Token last
Feature activation+0.000

INTERVAL 0.746 - 0.933
CONTAINS 0.008%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+1.062
please
Token please
Feature activation+0.764
,
Token,
Feature activation+0.320
âĢ
TokenâĢ
Feature activation+0.386
Ŀ
TokenĿ
Feature activation+0.618
I
Token I
Feature activation+0.466
said
Token said
Feature activation+0.729
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
getting
Token getting
Feature activation+0.000
off
Token off
Feature activation+0.000
at
Token at
Feature activation+0.836
Venice
Token Venice
Feature activation+0.000
Boulevard
Token Boulevard
Feature activation+0.000
and
Token and
Feature activation+0.000
Western
Token Western
Feature activation+0.000
,
Token,
Feature activation+0.211
to
Token to
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
Arabia
Token Arabia
Feature activation+0.275
,
Token,
Feature activation+0.848
and
Token and
Feature activation+0.663
he
Token he
Feature activation+0.876
told
Token told
Feature activation+0.339
us
Token us
Feature activation+0.194
that
Token that
Feature activation+0.516
we
Token we
Feature activation+0.254
shouldn
Token shouldn
Feature activation+0.055
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
walked
Token walked
Feature activation+0.000
away
Token away
Feature activation+0.000
under
Token under
Feature activation+0.753
cover
Token cover
Feature activation+0.000
of
Token of
Feature activation+0.000
darkness
Token darkness
Feature activation+0.000
on
Token on
Feature activation+0.182
June
Token June
Feature activation+0.064
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
professional
Token professional
Feature activation+0.000
tennis
Token tennis
Feature activation+0.000
?
Token?
Feature activation+0.733
Ċ
TokenĊ
Feature activation+0.793
Ċ
TokenĊ
Feature activation+0.698
Hopefully
TokenHopefully
Feature activation+0.110
.
Token.
Feature activation+0.688
But
Token But
Feature activation+0.081
there
Token there
Feature activation+0.297

INTERVAL 0.560 - 0.746
CONTAINS 0.018%

alone
Token alone
Feature activation+0.000
move
Token move
Feature activation+0.000
to
Token to
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
because
Token because
Feature activation+0.574
of
Token of
Feature activation+0.308
the
Token the
Feature activation+0.091
new
Token new
Feature activation+0.000
building
Token building
Feature activation+0.000
.
Token.
Feature activation+0.025
get
Token get
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
tank
Token tank
Feature activation+0.000
too
Token too
Feature activation+0.566
,"
Token,"
Feature activation+0.247
En
Token En
Feature activation+0.000
os
Tokenos
Feature activation+0.000
said
Token said
Feature activation+0.197
.
Token.
Feature activation+0.267
to
Token to
Feature activation+0.000
professional
Token professional
Feature activation+0.000
tennis
Token tennis
Feature activation+0.000
?
Token?
Feature activation+0.733
Ċ
TokenĊ
Feature activation+0.793
Ċ
TokenĊ
Feature activation+0.698
Hopefully
TokenHopefully
Feature activation+0.110
.
Token.
Feature activation+0.688
But
Token But
Feature activation+0.081
there
Token there
Feature activation+0.297
's
Token's
Feature activation+0.000
then
Token then
Feature activation+0.000
would
Token would
Feature activation+0.000
sc
Token sc
Feature activation+0.000
oot
Tokenoot
Feature activation+0.000
away
Token away
Feature activation+0.105
.
Token.
Feature activation+0.590
"
Token "
Feature activation+0.008
You
TokenYou
Feature activation+0.000
don
Token don
Feature activation+0.066
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.181
be
Token be
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
to
Token to
Feature activation+0.000
release
Token release
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.608
because
Token because
Feature activation+0.459
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.373 - 0.560
CONTAINS 0.040%

another
Token another
Feature activation+0.000
term
Token term
Feature activation+0.000
.
Token.
Feature activation+0.000
Next
Token Next
Feature activation+0.000
step
Token step
Feature activation+0.000
according
Token according
Feature activation+0.444
to
Token to
Feature activation+0.109
the
Token the
Feature activation+0.092
Greek
Token Greek
Feature activation+0.000
experiment
Token experiment
Feature activation+0.000
:
Token:
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.054
he
Token he
Feature activation+0.465
has
Token has
Feature activation+0.294
no
Token no
Feature activation+0.000
pain
Token pain
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.075
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
,
Token,
Feature activation+0.404
low
Token low
Feature activation+0.558
,"
Token,"
Feature activation+0.020
Judge
Token Judge
Feature activation+0.000
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.000
said
Token said
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
on
Token on
Feature activation+0.354
Monday
Token Monday
Feature activation+0.243
,
Token,
Feature activation+0.171
but
Token but
Feature activation+0.544
Luc
Token Luc
Feature activation+0.000
a
Tokena
Feature activation+0.324
was
Token was
Feature activation+0.000
actually
Token actually
Feature activation+0.000
due
Token due
Feature activation+0.000
conclude
Token conclude
Feature activation+0.000
?
Token?
Feature activation+0.374
Or
Token Or
Feature activation+0.070
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000
,
Token,
Feature activation+0.542
is
Token is
Feature activation+0.183
the
Token the
Feature activation+0.000
stock
Token stock
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.000

INTERVAL 0.187 - 0.373
CONTAINS 0.109%

.
Token.
Feature activation+0.000
Turning
Token Turning
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
engine
Token engine
Feature activation+0.196
roughly
Token roughly
Feature activation+0.370
five
Token five
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
early
Token early
Feature activation+0.000
would
Token would
Feature activation+0.000
yield
Token yield
Feature activation+0.000
animals
Token animals
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
family
Token family
Feature activation+0.086
unit
Token unit
Feature activation+0.000
,
Token,
Feature activation+0.274
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
prosecutor
Token prosecutor
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Robinson
Token Robinson
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
relations
Token relations
Feature activation+0.070
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
pair
Token pair
Feature activation+0.000
he
Token he
Feature activation+0.225
offered
Token offered
Feature activation+0.000
them
Token them
Feature activation+0.000
a
Token a
Feature activation+0.000
curry
Token curry
Feature activation+0.000
from
Token from
Feature activation+0.000
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.000
reborn
Token reborn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
tern
Tokentern
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
board
Token board
Feature activation+0.000
each
Token each
Feature activation+0.455
year
Token year
Feature activation+0.134
.
Token.
Feature activation+0.287
Look
Token Look
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000

INTERVAL 0.000 - 0.187
CONTAINS 99.821%

entity
Token entity
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
and
Token and
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
extends
Token extends
Feature activation+0.000
to
Token to
Feature activation+0.000
control
Tokencontrol
Feature activation+0.000
null
Token null
Feature activation+0.000
*
Token*
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Up
TokenUp
Feature activation+0.000
dates
Tokendates
Feature activation+0.000
:
Token:
Feature activation+0.000
(
Token (
Feature activation+0.000
15
Token15
Feature activation+0.000
/
Token/
Feature activation+0.000
and
Token and
Feature activation+0.000
hell
Token hell
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
cast
Token cast
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mark
TokenMark
Feature activation+0.000
St
Token St
Feature activation+0.000
ott
Tokenott
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
page
Token page
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H6.7: (feature 8463)

TOP ACTIVATIONS
MAX = 1.792

were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
very
Token very
Feature activation+0.000
successful
Token successful
Feature activation+0.010
,
Token,
Feature activation+1.050
according
Token according
Feature activation+1.792
to
Token to
Feature activation+1.386
press
Token press
Feature activation+0.053
cl
Token cl
Feature activation+0.000
ipp
Tokenipp
Feature activation+0.000
ings
Tokenings
Feature activation+0.127
got
Token got
Feature activation+0.376
released
Token released
Feature activation+0.044
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.150
,
Token,
Feature activation+1.264
but
Token but
Feature activation+1.529
PS
Token PS
Feature activation+0.000
3
Token3
Feature activation+0.000
gamers
Token gamers
Feature activation+0.000
probably
Token probably
Feature activation+0.000
had
Token had
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
game
Token game
Feature activation+0.596
,
Token,
Feature activation+1.516
but
Token but
Feature activation+1.355
it
Token it
Feature activation+0.808
appeals
Token appeals
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
results
Token results
Feature activation+0.376
that
Token that
Feature activation+0.960
I
Token I
Feature activation+1.058
believe
Token believe
Feature activation+0.990
you
Token you
Feature activation+0.877
were
Token were
Feature activation+1.512
expecting
Token expecting
Feature activation+1.182
,
Token,
Feature activation+1.270
falling
Token falling
Feature activation+0.387
short
Token short
Feature activation+0.257
at
Token at
Feature activation+0.693
it
Token it
Feature activation+0.000
Doesn
Token Doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
Make
Token Make
Feature activation+0.000
Sense
Token Sense
Feature activation+0.000
:
Token:
Feature activation+1.446
Ċ
TokenĊ
Feature activation+1.380
Ċ
TokenĊ
Feature activation+0.572
Jay
TokenJay
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
uden
Tokenuden
Feature activation+0.000
as
Token as
Feature activation+0.373
its
Token its
Feature activation+0.000
producers
Token producers
Feature activation+0.082
hoped
Token hoped
Feature activation+1.025
,
Token,
Feature activation+0.791
but
Token but
Feature activation+1.442
instead
Token instead
Feature activation+0.862
of
Token of
Feature activation+0.000
fading
Token fading
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
commission
Token commission
Feature activation+0.120
for
Token for
Feature activation+1.395
a
Token a
Feature activation+0.796
couple
Token couple
Feature activation+0.171
more
Token more
Feature activation+0.422
days
Token days
Feature activation+0.927
at
Token at
Feature activation+0.496
not
Token not
Feature activation+0.000
very
Token very
Feature activation+0.000
successful
Token successful
Feature activation+0.010
,
Token,
Feature activation+1.050
according
Token according
Feature activation+1.792
to
Token to
Feature activation+1.386
press
Token press
Feature activation+0.053
cl
Token cl
Feature activation+0.000
ipp
Tokenipp
Feature activation+0.000
ings
Tokenings
Feature activation+0.127
from
Token from
Feature activation+0.000
Doesn
Token Doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
Make
Token Make
Feature activation+0.000
Sense
Token Sense
Feature activation+0.000
:
Token:
Feature activation+1.446
Ċ
TokenĊ
Feature activation+1.380
Ċ
TokenĊ
Feature activation+0.572
Jay
TokenJay
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
uden
Tokenuden
Feature activation+0.000
signed
Token signed
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
in
Token in
Feature activation+0.186
the
Token the
Feature activation+0.319
group
Token group
Feature activation+0.028
stages
Token stages
Feature activation+0.386
.
Token.
Feature activation+1.372
What
Token What
Feature activation+1.043
have
Token have
Feature activation+0.746
you
Token you
Feature activation+0.616
guys
Token guys
Feature activation+0.199
worked
Token worked
Feature activation+0.138
oli
Tokenoli
Feature activation+0.057
in
Token in
Feature activation+0.666
a
Token a
Feature activation+0.779
long
Token long
Feature activation+0.454
time
Token time
Feature activation+1.033
,
Token,
Feature activation+1.367
and
Token and
Feature activation+0.633
using
Token using
Feature activation+0.181
a
Token a
Feature activation+0.000
player
Token player
Feature activation+0.000
who
Token who
Feature activation+0.000
the
Token the
Feature activation+0.000
recent
Token recent
Feature activation+0.000
patch
Token patch
Feature activation+0.000
was
Token was
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
was
Token was
Feature activation+1.363
that
Token that
Feature activation+0.313
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
discovered
Token discovered
Feature activation+0.000
additional
Token additional
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
game
Token game
Feature activation+0.596
,
Token,
Feature activation+1.516
but
Token but
Feature activation+1.355
it
Token it
Feature activation+0.808
appeals
Token appeals
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
drag
Token drag
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.123
."
Token."
Feature activation+1.340
Ċ
TokenĊ
Feature activation+0.804
Ċ
TokenĊ
Feature activation+0.206
Some
TokenSome
Feature activation+0.000
apartment
Token apartment
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
being
Token being
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.182
is
Token is
Feature activation+1.264
not
Token not
Feature activation+1.329
equivalent
Token equivalent
Feature activation+0.950
to
Token to
Feature activation+1.256
surrender
Token surrender
Feature activation+0.000
ing
Tokening
Feature activation+0.000
in
Token in
Feature activation+0.000
fal
Token fal
Feature activation+0.000
tered
Tokentered
Feature activation+0.000
on
Token on
Feature activation+0.053
a
Token a
Feature activation+0.546
host
Token host
Feature activation+0.486
of
Token of
Feature activation+1.294
issues
Token issues
Feature activation+0.290
,
Token,
Feature activation+0.210
including
Token including
Feature activation+0.000
scandals
Token scandals
Feature activation+0.000
over
Token over
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
poor
Token poor
Feature activation+0.000
performance
Token performance
Feature activation+0.314
not
Token not
Feature activation+0.331
only
Token only
Feature activation+1.279
ruined
Token ruined
Feature activation+0.394
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
balance
Token balance
Feature activation+0.000
sheet
Token sheet
Feature activation+0.000
I
Token I
Feature activation+1.058
believe
Token believe
Feature activation+0.990
you
Token you
Feature activation+0.877
were
Token were
Feature activation+1.512
expecting
Token expecting
Feature activation+1.182
,
Token,
Feature activation+1.270
falling
Token falling
Feature activation+0.387
short
Token short
Feature activation+0.257
at
Token at
Feature activation+0.693
Dream
Token Dream
Feature activation+0.000
Hack
TokenHack
Feature activation+0.000
But
TokenBut
Feature activation+0.000
being
Token being
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.182
is
Token is
Feature activation+1.264
not
Token not
Feature activation+1.329
equivalent
Token equivalent
Feature activation+0.950
to
Token to
Feature activation+1.256
surrender
Token surrender
Feature activation+0.000
ing
Tokening
Feature activation+0.000
it
Token it
Feature activation+0.367
got
Token got
Feature activation+0.376
released
Token released
Feature activation+0.044
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.150
,
Token,
Feature activation+1.264
but
Token but
Feature activation+1.529
PS
Token PS
Feature activation+0.000
3
Token3
Feature activation+0.000
gamers
Token gamers
Feature activation+0.000
probably
Token probably
Feature activation+0.000

Top DFA by src position
MAX = 1.891

ied
Tokenied
Feature activation+0.001
Top resid features:
ad
Tokenad
Feature activation+0.005
Top resid features:
were
Token were
Feature activation+0.029
Top resid features:
not
Token not
Feature activation+0.041
Top resid features:
very
Token very
Feature activation+0.183
Top resid features:
successful
Token successful
Feature activation+1.694
Top resid features:
,
Token,
Feature activation+0.288
Top resid features:
according
Token according
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
press
Token press
Feature activation+0.000
Top resid features:
cl
Token cl
Feature activation+0.000
Top resid features:
share
Token share
Feature activation-0.046
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
te
Token te
Feature activation+0.000
Top resid features:
et
Tokenet
Feature activation-0.003
Top resid features:
hing
Tokenhing
Feature activation+0.086
Top resid features:
problems
Token problems
Feature activation+1.891
Top resid features:
when
Token when
Feature activation+0.061
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
got
Token got
Feature activation+0.019
Top resid features:
released
Token released
Feature activation-0.024
Top resid features:
last
Token last
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
good
Token good
Feature activation+1.729
Top resid features:
game
Token game
Feature activation+0.166
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
appeals
Token appeals
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.029
Top resid features:
had
Token had
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
kind
Token kind
Feature activation+0.136
Top resid features:
of
Token of
Feature activation+0.084
Top resid features:
results
Token results
Feature activation+1.394
Top resid features:
that
Token that
Feature activation+0.074
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
believe
Token believe
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+0.062
Top resid features:
were
Token were
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Why
TokenWhy
Feature activation-0.005
Top resid features:
it
Token it
Feature activation-0.039
Top resid features:
Doesn
Token Doesn
Feature activation+0.059
Top resid features:
't
Token't
Feature activation+1.183
Top resid features:
Make
Token Make
Feature activation+0.064
Top resid features:
Sense
Token Sense
Feature activation+0.590
Top resid features:
:
Token:
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
franchise
Token franchise
Feature activation+0.005
Top resid features:
never
Token never
Feature activation-0.015
Top resid features:
did
Token did
Feature activation+0.049
Top resid features:
quite
Token quite
Feature activation+0.071
Top resid features:
as
Token as
Feature activation+0.118
Top resid features:
well
Token well
Feature activation+1.214
Top resid features:
at
Token at
Feature activation+0.207
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
box
Token box
Feature activation+0.006
Top resid features:
office
Token office
Feature activation+0.151
Top resid features:
as
Token as
Feature activation+0.063
Top resid features:
station
Token station
Feature activation-0.002
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
out
Token out
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.086
Top resid features:
commission
Token commission
Feature activation+1.704
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
couple
Token couple
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
days
Token days
Feature activation+0.000
Top resid features:
ied
Tokenied
Feature activation+0.001
Top resid features:
ad
Tokenad
Feature activation+0.008
Top resid features:
were
Token were
Feature activation+0.032
Top resid features:
not
Token not
Feature activation+0.056
Top resid features:
very
Token very
Feature activation+0.148
Top resid features:
successful
Token successful
Feature activation+1.303
Top resid features:
,
Token,
Feature activation+0.253
Top resid features:
according
Token according
Feature activation+0.035
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
press
Token press
Feature activation+0.000
Top resid features:
cl
Token cl
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Why
TokenWhy
Feature activation-0.016
Top resid features:
it
Token it
Feature activation-0.029
Top resid features:
Doesn
Token Doesn
Feature activation+0.054
Top resid features:
't
Token't
Feature activation+0.966
Top resid features:
Make
Token Make
Feature activation+0.041
Top resid features:
Sense
Token Sense
Feature activation+0.699
Top resid features:
:
Token:
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.052
Top resid features:
had
Token had
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.076
Top resid features:
kind
Token kind
Feature activation+0.069
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
results
Token results
Feature activation+0.574
Top resid features:
that
Token that
Feature activation+0.143
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
believe
Token believe
Feature activation+0.006
Top resid features:
you
Token you
Feature activation+0.007
Top resid features:
were
Token were
Feature activation+0.010
Top resid features:
He
Token He
Feature activation+0.029
Top resid features:
hasn
Token hasn
Feature activation+0.017
Top resid features:
't
Token't
Feature activation+0.009
Top resid features:
been
Token been
Feature activation+0.024
Top resid features:
very
Token very
Feature activation+0.052
Top resid features:
good
Token good
Feature activation+1.124
Top resid features:
for
Token for
Feature activation+0.315
Top resid features:
Nap
Token Nap
Feature activation-0.006
Top resid features:
oli
Tokenoli
Feature activation+0.066
Top resid features:
in
Token in
Feature activation+0.154
Top resid features:
a
Token a
Feature activation+0.034
Top resid features:
reasons
Token reasons
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
recent
Token recent
Feature activation+0.029
Top resid features:
patch
Token patch
Feature activation+0.009
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
delayed
Token delayed
Feature activation+1.739
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
discovered
Token discovered
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
not
Token not
Feature activation-0.043
Top resid features:
a
Token a
Feature activation-0.034
Top resid features:
good
Token good
Feature activation+1.542
Top resid features:
game
Token game
Feature activation+0.133
Top resid features:
,
Token,
Feature activation+0.224
Top resid features:
but
Token but
Feature activation+0.020
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
appeals
Token appeals
Feature activation+0.000
Top resid features:
main
Token main
Feature activation+0.004
Top resid features:
drag
Token drag
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
"
Token "
Feature activation+0.038
Top resid features:
Not
TokenNot
Feature activation+0.088
Top resid features:
beautiful
Token beautiful
Feature activation+1.646
Top resid features:
."
Token."
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Some
TokenSome
Feature activation+0.000
Top resid features:
apartment
Token apartment
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
But
TokenBut
Feature activation+0.013
Top resid features:
being
Token being
Feature activation+0.064
Top resid features:
unable
Token unable
Feature activation+0.989
Top resid features:
to
Token to
Feature activation+0.255
Top resid features:
win
Token win
Feature activation+0.383
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
not
Token not
Feature activation+0.022
Top resid features:
equivalent
Token equivalent
Feature activation+0.000
Top resid features:
truth
Token truth
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
government
Token government
Feature activation+0.038
Top resid features:
fal
Token fal
Feature activation+0.173
Top resid features:
tered
Tokentered
Feature activation+0.826
Top resid features:
on
Token on
Feature activation+0.760
Top resid features:
a
Token a
Feature activation+0.078
Top resid features:
host
Token host
Feature activation-0.011
Top resid features:
of
Token of
Feature activation-0.054
Top resid features:
issues
Token issues
Feature activation+0.000
Top resid features:
utility
Token utility
Feature activation+0.065
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
poor
Token poor
Feature activation+0.517
Top resid features:
performance
Token performance
Feature activation+1.122
Top resid features:
not
Token not
Feature activation+0.055
Top resid features:
only
Token only
Feature activation+0.019
Top resid features:
ruined
Token ruined
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.026
Top resid features:
had
Token had
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
kind
Token kind
Feature activation+0.118
Top resid features:
of
Token of
Feature activation+0.046
Top resid features:
results
Token results
Feature activation+0.945
Top resid features:
that
Token that
Feature activation+0.158
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
believe
Token believe
Feature activation+0.015
Top resid features:
you
Token you
Feature activation+0.023
Top resid features:
were
Token were
Feature activation+0.039
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
But
TokenBut
Feature activation+0.008
Top resid features:
being
Token being
Feature activation+0.037
Top resid features:
unable
Token unable
Feature activation+0.734
Top resid features:
to
Token to
Feature activation+0.237
Top resid features:
win
Token win
Feature activation+0.672
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
equivalent
Token equivalent
Feature activation+0.000
Top resid features:
share
Token share
Feature activation-0.031
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
te
Token te
Feature activation+0.000
Top resid features:
et
Tokenet
Feature activation-0.003
Top resid features:
hing
Tokenhing
Feature activation+0.097
Top resid features:
problems
Token problems
Feature activation+1.592
Top resid features:
when
Token when
Feature activation+0.062
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
got
Token got
Feature activation+0.023
Top resid features:
released
Token released
Feature activation-0.043
Top resid features:
last
Token last
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.03

Head 3: 0.11

Head 4: 0.06

Head 5: 0.08

Head 6: 0.06

Head 7: 0.41

Head 8: 0.06

Head 9: 0.01

Head 10: 0.02

Head 11: 0.06

Positive logits

Worse3.81

blame3.72

worse3.43

worsened3.38

blaming3.06

blamed3.02

exacerbated2.90

incompetence2.87

plag2.87

Syndrome2.86

weaken2.84

fault2.84

careless2.82

syndrome2.75

blames2.74

faults2.74

havoc2.73

faulty2.72

plagued2.70

inability2.70

Negative logits

Lago-2.39

din-2.33

honoured-2.32

Awesome-2.30

ACP-2.24

AZ-2.10

Wonder-2.09

photos-2.08

mosqu-2.08

confer-2.08

Compact-2.07

authorization-2.03

ceivable-2.02

ausp-1.98

apest-1.96

DonaldTrump-1.94

Authorization-1.93

Guests-1.93

Sphere-1.91

-1.91

INTERVAL 1.612 - 1.792
CONTAINS 0.000%

were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
very
Token very
Feature activation+0.000
successful
Token successful
Feature activation+0.010
,
Token,
Feature activation+1.050
according
Token according
Feature activation+1.792
to
Token to
Feature activation+1.386
press
Token press
Feature activation+0.053
cl
Token cl
Feature activation+0.000
ipp
Tokenipp
Feature activation+0.000
ings
Tokenings
Feature activation+0.127

INTERVAL 1.433 - 1.612
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
game
Token game
Feature activation+0.596
,
Token,
Feature activation+1.516
but
Token but
Feature activation+1.355
it
Token it
Feature activation+0.808
appeals
Token appeals
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
got
Token got
Feature activation+0.376
released
Token released
Feature activation+0.044
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.150
,
Token,
Feature activation+1.264
but
Token but
Feature activation+1.529
PS
Token PS
Feature activation+0.000
3
Token3
Feature activation+0.000
gamers
Token gamers
Feature activation+0.000
probably
Token probably
Feature activation+0.000
had
Token had
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
Make
Token Make
Feature activation+0.000
Sense
Token Sense
Feature activation+0.000
:
Token:
Feature activation+1.446
Ċ
TokenĊ
Feature activation+1.380
Ċ
TokenĊ
Feature activation+0.572
Jay
TokenJay
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
uden
Tokenuden
Feature activation+0.000
results
Token results
Feature activation+0.376
that
Token that
Feature activation+0.960
I
Token I
Feature activation+1.058
believe
Token believe
Feature activation+0.990
you
Token you
Feature activation+0.877
were
Token were
Feature activation+1.512
expecting
Token expecting
Feature activation+1.182
,
Token,
Feature activation+1.270
falling
Token falling
Feature activation+0.387
short
Token short
Feature activation+0.257
at
Token at
Feature activation+0.693
as
Token as
Feature activation+0.373
its
Token its
Feature activation+0.000
producers
Token producers
Feature activation+0.082
hoped
Token hoped
Feature activation+1.025
,
Token,
Feature activation+0.791
but
Token but
Feature activation+1.442
instead
Token instead
Feature activation+0.862
of
Token of
Feature activation+0.000
fading
Token fading
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.254 - 1.433
CONTAINS 0.002%

not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
game
Token game
Feature activation+0.596
,
Token,
Feature activation+1.516
but
Token but
Feature activation+1.355
it
Token it
Feature activation+0.808
appeals
Token appeals
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
commission
Token commission
Feature activation+0.120
for
Token for
Feature activation+1.395
a
Token a
Feature activation+0.796
couple
Token couple
Feature activation+0.171
more
Token more
Feature activation+0.422
days
Token days
Feature activation+0.927
at
Token at
Feature activation+0.496
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
poor
Token poor
Feature activation+0.000
performance
Token performance
Feature activation+0.314
not
Token not
Feature activation+0.331
only
Token only
Feature activation+1.279
ruined
Token ruined
Feature activation+0.394
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
balance
Token balance
Feature activation+0.000
sheet
Token sheet
Feature activation+0.000
being
Token being
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.182
is
Token is
Feature activation+1.264
not
Token not
Feature activation+1.329
equivalent
Token equivalent
Feature activation+0.950
to
Token to
Feature activation+1.256
surrender
Token surrender
Feature activation+0.000
ing
Tokening
Feature activation+0.000
in
Token in
Feature activation+0.000
you
Token you
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
consistently
Token consistently
Feature activation+0.000
buggy
Token buggy
Feature activation+0.000
software
Token software
Feature activation+0.129
...
Token...
Feature activation+1.255
thru
Token thru
Feature activation+0.578
no
Token no
Feature activation+0.236
fault
Token fault
Feature activation+0.285
of
Token of
Feature activation+0.001
your
Token your
Feature activation+0.000

INTERVAL 1.075 - 1.254
CONTAINS 0.002%

no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
as
Token as
Feature activation+0.000
effective
Token effective
Feature activation+0.019
,
Token,
Feature activation+0.947
although
Token although
Feature activation+1.190
it
Token it
Feature activation+0.596
still
Token still
Feature activation+0.547
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
,
Token,
Feature activation+0.065
and
Token and
Feature activation+0.209
for
Token for
Feature activation+0.127
good
Token good
Feature activation+0.350
reason
Token reason
Feature activation+1.216
âĢ¦
TokenâĢ¦
Feature activation+0.000
The
Token The
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
Finance
Token Finance
Feature activation+0.000
and
Token and
Feature activation+0.000
any
Token any
Feature activation+0.101
other
Token other
Feature activation+0.000
imp
Token imp
Feature activation+0.000
orter
Tokenorter
Feature activation+0.000
),
Token),
Feature activation+1.261
then
Token then
Feature activation+1.088
the
Token the
Feature activation+0.263
process
Token process
Feature activation+0.001
is
Token is
Feature activation+0.000
compounded
Token compounded
Feature activation+0.000
extensively
Token extensively
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.150
in
Token in
Feature activation+0.104
recent
Token recent
Feature activation+1.008
years
Token years
Feature activation+1.215
and
Token and
Feature activation+0.863
failed
Token failed
Feature activation+0.410
to
Token to
Feature activation+0.516
improve
Token improve
Feature activation+0.033
the
Token the
Feature activation+0.108
bargain
Token bargain
Feature activation+0.000
.
Token.
Feature activation+0.451
This
Token This
Feature activation+0.572
is
Token is
Feature activation+0.691
consistent
Token consistent
Feature activation+0.620
with
Token with
Feature activation+1.082
past
Token past
Feature activation+0.422
practice
Token practice
Feature activation+0.066
.
Token.
Feature activation+0.227
Israel
Token Israel
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.896 - 1.075
CONTAINS 0.006%

note
Token note
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.206
However
TokenHowever
Feature activation+0.907
,
Token,
Feature activation+0.575
we
Token we
Feature activation+0.000
expect
Token expect
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
certified
Token certified
Feature activation+0.000
fl
Token fl
Feature activation+0.000
op
Tokenop
Feature activation+0.274
.
Token.
Feature activation+0.748
Ċ
TokenĊ
Feature activation+1.018
Ċ
TokenĊ
Feature activation+1.232
The
TokenThe
Feature activation+0.314
military
Token military
Feature activation+0.000
thriller
Token thriller
Feature activation+0.000
Man
Token Man
Feature activation+0.000
the
Token the
Feature activation+0.063
kind
Token kind
Feature activation+0.071
of
Token of
Feature activation+0.107
results
Token results
Feature activation+0.376
that
Token that
Feature activation+0.960
I
Token I
Feature activation+1.058
believe
Token believe
Feature activation+0.990
you
Token you
Feature activation+0.877
were
Token were
Feature activation+1.512
expecting
Token expecting
Feature activation+1.182
,
Token,
Feature activation+1.270
enough
Token enough
Feature activation+0.000
support
Token support
Feature activation+0.000
.
Token.
Feature activation+0.307
But
Token But
Feature activation+0.450
that
Token that
Feature activation+0.504
has
Token has
Feature activation+0.968
not
Token not
Feature activation+0.610
deter
Token deter
Feature activation+0.000
red
Tokenred
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
is
Token is
Feature activation+0.000
probably
Token probably
Feature activation+0.000
not
Token not
Feature activation+0.000
that
Token that
Feature activation+0.000
great
Token great
Feature activation+0.121
and
Token and
Feature activation+1.044
it
Token it
Feature activation+1.106
âĢ
TokenâĢ
Feature activation+0.327
Ļ
TokenĻ
Feature activation+0.320
s
Tokens
Feature activation+0.912
just
Token just
Feature activation+0.397

INTERVAL 0.717 - 0.896
CONTAINS 0.015%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
been
Token been
Feature activation+0.000
pristine
Token pristine
Feature activation+0.103
,
Token,
Feature activation+0.806
and
Token and
Feature activation+0.611
that
Token that
Feature activation+0.668
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.555
really
Token really
Feature activation+0.000
liked
Token liked
Feature activation+0.088
Mole
Token Mole
Feature activation+0.000
very
Token very
Feature activation+0.499
much
Token much
Feature activation+0.276
because
Token because
Feature activation+0.753
he
Token he
Feature activation+0.179
was
Token was
Feature activation+0.146
an
Token an
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.000
child
Token child
Feature activation+0.055
t
Tokent
Feature activation+0.000
good
Token good
Feature activation+0.000
enough
Token enough
Feature activation+0.164
?
Token?
Feature activation+0.794
Does
Token Does
Feature activation+0.462
that
Token that
Feature activation+0.721
mean
Token mean
Feature activation+0.587
I
Token I
Feature activation+0.040
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.123
."
Token."
Feature activation+1.340
Ċ
TokenĊ
Feature activation+0.804
Ċ
TokenĊ
Feature activation+0.206
Some
TokenSome
Feature activation+0.000
apartment
Token apartment
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
.
Token.
Feature activation+0.131
.
Token.
Feature activation+0.623
Med
Token Med
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ocre
Tokenocre
Feature activation+0.310
teams
Token teams
Feature activation+1.217
stay
Token stay
Feature activation+0.755
mediocre
Token mediocre
Feature activation+0.032
.
Token.
Feature activation+1.048
Ċ
TokenĊ
Feature activation+0.344
Ċ
TokenĊ
Feature activation+0.347
From
TokenFrom
Feature activation+0.000

INTERVAL 0.537 - 0.717
CONTAINS 0.038%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
lack
Token lack
Feature activation+0.000
jobs
Token jobs
Feature activation+0.118
.
Token.
Feature activation+0.682
Ċ
TokenĊ
Feature activation+0.490
Ċ
TokenĊ
Feature activation+0.551
Follow
TokenFollow
Feature activation+0.000
Neil
Token Neil
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
control
Token control
Feature activation+0.250
only
Token only
Feature activation+0.629
affects
Token affects
Feature activation+0.283
one
Token one
Feature activation+0.147
character
Token character
Feature activation+0.069
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
surface
Token surface
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
bad
Token bad
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.190
and
Token and
Feature activation+0.625
there
Token there
Feature activation+0.288
's
Token's
Feature activation+0.171
plenty
Token plenty
Feature activation+0.032
of
Token of
Feature activation+0.000
bad
Token bad
Feature activation+0.000
things
Token things
Feature activation+0.041
,
Token,
Feature activation+0.848
it
Token it
Feature activation+0.726
âĢ
TokenâĢ
Feature activation+0.016
Ļ
TokenĻ
Feature activation+0.227
s
Tokens
Feature activation+0.676
very
Token very
Feature activation+0.231
likely
Token likely
Feature activation+0.369
that
Token that
Feature activation+0.272
the
Token the
Feature activation+0.141
original
Token original
Feature activation+0.061
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.555
evident
Token evident
Feature activation+0.555
by
Token by
Feature activation+0.643
the
Token the
Feature activation+0.413
fact
Token fact
Feature activation+0.572
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.118
been
Token been
Feature activation+0.000

INTERVAL 0.358 - 0.537
CONTAINS 0.090%

penalties
Token penalties
Feature activation+0.000
ended
Token ended
Feature activation+0.000
up
Token up
Feature activation+0.000
hurting
Token hurting
Feature activation+0.000
us
Token us
Feature activation+0.000
,"
Token,"
Feature activation+0.503
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.244
"
Token "
Feature activation+0.293
I
TokenI
Feature activation+0.184
fall
Token fall
Feature activation+0.000
behind
Token behind
Feature activation+0.000
in
Token in
Feature activation+0.296
towers
Token towers
Feature activation+0.110
but
Token but
Feature activation+0.816
stay
Token stay
Feature activation+0.488
even
Token even
Feature activation+0.000
in
Token in
Feature activation+0.018
the
Token the
Feature activation+0.052
gold
Token gold
Feature activation+0.000
until
Token until
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
because
Token because
Feature activation+0.416
of
Token of
Feature activation+0.526
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.014
appeal
Token appeal
Feature activation+0.038
to
Token to
Feature activation+0.108
many
Token many
Feature activation+0.372
so
Token so
Feature activation+0.416
we
Token we
Feature activation+0.576
will
Token will
Feature activation+0.496
add
Token add
Feature activation+0.377
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
filter
Token filter
Feature activation+0.000
that
Token that
Feature activation+0.000
plant
Token plant
Feature activation+0.000
got
Token got
Feature activation+0.000
shut
Token shut
Feature activation+0.000
down
Token down
Feature activation+0.000
was
Token was
Feature activation+0.432
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
gasoline
Token gasoline
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000

INTERVAL 0.179 - 0.358
CONTAINS 0.247%

holds
Token holds
Feature activation+0.000
back
Token back
Feature activation+0.000
on
Token on
Feature activation+0.000
spending
Token spending
Feature activation+0.000
,
Token,
Feature activation+0.000
resulting
Token resulting
Feature activation+0.237
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
layoffs
Token layoffs
Feature activation+0.000
,
Token,
Feature activation+0.001
which
Token which
Feature activation+0.000
their
Token their
Feature activation+0.000
health
Token health
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
.
Token.
Feature activation+0.113
Which
Token Which
Feature activation+0.228
seems
Token seems
Feature activation+0.281
a
Token a
Feature activation+0.102
bit
Token bit
Feature activation+0.157
counterproductive
Token counterproductive
Feature activation+0.020
to
Token to
Feature activation+0.025
the
Token the
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
lazy
Token lazy
Feature activation+0.000
eye
Token eye
Feature activation+0.000
and
Token and
Feature activation+0.042
was
Token was
Feature activation+0.188
nicknamed
Token nicknamed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
El
TokenEl
Feature activation+0.000
Tu
Token Tu
Feature activation+0.000
That
TokenThat
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
is
Token is
Feature activation+0.475
sp
Token sp
Feature activation+0.251
urring
Tokenurring
Feature activation+0.206
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
service
Token service
Feature activation+0.000
lives
Token lives
Feature activation+0.000
,
Token,
Feature activation+0.000
worn
Token worn
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.309
ready
Token ready
Feature activation+0.091
for
Token for
Feature activation+0.239
retirement
Token retirement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.179
CONTAINS 99.599%

of
Token of
Feature activation+0.000
bicycl
Token bicycl
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
handed
Token handed
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
fl
Token fl
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
prominent
Token prominent
Feature activation+0.000
national
Token national
Feature activation+0.000
security
Token security
Feature activation+0.000
reporter
Token reporter
Feature activation+0.000
concluded
Token concluded
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
right
Token right
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
focusing
Token focusing
Feature activation+0.000
on
Token on
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
suburbs
Token suburbs
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
lower
Token lower
Feature activation+0.000
north
Token north
Feature activation+0.000
shore
Token shore
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
ethics
Token ethics
Feature activation+0.000
teachers
Token teachers
Feature activation+0.000
players
Token players
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
17
Token17
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H6.7: (feature 9082)

TOP ACTIVATIONS
MAX = 2.174

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
no
Token no
Feature activation+0.000
expert
Token expert
Feature activation+0.000
hire
Token hire
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
people
Token people
Feature activation+0.000
fast
Token fast
Feature activation+1.026
by
Token by
Feature activation+1.424
posting
Token posting
Feature activation+1.249
to
Token to
Feature activation+0.494
200
Token 200
Feature activation+0.066
+
Token+
Feature activation+0.000
job
Token job
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
All
TokenAll
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
team
Token team
Feature activation+0.000
news
Token news
Feature activation+1.294
heading
Token heading
Feature activation+0.051
into
Token into
Feature activation+0.258
Round
Token Round
Feature activation+0.000
14
Token 14
Feature activation+0.000
of
Token of
Feature activation+0.000
began
Token began
Feature activation+0.000
hiring
Token hiring
Feature activation+0.000
200
Token 200
Feature activation+0.214
deputies
Token deputies
Feature activation+0.062
as
Token as
Feature activation+0.628
part
Token part
Feature activation+1.263
of
Token of
Feature activation+1.114
its
Token its
Feature activation+0.838
ongoing
Token ongoing
Feature activation+0.424
reform
Token reform
Feature activation+0.000
effort
Token effort
Feature activation+0.000
.
Token.
Feature activation+0.912
A
Token A
Feature activation+0.641
larger
Token larger
Feature activation+0.537
staff
Token staff
Feature activation+0.197
was
Token was
Feature activation+0.702
needed
Token needed
Feature activation+1.255
to
Token to
Feature activation+0.652
minimize
Token minimize
Feature activation+0.731
officers
Token officers
Feature activation+0.238
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
people
Token people
Feature activation+0.000
fast
Token fast
Feature activation+1.026
by
Token by
Feature activation+1.424
posting
Token posting
Feature activation+1.249
to
Token to
Feature activation+0.494
200
Token 200
Feature activation+0.066
+
Token+
Feature activation+0.000
job
Token job
Feature activation+0.000
sites
Token sites
Feature activation+0.109
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
[
Token [
Feature activation+0.664
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.894
Ċ
TokenĊ
Feature activation+1.241
Ċ
TokenĊ
Feature activation+1.220
Current
TokenCurrent
Feature activation+0.177
members
Token members
Feature activation+0.000
[
Token [
Feature activation+0.313
edit
Token edit
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
[
Token [
Feature activation+0.664
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.894
Ċ
TokenĊ
Feature activation+1.241
Ċ
TokenĊ
Feature activation+1.220
Current
TokenCurrent
Feature activation+0.177
members
Token members
Feature activation+0.000
[
Token [
Feature activation+0.313
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.510
surprises
Token surprises
Feature activation+0.109
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
squad
Token squad
Feature activation+0.000
is
Token is
Feature activation+0.617
announced
Token announced
Feature activation+1.205
towards
Token towards
Feature activation+0.113
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.087
of
Token of
Feature activation+0.029
May
Token May
Feature activation+0.390
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.179
.
Token.
Feature activation+1.136
He
Token He
Feature activation+0.123
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
grown
Token grown
Feature activation+0.042
to
Token to
Feature activation+0.000
ten
Token ten
Feature activation+0.137
teams
Token teams
Feature activation+0.110
,
Token,
Feature activation+1.060
with
Token with
Feature activation+1.121
six
Token six
Feature activation+0.560
located
Token located
Feature activation+0.103
in
Token in
Feature activation+0.100
the
Token the
Feature activation+0.173
Atlantic
Token Atlantic
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
no
Token no
Feature activation+0.000
hiring
Token hiring
Feature activation+0.000
200
Token 200
Feature activation+0.214
deputies
Token deputies
Feature activation+0.062
as
Token as
Feature activation+0.628
part
Token part
Feature activation+1.263
of
Token of
Feature activation+1.114
its
Token its
Feature activation+0.838
ongoing
Token ongoing
Feature activation+0.424
reform
Token reform
Feature activation+0.000
effort
Token effort
Feature activation+0.000
at
Token at
Feature activation+0.373
-
Token -
Feature activation+0.155
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bench
Token bench
Feature activation+0.000
even
Token even
Feature activation+0.648
though
Token though
Feature activation+1.099
neither
Token neither
Feature activation+0.056
one
Token one
Feature activation+0.084
was
Token was
Feature activation+0.586
really
Token really
Feature activation+0.128
qualified
Token qualified
Feature activation+0.066
had
Token had
Feature activation+0.000
grown
Token grown
Feature activation+0.042
to
Token to
Feature activation+0.000
ten
Token ten
Feature activation+0.137
teams
Token teams
Feature activation+0.110
,
Token,
Feature activation+1.060
with
Token with
Feature activation+1.121
six
Token six
Feature activation+0.560
located
Token located
Feature activation+0.103
in
Token in
Feature activation+0.100
the
Token the
Feature activation+0.173
comes
Token comes
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
talent
Token talent
Feature activation+0.000
.
Token.
Feature activation+1.046
So
Token So
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
new
Token new
Feature activation+0.000
members
Token members
Feature activation+0.215
joining
Token joining
Feature activation+0.398
since
Token since
Feature activation+1.046
the
Token the
Feature activation+0.428
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.833
This
Token This
Feature activation+0.456
recruitment
Token recruitment
Feature activation+0.425
.
Token.
Feature activation+0.029
Ċ
TokenĊ
Feature activation+0.048
Ċ
TokenĊ
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
Team
Token Team
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.041
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
-
Token-
Feature activation+0.000
built
Token built
Feature activation+0.000
out
Token out
Feature activation+0.000
an
Token an
Feature activation+0.000
exceptional
Token exceptional
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+1.029
We
Token We
Feature activation+0.496
are
Token are
Feature activation+0.331
a
Token a
Feature activation+0.168
collection
Token collection
Feature activation+0.279
of
Token of
Feature activation+0.457

Top DFA by src position
MAX = 2.676

.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Growing
TokenGrowing
Feature activation-0.024
Top resid features:
a
Token a
Feature activation+0.063
Top resid features:
team
Token team
Feature activation+2.676
Top resid features:
is
Token is
Feature activation+0.020
Top resid features:
hard
Token hard
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Growing
TokenGrowing
Feature activation-0.031
Top resid features:
a
Token a
Feature activation+0.044
Top resid features:
team
Token team
Feature activation+2.388
Top resid features:
is
Token is
Feature activation+0.034
Top resid features:
hard
Token hard
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
Find
TokenFind
Feature activation+0.013
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
hire
Token hire
Feature activation+0.347
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
right
Token right
Feature activation+0.027
Top resid features:
people
Token people
Feature activation+1.564
Top resid features:
fast
Token fast
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
posting
Token posting
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
200
Token 200
Feature activation+0.000
Top resid features:
Stories
Token Stories
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.023
Top resid features:
All
TokenAll
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.027
Top resid features:
latest
Token latest
Feature activation-0.139
Top resid features:
team
Token team
Feature activation+1.976
Top resid features:
news
Token news
Feature activation+0.081
Top resid features:
heading
Token heading
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
Round
Token Round
Feature activation+0.000
Top resid features:
14
Token 14
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
department
Token department
Feature activation+0.007
Top resid features:
began
Token began
Feature activation+0.009
Top resid features:
hiring
Token hiring
Feature activation+0.604
Top resid features:
200
Token 200
Feature activation+0.201
Top resid features:
deputies
Token deputies
Feature activation+0.948
Top resid features:
as
Token as
Feature activation+0.088
Top resid features:
part
Token part
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
ongoing
Token ongoing
Feature activation+0.000
Top resid features:
clus
Tokenclus
Feature activation+0.012
Top resid features:
iveness
Tokeniveness
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
A
Token A
Feature activation+0.003
Top resid features:
larger
Token larger
Feature activation+0.278
Top resid features:
staff
Token staff
Feature activation+1.215
Top resid features:
was
Token was
Feature activation+0.095
Top resid features:
needed
Token needed
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
minimize
Token minimize
Feature activation+0.000
Top resid features:
officers
Token officers
Feature activation+0.000
Top resid features:
Find
TokenFind
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
hire
Token hire
Feature activation+0.232
Top resid features:
the
Token the
Feature activation+0.108
Top resid features:
right
Token right
Feature activation+0.027
Top resid features:
people
Token people
Feature activation+1.424
Top resid features:
fast
Token fast
Feature activation+0.008
Top resid features:
by
Token by
Feature activation+0.043
Top resid features:
posting
Token posting
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
200
Token 200
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.023
Top resid features:
1
Token1
Feature activation-0.001
Top resid features:
]
Token]
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.048
Top resid features:
Members
TokenMembers
Feature activation+1.521
Top resid features:
[
Token [
Feature activation+0.060
Top resid features:
edit
Token edit
Feature activation+0.017
Top resid features:
]
Token ]
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.025
Top resid features:
1
Token1
Feature activation-0.001
Top resid features:
]
Token]
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Members
TokenMembers
Feature activation+1.392
Top resid features:
[
Token [
Feature activation+0.083
Top resid features:
edit
Token edit
Feature activation+0.007
Top resid features:
]
Token ]
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.080
Top resid features:
great
Token great
Feature activation+0.001
Top resid features:
selection
Token selection
Feature activation+0.084
Top resid features:
surprises
Token surprises
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
squad
Token squad
Feature activation+1.615
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
announced
Token announced
Feature activation+0.025
Top resid features:
towards
Token towards
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
plane
Token plane
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
make
Token make
Feature activation-0.024
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
team
Token team
Feature activation+1.667
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
league
Token league
Feature activation+0.067
Top resid features:
had
Token had
Feature activation+0.020
Top resid features:
grown
Token grown
Feature activation+0.085
Top resid features:
to
Token to
Feature activation+0.067
Top resid features:
ten
Token ten
Feature activation+0.253
Top resid features:
teams
Token teams
Feature activation+0.996
Top resid features:
,
Token,
Feature activation+0.153
Top resid features:
with
Token with
Feature activation-0.014
Top resid features:
six
Token six
Feature activation+0.000
Top resid features:
located
Token located
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Growing
TokenGrowing
Feature activation+0.046
Top resid features:
a
Token a
Feature activation+0.216
Top resid features:
team
Token team
Feature activation+1.373
Top resid features:
is
Token is
Feature activation+0.058
Top resid features:
hard
Token hard
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
department
Token department
Feature activation+0.010
Top resid features:
began
Token began
Feature activation+0.019
Top resid features:
hiring
Token hiring
Feature activation+0.438
Top resid features:
200
Token 200
Feature activation+0.341
Top resid features:
deputies
Token deputies
Feature activation+0.860
Top resid features:
as
Token as
Feature activation+0.087
Top resid features:
part
Token part
Feature activation+0.022
Top resid features:
of
Token of
Feature activation-0.026
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
ongoing
Token ongoing
Feature activation+0.000
Top resid features:
appointed
Token appointed
Feature activation+0.156
Top resid features:
a
Token a
Feature activation+0.044
Top resid features:
couple
Token couple
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
cr
Token cr
Feature activation+0.008
Top resid features:
onies
Tokenonies
Feature activation+0.610
Top resid features:
-
Token -
Feature activation+0.035
Top resid features:
Rebecca
Token Rebecca
Feature activation-0.011
Top resid features:
Bradley
Token Bradley
Feature activation-0.005
Top resid features:
and
Token and
Feature activation-0.010
Top resid features:
James
Token James
Feature activation-0.002
Top resid features:
league
Token league
Feature activation+0.022
Top resid features:
had
Token had
Feature activation+0.018
Top resid features:
grown
Token grown
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
ten
Token ten
Feature activation+0.243
Top resid features:
teams
Token teams
Feature activation+1.145
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
six
Token six
Feature activation+0.000
Top resid features:
located
Token located
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
really
Token really
Feature activation-0.001
Top resid features:
comes
Token comes
Feature activation+0.004
Top resid features:
down
Token down
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
talent
Token talent
Feature activation+1.558
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
So
Token So
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.002
Top resid features:
1
Token 1
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
000
Token000
Feature activation+0.082
Top resid features:
new
Token new
Feature activation+0.110
Top resid features:
members
Token members
Feature activation+1.113
Top resid features:
joining
Token joining
Feature activation+0.285
Top resid features:
since
Token since
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
election
Token election
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Our
TokenOur
Feature activation+0.039
Top resid features:
Team
Token Team
Feature activation+1.170
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
When
TokenWhen
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
since
Token since
Feature activation-0.002
Top resid features:
built
Token built
Feature activation-0.015
Top resid features:
out
Token out
Feature activation+0.042
Top resid features:
an
Token an
Feature activation+0.003
Top resid features:
exceptional
Token exceptional
Feature activation+0.006
Top resid features:
team
Token team
Feature activation+1.597
Top resid features:
.
Token.
Feature activation+0.079
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
collection
Token collection
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.04

Head 3: 0.07

Head 4: 0.08

Head 5: 0.09

Head 6: 0.06

Head 7: 0.40

Head 8: 0.06

Head 9: 0.01

Head 10: 0.02

Head 11: 0.05

Positive logits

recruitment3.32

roster2.85

rosters2.73

recruiting2.72

recruit2.64

recruits2.60

attrition2.56

recruited2.50

Teams2.49

vacancies2.48

staffing2.45

hiring2.44

payroll2.41

manpower2.40

hires2.32

squads2.27

organizational2.26

staffed2.22

quotas2.20

salary2.17

Negative logits

avorite-2.19

Meteor-2.17

pollutants-2.16

Vapor-2.09

conom-2.07

ibur-2.03

meteor-2.02

polluted-1.94

Tropical-1.89

pollut-1.88

Glac-1.85

raviolet-1.84

pollen-1.82

outher-1.81

electromagnetic-1.80

collided-1.79

graz-1.76

Kindle-1.76

contamin-1.76

renheit-1.76

INTERVAL 1.957 - 2.174
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000

INTERVAL 1.739 - 1.957
CONTAINS 0.000%

Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
no
Token no
Feature activation+0.000
expert
Token expert
Feature activation+0.000

INTERVAL 1.522 - 1.739
CONTAINS 0.000%

INTERVAL 1.305 - 1.522
CONTAINS 0.000%

hire
Token hire
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
people
Token people
Feature activation+0.000
fast
Token fast
Feature activation+1.026
by
Token by
Feature activation+1.424
posting
Token posting
Feature activation+1.249
to
Token to
Feature activation+0.494
200
Token 200
Feature activation+0.066
+
Token+
Feature activation+0.000
job
Token job
Feature activation+0.000

INTERVAL 1.087 - 1.305
CONTAINS 0.001%

began
Token began
Feature activation+0.000
hiring
Token hiring
Feature activation+0.000
200
Token 200
Feature activation+0.214
deputies
Token deputies
Feature activation+0.062
as
Token as
Feature activation+0.628
part
Token part
Feature activation+1.263
of
Token of
Feature activation+1.114
its
Token its
Feature activation+0.838
ongoing
Token ongoing
Feature activation+0.424
reform
Token reform
Feature activation+0.000
effort
Token effort
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
people
Token people
Feature activation+0.000
fast
Token fast
Feature activation+1.026
by
Token by
Feature activation+1.424
posting
Token posting
Feature activation+1.249
to
Token to
Feature activation+0.494
200
Token 200
Feature activation+0.066
+
Token+
Feature activation+0.000
job
Token job
Feature activation+0.000
sites
Token sites
Feature activation+0.109
Ċ
TokenĊ
Feature activation+0.000
Growing
TokenGrowing
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.841
is
Token is
Feature activation+2.174
hard
Token hard
Feature activation+1.119
Ċ
TokenĊ
Feature activation+1.837
Ċ
TokenĊ
Feature activation+1.008
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.179
.
Token.
Feature activation+1.136
He
Token He
Feature activation+0.123
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.912
A
Token A
Feature activation+0.641
larger
Token larger
Feature activation+0.537
staff
Token staff
Feature activation+0.197
was
Token was
Feature activation+0.702
needed
Token needed
Feature activation+1.255
to
Token to
Feature activation+0.652
minimize
Token minimize
Feature activation+0.731
officers
Token officers
Feature activation+0.238
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.870 - 1.087
CONTAINS 0.003%

are
Token are
Feature activation+0.396
boosted
Token boosted
Feature activation+0.997
by
Token by
Feature activation+0.664
a
Token a
Feature activation+0.675
recruitment
Token recruitment
Feature activation+0.167
drive
Token drive
Feature activation+0.877
to
Token to
Feature activation+0.319
hire
Token hire
Feature activation+0.147
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.341
500
Token500
Feature activation+0.673
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.000
hire
Token hire
Feature activation+0.309
individuals
Token individuals
Feature activation+0.537
if
Token if
Feature activation+0.993
they
Token they
Feature activation+0.243
absolutely
Token absolutely
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.340
Opt
TokenOpt
Feature activation+0.000
imize
Tokenimize
Feature activation+0.000
your
Token your
Feature activation+0.000
Line
Token Line
Feature activation+0.000
up
Tokenup
Feature activation+0.231
Ċ
TokenĊ
Feature activation+0.934
Ċ
TokenĊ
Feature activation+0.553
M
TokenM
Feature activation+0.000
ight
Tokenight
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.146
at
Token at
Feature activation+0.386
the
Token the
Feature activation+0.304
riding
Token riding
Feature activation+0.000
level
Token level
Feature activation+0.451
.
Token.
Feature activation+0.911
Even
Token Even
Feature activation+0.374
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
warts
Tokenwarts
Feature activation+0.094
who
Token who
Feature activation+0.013
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
new
Token new
Feature activation+0.000
members
Token members
Feature activation+0.215
joining
Token joining
Feature activation+0.398
since
Token since
Feature activation+1.046
the
Token the
Feature activation+0.428
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.833
This
Token This
Feature activation+0.456
recruitment
Token recruitment
Feature activation+0.425

INTERVAL 0.652 - 0.870
CONTAINS 0.009%

actors
Token actors
Feature activation+0.144
available
Token available
Feature activation+0.113
,
Token,
Feature activation+0.957
no
Token no
Feature activation+0.528
problem
Token problem
Feature activation+0.629
!
Token!
Feature activation+0.859
You
Token You
Feature activation+0.373
can
Token can
Feature activation+0.571
add
Token add
Feature activation+0.422
digital
Token digital
Feature activation+0.000
stand
Token stand
Feature activation+0.000
the
Token the
Feature activation+0.000
ship
Token ship
Feature activation+0.000
building
Tokenbuilding
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
will
Token will
Feature activation+0.595
double
Token double
Feature activation+0.715
,
Token,
Feature activation+0.597
possibly
Token possibly
Feature activation+0.200
triple
Token triple
Feature activation+0.642
.
Token.
Feature activation+0.459
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
player
Token player
Feature activation+0.683
&
Token &
Feature activation+0.593
want
Token want
Feature activation+0.463
to
Token to
Feature activation+0.390
help
Token help
Feature activation+0.000
others
Token others
Feature activation+0.000
of
Token of
Feature activation+0.304
these
Token these
Feature activation+0.138
team
Token team
Feature activation+0.000
members
Token members
Feature activation+0.281
are
Token are
Feature activation+0.261
identified
Token identified
Feature activation+0.724
on
Token on
Feature activation+0.495
the
Token the
Feature activation+0.414
site
Token site
Feature activation+0.256
.
Token.
Feature activation+0.268
Multiple
Token Multiple
Feature activation+0.291
place
Token place
Feature activation+0.000
two
Token two
Feature activation+0.000
brig
Token brig
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
on
Token on
Feature activation+0.276
its
Token its
Feature activation+0.670
Eastern
Token Eastern
Feature activation+0.000
flank
Token flank
Feature activation+0.000
.
Token.
Feature activation+0.299
As
Token As
Feature activation+0.147
it
Token it
Feature activation+0.000

INTERVAL 0.435 - 0.652
CONTAINS 0.035%

X
Token X
Feature activation+0.038
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.111
sales
Token sales
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
but
Token but
Feature activation+0.576
only
Token only
Feature activation+0.424
20
Token 20
Feature activation+0.473
%
Token%
Feature activation+0.135
of
Token of
Feature activation+0.399
them
Token them
Feature activation+0.181
much
Token much
Feature activation+0.000
less
Token less
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.103
experience
Token experience
Feature activation+0.698
than
Token than
Feature activation+0.571
many
Token many
Feature activation+0.581
other
Token other
Feature activation+0.477
ministers
Token ministers
Feature activation+0.060
.
Token.
Feature activation+0.773
If
Token If
Feature activation+0.275
experience
Token experience
Feature activation+0.053
will
Token will
Feature activation+0.000
allow
Token allow
Feature activation+0.000
training
Token training
Feature activation+0.000
500
Token 500
Feature activation+0.000
pastors
Token pastors
Feature activation+0.000
,
Token,
Feature activation+0.511
servants
Token servants
Feature activation+0.000
and
Token and
Feature activation+0.121
priests
Token priests
Feature activation+0.059
to
Token to
Feature activation+0.068
be
Token be
Feature activation+0.109
these
Token these
Feature activation+0.138
team
Token team
Feature activation+0.000
members
Token members
Feature activation+0.281
are
Token are
Feature activation+0.261
identified
Token identified
Feature activation+0.724
on
Token on
Feature activation+0.495
the
Token the
Feature activation+0.414
site
Token site
Feature activation+0.256
.
Token.
Feature activation+0.268
Multiple
Token Multiple
Feature activation+0.291
attempts
Token attempts
Feature activation+0.099
The
TokenThe
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
draft
Token draft
Feature activation+0.000
class
Token class
Feature activation+0.006
,
Token,
Feature activation+0.410
with
Token with
Feature activation+0.524
some
Token some
Feature activation+0.553
slight
Token slight
Feature activation+0.193
exceptions
Token exceptions
Feature activation+0.000
,
Token,
Feature activation+0.147
was
Token was
Feature activation+0.469

INTERVAL 0.217 - 0.435
CONTAINS 0.114%

citizen
Token citizen
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.159
,
Token,
Feature activation+0.027
except
Token except
Feature activation+0.257
for
Token for
Feature activation+0.288
the
Token the
Feature activation+0.247
professional
Token professional
Feature activation+0.098
army
Token army
Feature activation+0.320
of
Token of
Feature activation+0.475
Spart
Token Spart
Feature activation+0.000
a
Tokena
Feature activation+0.008
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
John
Token John
Feature activation+0.000
's
Token's
Feature activation+0.000
and
Token and
Feature activation+0.000
had
Token had
Feature activation+0.259
earned
Token earned
Feature activation+0.119
good
Token good
Feature activation+0.000
grades
Token grades
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
during
Token during
Feature activation+0.000
pools
Token pools
Feature activation+0.000
and
Token and
Feature activation+0.000
once
Token once
Feature activation+0.000
you
Token you
Feature activation+0.000
rise
Token rise
Feature activation+0.235
up
Token up
Feature activation+0.009
to
Token to
Feature activation+0.000
top
Token top
Feature activation+0.000
32
Token 32
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
maintain
Token maintain
Feature activation+0.000
er
Tokener
Feature activation+0.000
or
Token or
Feature activation+0.329
even
Token even
Feature activation+0.302
been
Token been
Feature activation+0.397
booted
Token booted
Feature activation+0.152
in
Token in
Feature activation+0.004
about
Token about
Feature activation+0.000
an
Tokenan
Feature activation+0.000
engaged
Token engaged
Feature activation+0.000
community
Token community
Feature activation+0.023
of
Token of
Feature activation+0.373
supporters
Token supporters
Feature activation+0.392
and
Token and
Feature activation+0.246
early
Token early
Feature activation+0.000
adop
Token adop
Feature activation+0.000
ters
Tokenters
Feature activation+0.032
.
Token .
Feature activation+0.467
The
Token The
Feature activation+0.401

INTERVAL 0.000 - 0.217
CONTAINS 99.836%

after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
approved
Token approved
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
October
Token October
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
lasting
Tokenlasting
Feature activation+0.000
souven
Token souven
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
should
Token should
Feature activation+0.000
dissolve
Token dissolve
Feature activation+0.000
the
Token the
Feature activation+0.000
special
Token special
Feature activation+0.000
panel
Token panel
Feature activation+0.000
investigating
Token investigating
Feature activation+0.000
the
Token the
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
Benghazi
Token Benghazi
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
.
Token.
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
ARE
Token ARE
Feature activation+0.000
NOT
Token NOT
Feature activation+0.000
HELP
Token HELP
Feature activation+0.000
ING
TokenING
Feature activation+0.000
,
Token,
Feature activation+0.000
SC
Token SC
Feature activation+0.000
AN
TokenAN
Feature activation+0.000
LINE
TokenLINE
Feature activation+0.000
FIL
Token FIL
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
was
Token was
Feature activation+0.000
held
Token held
Feature activation+0.000
on
Token on
Feature activation+0.000
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
possessing
Token possessing
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 7 in H6.7: (feature 19223)

TOP ACTIVATIONS
MAX = 2.150

medical
Token medical
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.039
die
Token die
Feature activation+0.134
...
Token...
Feature activation+1.730
because
Token because
Feature activation+0.945
of
Token of
Feature activation+1.092
cosmic
Token cosmic
Feature activation+0.405
rays
Token rays
Feature activation+0.172
!
Token!
Feature activation+0.830
death
Token death
Feature activation+0.187
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.164
run
Token run
Feature activation+0.136
over
Token over
Feature activation+0.000
.
Token.
Feature activation+1.484
In
Token In
Feature activation+0.535
fact
Token fact
Feature activation+0.745
,
Token,
Feature activation+0.793
he
Token he
Feature activation+0.966
was
Token was
Feature activation+0.837
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
killed
Token killed
Feature activation+0.593
is
Token is
Feature activation+1.343
not
Token not
Feature activation+0.563
imm
Token imm
Feature activation+0.275
aterial
Tokenaterial
Feature activation+0.674
to
Token to
Feature activation+0.208
how
Token how
Feature activation+0.282
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+1.111
from
Token from
Feature activation+1.270
an
Token an
Feature activation+0.935
ambush
Token ambush
Feature activation+0.111
in
Token in
Feature activation+0.008
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.083
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.605
killed
Token killed
Feature activation+0.294
,
Token,
Feature activation+1.247
it
Token it
Feature activation+1.110
would
Token would
Feature activation+1.106
prompt
Token prompt
Feature activation+0.574
journalists
Token journalists
Feature activation+0.077
and
Token and
Feature activation+0.000
ĵ
Tokenĵ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
we
Token we
Feature activation+0.000
die
Token die
Feature activation+0.085
,
Token,
Feature activation+0.792
we
Token we
Feature activation+1.233
want
Token want
Feature activation+0.694
people
Token people
Feature activation+0.013
to
Token to
Feature activation+0.038
accept
Token accept
Feature activation+0.001
it
Token it
Feature activation+0.046
killing
Token killing
Feature activation+0.000
4
Token 4
Feature activation+0.105
,
Token,
Feature activation+0.064
000
Token000
Feature activation+0.057
people
Token people
Feature activation+0.337
every
Token every
Feature activation+1.229
year
Token year
Feature activation+1.052
.
Token.
Feature activation+0.972
This
Token This
Feature activation+0.806
has
Token has
Feature activation+0.811
just
Token just
Feature activation+0.129
suggested
Token suggested
Feature activation+0.000
his
Token his
Feature activation+0.000
employees
Token employees
Feature activation+0.000
commit
Token commit
Feature activation+0.000
suicide
Token suicide
Feature activation+0.147
if
Token if
Feature activation+1.181
they
Token they
Feature activation+0.354
are
Token are
Feature activation+0.462
unhappy
Token unhappy
Feature activation+0.138
Ċ
TokenĊ
Feature activation+0.150
Ċ
TokenĊ
Feature activation+0.000
die
Token die
Feature activation+0.147
âĢĵ
Token âĢĵ
Feature activation+0.897
that
Token that
Feature activation+0.927
is
Token is
Feature activation+0.782
,
Token,
Feature activation+0.975
we
Token we
Feature activation+1.178
will
Token will
Feature activation+0.707
no
Token no
Feature activation+0.292
longer
Token longer
Feature activation+0.107
be
Token be
Feature activation+0.135
alive
Token alive
Feature activation+0.132
I
Token I
Feature activation+0.000
die
Token die
Feature activation+0.118
anytime
Token anytime
Feature activation+0.491
soon
Token soon
Feature activation+0.644
,
Token,
Feature activation+0.496
it
Token it
Feature activation+1.152
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.939
probably
Token probably
Feature activation+0.744
likely
Token likely
Feature activation+0.915
somehow
Token somehow
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+1.111
from
Token from
Feature activation+1.270
an
Token an
Feature activation+0.935
ambush
Token ambush
Feature activation+0.111
in
Token in
Feature activation+0.008
the
Token the
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
dance
Token dance
Feature activation+0.000
with
Token with
Feature activation+0.000
death
Token death
Feature activation+0.000
every
Token every
Feature activation+1.111
day
Token day
Feature activation+0.742
,
Token,
Feature activation+0.752
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.007
said
Token said
Feature activation+0.000
been
Token been
Feature activation+0.000
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.605
killed
Token killed
Feature activation+0.294
,
Token,
Feature activation+1.247
it
Token it
Feature activation+1.110
would
Token would
Feature activation+1.106
prompt
Token prompt
Feature activation+0.574
journalists
Token journalists
Feature activation+0.077
and
Token and
Feature activation+0.000
friends
Token friends
Feature activation+0.000
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.605
killed
Token killed
Feature activation+0.294
,
Token,
Feature activation+1.247
it
Token it
Feature activation+1.110
would
Token would
Feature activation+1.106
prompt
Token prompt
Feature activation+0.574
journalists
Token journalists
Feature activation+0.077
and
Token and
Feature activation+0.000
friends
Token friends
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.039
die
Token die
Feature activation+0.134
...
Token...
Feature activation+1.730
because
Token because
Feature activation+0.945
of
Token of
Feature activation+1.092
cosmic
Token cosmic
Feature activation+0.405
rays
Token rays
Feature activation+0.172
!
Token!
Feature activation+0.830
Ċ
TokenĊ
Feature activation+0.637
Ċ
TokenĊ
Feature activation+0.381
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
you
Token you
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
hell
Token hell
Feature activation+0.000
?'
Token?'
Feature activation+1.091
I
Token I
Feature activation+0.031
didn
Token didn
Feature activation+0.039
't
Token't
Feature activation+0.000
even
Token even
Feature activation+0.000
have
Token have
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
die
Token die
Feature activation+0.008
.
Token.
Feature activation+1.090
I
Token I
Feature activation+0.424
decide
Token decide
Feature activation+0.518
I
Token I
Feature activation+0.357
can
Token can
Feature activation+0.035
ditch
Token ditch
Feature activation+0.000
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
life
Token life
Feature activation+0.655
three
Token three
Feature activation+0.929
times
Token times
Feature activation+0.995
after
Token after
Feature activation+1.072
suffering
Token suffering
Feature activation+0.310
a
Token a
Feature activation+0.175
lifetime
Token lifetime
Feature activation+0.000
of
Token of
Feature activation+0.000
trauma
Token trauma
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
chemical
Token chemical
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
would
Token would
Feature activation+1.038
be
Token be
Feature activation+1.058
a
Token a
Feature activation+1.025
'
Token '
Feature activation+0.000
red
Tokenred
Feature activation+0.000
line
Token line
Feature activation+0.147
'
Token'
Feature activation+0.000
those
Token those
Feature activation+0.000
cases
Token cases
Feature activation+0.000
were
Token were
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
,
Token,
Feature activation+0.136
but
Token but
Feature activation+1.058
there
Token there
Feature activation+0.962
were
Token were
Feature activation+0.476
some
Token some
Feature activation+0.105
deaths
Token deaths
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 1.913

appropriate
Token appropriate
Feature activation-0.007
Top resid features:
medical
Token medical
Feature activation+0.014
Top resid features:
care
Token care
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
You
Token You
Feature activation+0.008
Top resid features:
die
Token die
Feature activation+1.913
Top resid features:
...
Token...
Feature activation+0.023
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
cosmic
Token cosmic
Feature activation+0.000
Top resid features:
rays
Token rays
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.034
Top resid features:
death
Token death
Feature activation+0.668
Top resid features:
from
Token from
Feature activation+0.045
Top resid features:
being
Token being
Feature activation+0.042
Top resid features:
run
Token run
Feature activation+0.103
Top resid features:
over
Token over
Feature activation+0.728
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
First
TokenFirst
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
who
Token who
Feature activation+0.019
Top resid features:
is
Token is
Feature activation-0.052
Top resid features:
being
Token being
Feature activation+0.261
Top resid features:
killed
Token killed
Feature activation+1.609
Top resid features:
is
Token is
Feature activation+0.041
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
imm
Token imm
Feature activation+0.000
Top resid features:
aterial
Tokenaterial
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
somehow
Token somehow
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
loss
Token loss
Feature activation+0.045
Top resid features:
of
Token of
Feature activation-0.028
Top resid features:
life
Token life
Feature activation+1.727
Top resid features:
from
Token from
Feature activation+0.015
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ambush
Token ambush
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.008
Top resid features:
has
Token has
Feature activation+0.028
Top resid features:
been
Token been
Feature activation+0.095
Top resid features:
captured
Token captured
Feature activation+0.649
Top resid features:
or
Token or
Feature activation+0.079
Top resid features:
killed
Token killed
Feature activation+0.924
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
prompt
Token prompt
Feature activation+0.000
Top resid features:
journalists
Token journalists
Feature activation+0.000
Top resid features:
io
Tokenio
Feature activation-0.008
Top resid features:
Â
Token Â
Feature activation+0.013
Top resid features:
ĵ
Tokenĵ
Feature activation-0.005
Top resid features:
If
TokenIf
Feature activation+0.031
Top resid features:
we
Token we
Feature activation-0.009
Top resid features:
die
Token die
Feature activation+1.549
Top resid features:
,
Token,
Feature activation+0.190
Top resid features:
we
Token we
Feature activation+0.052
Top resid features:
want
Token want
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.002
Top resid features:
killing
Token killing
Feature activation+0.383
Top resid features:
4
Token 4
Feature activation+0.083
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
000
Token000
Feature activation+0.362
Top resid features:
people
Token people
Feature activation+0.872
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
official
Token official
Feature activation-0.006
Top resid features:
suggested
Token suggested
Feature activation+0.048
Top resid features:
his
Token his
Feature activation+0.035
Top resid features:
employees
Token employees
Feature activation+0.055
Top resid features:
commit
Token commit
Feature activation+0.158
Top resid features:
suicide
Token suicide
Feature activation+1.345
Top resid features:
if
Token if
Feature activation+0.101
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
unhappy
Token unhappy
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
eventually
Token eventually
Feature activation+0.043
Top resid features:
we
Token we
Feature activation+0.011
Top resid features:
will
Token will
Feature activation-0.075
Top resid features:
die
Token die
Feature activation+1.547
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.090
Top resid features:
that
Token that
Feature activation+0.040
Top resid features:
is
Token is
Feature activation-0.024
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
we
Token we
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
If
TokenIf
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
die
Token die
Feature activation+1.285
Top resid features:
anytime
Token anytime
Feature activation+0.285
Top resid features:
soon
Token soon
Feature activation-0.051
Top resid features:
,
Token,
Feature activation+0.089
Top resid features:
it
Token it
Feature activation+0.047
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
somehow
Token somehow
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
loss
Token loss
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
life
Token life
Feature activation+1.567
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ambush
Token ambush
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
I
TokenI
Feature activation+0.008
Top resid features:
dance
Token dance
Feature activation+0.260
Top resid features:
with
Token with
Feature activation+0.059
Top resid features:
death
Token death
Feature activation+1.277
Top resid features:
every
Token every
Feature activation+0.029
Top resid features:
day
Token day
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.004
Top resid features:
has
Token has
Feature activation+0.038
Top resid features:
been
Token been
Feature activation+0.128
Top resid features:
captured
Token captured
Feature activation+0.524
Top resid features:
or
Token or
Feature activation+0.068
Top resid features:
killed
Token killed
Feature activation+0.780
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
it
Token it
Feature activation+0.020
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
prompt
Token prompt
Feature activation+0.000
Top resid features:
journalists
Token journalists
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
if
Token if
Feature activation+0.012
Top resid features:
he
Token he
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+0.031
Top resid features:
been
Token been
Feature activation+0.094
Top resid features:
captured
Token captured
Feature activation+0.716
Top resid features:
or
Token or
Feature activation+0.039
Top resid features:
killed
Token killed
Feature activation+0.674
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
it
Token it
Feature activation+0.023
Top resid features:
would
Token would
Feature activation+0.017
Top resid features:
appropriate
Token appropriate
Feature activation-0.006
Top resid features:
medical
Token medical
Feature activation+0.017
Top resid features:
care
Token care
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
You
Token You
Feature activation+0.017
Top resid features:
die
Token die
Feature activation+1.024
Top resid features:
...
Token...
Feature activation+0.126
Top resid features:
because
Token because
Feature activation+0.163
Top resid features:
of
Token of
Feature activation+0.085
Top resid features:
cosmic
Token cosmic
Feature activation+0.000
Top resid features:
rays
Token rays
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.165
Top resid features:
you
Token you
Feature activation+0.027
Top resid features:
going
Token going
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
hell
Token hell
Feature activation+1.453
Top resid features:
?'
Token?'
Feature activation+0.035
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
morning
Token morning
Feature activation-0.047
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
I
Token I
Feature activation+0.015
Top resid features:
want
Token want
Feature activation+0.085
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
die
Token die
Feature activation+1.594
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
decide
Token decide
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
tried
Token tried
Feature activation+0.079
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
take
Token take
Feature activation+0.005
Top resid features:
his
Token his
Feature activation+0.054
Top resid features:
own
Token own
Feature activation+0.037
Top resid features:
life
Token life
Feature activation+1.399
Top resid features:
three
Token three
Feature activation+0.023
Top resid features:
times
Token times
Feature activation+0.031
Top resid features:
after
Token after
Feature activation-0.003
Top resid features:
suffering
Token suffering
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.054
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
use
Token use
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.031
Top resid features:
chemical
Token chemical
Feature activation+0.597
Top resid features:
weapons
Token weapons
Feature activation+1.092
Top resid features:
would
Token would
Feature activation-0.020
Top resid features:
be
Token be
Feature activation-0.012
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
red
Tokenred
Feature activation+0.000
Top resid features:
majority
Token majority
Feature activation+0.099
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
those
Token those
Feature activation-0.016
Top resid features:
cases
Token cases
Feature activation-0.022
Top resid features:
were
Token were
Feature activation-0.069
Top resid features:
suicide
Token suicide
Feature activation+1.615
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
but
Token but
Feature activation+0.002
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.06

Head 2: 0.03

Head 3: 0.08

Head 4: 0.06

Head 5: 0.10

Head 6: 0.05

Head 7: 0.40

Head 8: 0.06

Head 9: 0.02

Head 10: 0.03

Head 11: 0.04

Positive logits

deaths3.38

Deaths3.37

retribution3.10

murderer3.02

revenge3.00

murders2.94

death2.91

murderers2.91

gruesome2.90

murder2.86

death2.84

inflicted2.81

murdered2.80

corpses2.78

suicides2.74

punishments2.73

martyr2.72

Death2.72

punishment2.69

rape2.68

Negative logits

Preferences-2.30

icient-2.27

Commerce-2.22

UX-2.21

SEO-2.19

portfolios-2.11

Commerce-2.10

workspace-2.07

portfolio-2.05

iversity-2.03

Customer-2.03

folio-1.97

wcsstore-1.93

synergy-1.91

complimentary-1.91

config-1.91

productivity-1.90

competence-1.90

Product-1.87

icio-1.86

INTERVAL 1.935 - 2.150
CONTAINS 0.000%

INTERVAL 1.720 - 1.935
CONTAINS 0.000%

medical
Token medical
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.039
die
Token die
Feature activation+0.134
...
Token...
Feature activation+1.730
because
Token because
Feature activation+0.945
of
Token of
Feature activation+1.092
cosmic
Token cosmic
Feature activation+0.405
rays
Token rays
Feature activation+0.172
!
Token!
Feature activation+0.830

INTERVAL 1.505 - 1.720
CONTAINS 0.000%

INTERVAL 1.290 - 1.505
CONTAINS 0.000%

,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
killed
Token killed
Feature activation+0.593
is
Token is
Feature activation+1.343
not
Token not
Feature activation+0.563
imm
Token imm
Feature activation+0.275
aterial
Tokenaterial
Feature activation+0.674
to
Token to
Feature activation+0.208
how
Token how
Feature activation+0.282
death
Token death
Feature activation+0.187
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.164
run
Token run
Feature activation+0.136
over
Token over
Feature activation+0.000
.
Token.
Feature activation+1.484
In
Token In
Feature activation+0.535
fact
Token fact
Feature activation+0.745
,
Token,
Feature activation+0.793
he
Token he
Feature activation+0.966
was
Token was
Feature activation+0.837

INTERVAL 1.075 - 1.290
CONTAINS 0.002%

captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.605
killed
Token killed
Feature activation+0.294
,
Token,
Feature activation+1.247
it
Token it
Feature activation+1.110
would
Token would
Feature activation+1.106
prompt
Token prompt
Feature activation+0.574
journalists
Token journalists
Feature activation+0.077
and
Token and
Feature activation+0.000
friends
Token friends
Feature activation+0.000
to
Token to
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+1.111
from
Token from
Feature activation+1.270
an
Token an
Feature activation+0.935
ambush
Token ambush
Feature activation+0.111
in
Token in
Feature activation+0.008
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
die
Token die
Feature activation+0.118
anytime
Token anytime
Feature activation+0.491
soon
Token soon
Feature activation+0.644
,
Token,
Feature activation+0.496
it
Token it
Feature activation+1.152
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.939
probably
Token probably
Feature activation+0.744
likely
Token likely
Feature activation+0.915
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
dance
Token dance
Feature activation+0.000
with
Token with
Feature activation+0.000
death
Token death
Feature activation+0.000
every
Token every
Feature activation+1.111
day
Token day
Feature activation+0.742
,
Token,
Feature activation+0.752
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.007
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.039
die
Token die
Feature activation+0.134
...
Token...
Feature activation+1.730
because
Token because
Feature activation+0.945
of
Token of
Feature activation+1.092
cosmic
Token cosmic
Feature activation+0.405
rays
Token rays
Feature activation+0.172
!
Token!
Feature activation+0.830
Ċ
TokenĊ
Feature activation+0.637
Ċ
TokenĊ
Feature activation+0.381

INTERVAL 0.860 - 1.075
CONTAINS 0.006%

then
Token then
Feature activation+0.196
sad
Token sad
Feature activation+0.000
,
Token,
Feature activation+0.219
then
Token then
Feature activation+0.137
eaten
Token eaten
Feature activation+0.114
but
Token but
Feature activation+0.925
clearly
Token clearly
Feature activation+0.611
I
Token I
Feature activation+0.166
am
Token am
Feature activation+0.162
missing
Token missing
Feature activation+0.000
some
Token some
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
die
Token die
Feature activation+0.147
âĢĵ
Token âĢĵ
Feature activation+0.897
that
Token that
Feature activation+0.927
is
Token is
Feature activation+0.782
,
Token,
Feature activation+0.975
we
Token we
Feature activation+1.178
will
Token will
Feature activation+0.707
no
Token no
Feature activation+0.292
leave
Token leave
Feature activation+0.000
or
Token or
Feature activation+0.000
go
Token go
Feature activation+0.000
kill
Token kill
Feature activation+0.000
yourself
Token yourself
Feature activation+0.162
,
Token,
Feature activation+0.885
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.137
Br
Token Br
Feature activation+0.000
onson
Tokenonson
Feature activation+0.000
told
Token told
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
earth
Token earth
Feature activation+0.000
to
Token to
Feature activation+0.066
die
Token die
Feature activation+0.430
,
Token,
Feature activation+0.915
to
Token to
Feature activation+0.900
losing
Token losing
Feature activation+0.438
members
Token members
Feature activation+0.304
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.204
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.152
.
Token.
Feature activation+0.137
Every
Token Every
Feature activation+0.887
28
Token 28
Feature activation+0.000
Hours
Token Hours
Feature activation+0.152
by
Token by
Feature activation+0.000
Police
Token Police
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.147

INTERVAL 0.645 - 0.860
CONTAINS 0.014%

murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.530
to
Token to
Feature activation+0.476
genocide
Token genocide
Feature activation+0.120
.
Token.
Feature activation+0.541
And
Token And
Feature activation+0.730
so
Token so
Feature activation+0.304
in
Token in
Feature activation+0.125
this
Token this
Feature activation+0.000
way
Token way
Feature activation+0.240
,
Token,
Feature activation+0.441
landers
Tokenlanders
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
die
Token die
Feature activation+0.169
.
Token.
Feature activation+0.761
The
Token The
Feature activation+0.142
real
Token real
Feature activation+0.251
-
Token-
Feature activation+0.000
life
Tokenlife
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.241
the
Token the
Feature activation+0.139
eyes
Token eyes
Feature activation+0.275
to
Token to
Feature activation+0.288
achieve
Token achieve
Feature activation+0.646
that
Token that
Feature activation+0.153
.
Token.
Feature activation+0.344
It
Token It
Feature activation+0.294
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
crew
Token crew
Feature activation+0.000
man
Tokenman
Feature activation+0.000
to
Token to
Feature activation+0.000
die
Token die
Feature activation+0.158
suddenly
Token suddenly
Feature activation+0.506
,
Token,
Feature activation+0.704
height
Token height
Feature activation+0.657
ening
Tokenening
Feature activation+0.698
the
Token the
Feature activation+0.376
fear
Token fear
Feature activation+0.098
that
Token that
Feature activation+0.113
In
Token In
Feature activation+0.535
fact
Token fact
Feature activation+0.745
,
Token,
Feature activation+0.793
he
Token he
Feature activation+0.966
was
Token was
Feature activation+0.837
not
Token not
Feature activation+0.657
run
Token run
Feature activation+0.195
over
Token over
Feature activation+0.000
and
Token and
Feature activation+0.042
there
Token there
Feature activation+0.412
is
Token is
Feature activation+0.348

INTERVAL 0.430 - 0.645
CONTAINS 0.044%

don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
die
Token die
Feature activation+0.013
and
Token and
Feature activation+0.513
help
Token help
Feature activation+0.216
you
Token you
Feature activation+0.012
get
Token get
Feature activation+0.000
through
Token through
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.652
cell
Token cell
Feature activation+0.000
's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.484
which
Token which
Feature activation+0.384
is
Token is
Feature activation+0.510
"
Token "
Feature activation+0.350
a
Tokena
Feature activation+0.315
particular
Token particular
Feature activation+0.323
Achilles
Token Achilles
Feature activation+0.000
heel
Token heel
Feature activation+0.000
"
Token"
Feature activation+0.416
by
Token by
Feature activation+0.395
a
Token a
Feature activation+0.297
mob
Token mob
Feature activation+0.000
according
Token according
Feature activation+0.532
to
Token to
Feature activation+0.444
local
Token local
Feature activation+0.280
media
Token media
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+0.402
Inc
Token Inc
Feature activation+0.000
start
Token start
Feature activation+0.061
to
Token to
Feature activation+0.000
burn
Token burn
Feature activation+0.036
,
Token,
Feature activation+0.334
blow
Token blow
Feature activation+0.034
.
Token.
Feature activation+0.460
Ċ
TokenĊ
Feature activation+0.479
Ċ
TokenĊ
Feature activation+0.149
The
TokenThe
Feature activation+0.049
hardest
Token hardest
Feature activation+0.027
part
Token part
Feature activation+0.000
they
Token they
Feature activation+0.000
face
Token face
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
death
Token death
Feature activation+0.000
.
Token.
Feature activation+0.474
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Special
TokenSpecial
Feature activation+0.000
Features
Token Features
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.215 - 0.430
CONTAINS 0.147%

,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.390
"
Token "
Feature activation+0.630
Pretty
TokenPretty
Feature activation+0.347
wrong
Token wrong
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
ask
Token ask
Feature activation+0.000
should
Token should
Feature activation+0.000
you
Token you
Feature activation+0.000
return
Token return
Feature activation+0.000
fire
Token fire
Feature activation+0.034
!
Token!
Feature activation+0.466
This
Token This
Feature activation+0.336
will
Token will
Feature activation+0.360
stop
Token stop
Feature activation+0.206
you
Token you
Feature activation+0.225
from
Token from
Feature activation+0.273
going
Token going
Feature activation+0.109
be
Token be
Feature activation+0.000
be
Token be
Feature activation+0.000
headed
Tokenheaded
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.144
body
Token body
Feature activation+0.242
publicly
Token publicly
Feature activation+0.546
cruc
Token cruc
Feature activation+0.000
ified
Tokenified
Feature activation+0.000
.
Token.
Feature activation+0.620
https
Token https
Feature activation+0.000
boundary
Token boundary
Feature activation+0.000
will
Token will
Feature activation+0.000
cost
Token cost
Feature activation+0.000
them
Token them
Feature activation+0.000
their
Token their
Feature activation+0.000
lives
Token lives
Feature activation+0.323
.
Token.
Feature activation+0.579
In
Token In
Feature activation+0.243
this
Token this
Feature activation+0.197
issue
Token issue
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.089
She
Token She
Feature activation+0.132
almost
Token almost
Feature activation+0.000
died
Token died
Feature activation+0.060
.
Token.
Feature activation+0.342
She
Token She
Feature activation+0.331
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.188
in
Token in
Feature activation+0.010
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.215
CONTAINS 99.787%

,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
gl
Token gl
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
maximum
Token maximum
Feature activation+0.000
(
Token (
Feature activation+0.000
c
Tokenc
Feature activation+0.000
ollo
Tokenollo
Feature activation+0.000
qu
Tokenqu
Feature activation+0.000
A
TokenA
Feature activation+0.000
cop
Token cop
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
moisture
Token moisture
Feature activation+0.000
will
Token will
Feature activation+0.000
un
Token un
Feature activation+0.000
load
Tokenload
Feature activation+0.000
very
Token very
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
t
Tokent
Feature activation+0.000
t
Token t
Feature activation+0.000
amped
Tokenamped
Feature activation+0.000
down
Token down
Feature activation+0.000
their
Token their
Feature activation+0.000
aggress
Token aggress
Feature activation+0.000
iveness
Tokeniveness
Feature activation+0.000
with
Token with
Feature activation+0.000
free
Token free
Feature activation+0.000
agents
Token agents
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
in
Token in
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
showing
Token showing
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
arguments
Token arguments
Feature activation+0.000
."
Token."
Feature activation+0.000
"
Token"
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
are
Token are
Feature activation+0.000
proposing
Token proposing
Feature activation+0.000
today
Token today
Feature activation+0.000
were
Token were
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H6.7: (feature 7804)

TOP ACTIVATIONS
MAX = 1.531

the
Token the
Feature activation+0.000
summit
Token summit
Feature activation+0.000
cannot
Token cannot
Feature activation+0.032
be
Token be
Feature activation+0.410
held
Token held
Feature activation+0.438
without
Token without
Feature activation+1.531
all
Token all
Feature activation+0.420
the
Token the
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
(
Token (
Feature activation+0.043
heads
Tokenheads
Feature activation+0.000
at
Token at
Feature activation+0.000
Phot
Token Phot
Feature activation+0.000
ok
Tokenok
Feature activation+0.000
ina
Tokenina
Feature activation+0.000
2016
Token 2016
Feature activation+0.375
this
Token this
Feature activation+1.470
September
Token September
Feature activation+1.006
in
Token in
Feature activation+0.872
Cologne
Token Cologne
Feature activation+0.056
,
Token,
Feature activation+0.256
Germany
Token Germany
Feature activation+0.419
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.000
to
Token to
Feature activation+0.000
CP
Token CP
Feature activation+0.000
AC
TokenAC
Feature activation+1.196
in
Token in
Feature activation+1.404
which
Token which
Feature activation+0.582
he
Token he
Feature activation+0.482
says
Token says
Feature activation+0.447
he
Token he
Feature activation+0.695
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.283
Long
Token Long
Feature activation+0.571
Beach
Token Beach
Feature activation+0.376
,
Token,
Feature activation+0.303
California
Token California
Feature activation+0.725
October
Token October
Feature activation+1.372
22
Token 22
Feature activation+0.698
,
Token,
Feature activation+0.217
2008
Token 2008
Feature activation+0.356
.
Token.
Feature activation+0.818
RE
TokenRE
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.279
on
Token on
Feature activation+0.416
Dec
Token Dec
Feature activation+0.508
.
Token.
Feature activation+0.815
6
Token 6
Feature activation+0.468
.
Token.
Feature activation+1.322
Ċ
TokenĊ
Feature activation+0.205
Ċ
TokenĊ
Feature activation+0.287
G
TokenG
Feature activation+0.000
ram
Tokenram
Feature activation+0.000
my
Tokenmy
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.224
sources
Token sources
Feature activation+0.260
told
Token told
Feature activation+0.000
Reuters
Token Reuters
Feature activation+0.000
,
Token,
Feature activation+0.392
as
Token as
Feature activation+1.320
London
Token London
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000
Lady
Token Lady
Feature activation+0.066
Michelle
Token Michelle
Feature activation+0.000
Obama
Token Obama
Feature activation+0.063
in
Token in
Feature activation+0.265
an
Token an
Feature activation+0.868
effort
Token effort
Feature activation+1.317
to
Token to
Feature activation+0.693
encourage
Token encourage
Feature activation+0.149
companies
Token companies
Feature activation+0.000
to
Token to
Feature activation+0.000
hire
Token hire
Feature activation+0.000
to
Token to
Feature activation+0.000
Missouri
Token Missouri
Feature activation+0.000
on
Token on
Feature activation+0.110
Wednesday
Token Wednesday
Feature activation+0.000
as
Token as
Feature activation+0.474
part
Token part
Feature activation+1.310
of
Token of
Feature activation+0.957
an
Token an
Feature activation+0.855
ongoing
Token ongoing
Feature activation+0.432
effort
Token effort
Feature activation+0.301
to
Token to
Feature activation+0.154
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000
China
Token China
Feature activation+0.000
this
Token this
Feature activation+0.107
year
Token year
Feature activation+0.000
.
Token.
Feature activation+1.280
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FILE
TokenFILE
Feature activation+0.000
PHOTO
Token PHOTO
Feature activation+0.000
:
Token:
Feature activation+0.000
's
Token's
Feature activation+0.000
presence
Token presence
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
PAX
Token PAX
Feature activation+0.116
Prime
Token Prime
Feature activation+1.267
exp
Token exp
Feature activation+0.561
o
Tokeno
Feature activation+0.733
,
Token,
Feature activation+0.177
Valve
Token Valve
Feature activation+0.000
says
Token says
Feature activation+0.000
an
Token an
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
at
Token at
Feature activation+0.000
Cinema
Token Cinema
Feature activation+0.000
Con
Token Con
Feature activation+0.000
this
Token this
Feature activation+1.253
month
Token month
Feature activation+1.164
to
Token to
Feature activation+1.167
get
Token get
Feature activation+1.189
theater
Token theater
Feature activation+0.147
owners
Token owners
Feature activation+0.429
in
Token in
Feature activation+0.935
New
Token New
Feature activation+0.325
York
Token York
Feature activation+0.672
raised
Token raised
Feature activation+0.874
$
Token $
Feature activation+0.541
26
Token26
Feature activation+1.230
million
Token million
Feature activation+0.624
,
Token,
Feature activation+0.187
Y
Token Y
Feature activation+0.218
net
Tokennet
Feature activation+0.000
News
Token News
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.332
the
Token the
Feature activation+0.033
event
Token event
Feature activation+0.354
in
Token in
Feature activation+0.491
hopes
Token hopes
Feature activation+1.228
of
Token of
Feature activation+0.557
using
Token using
Feature activation+0.828
his
Token his
Feature activation+0.351
star
Token star
Feature activation+0.000
power
Token power
Feature activation+0.000
and
Token and
Feature activation+0.170
Leeds
Token Leeds
Feature activation+0.000
festivals
Token festivals
Feature activation+0.000
last
Token last
Feature activation+1.032
year
Token year
Feature activation+0.774
.
Token.
Feature activation+1.218
Ċ
TokenĊ
Feature activation+0.217
Ċ
TokenĊ
Feature activation+0.353
The
TokenThe
Feature activation+0.194
young
Token young
Feature activation+0.000
band
Token band
Feature activation+0.000
game
Tokengame
Feature activation+0.000
warm
Token warm
Feature activation+0.101
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.486
together
Token together
Feature activation+0.337
.
Token.
Feature activation+1.215
When
Token When
Feature activation+0.430
Bob
Token Bob
Feature activation+0.054
seriously
Token seriously
Feature activation+0.000
injured
Token injured
Feature activation+0.000
a
Token a
Feature activation+0.000
in
Token in
Feature activation+0.383
Sweden
Token Sweden
Feature activation+0.593
.
Token.
Feature activation+1.097
Unfortunately
Token Unfortunately
Feature activation+0.916
,
Token,
Feature activation+1.082
it
Token it
Feature activation+1.212
was
Token was
Feature activation+0.922
the
Token the
Feature activation+0.437
last
Token last
Feature activation+0.874
gig
Token gig
Feature activation+0.385
for
Token for
Feature activation+0.684
don
Token don
Feature activation+0.310
't
Token't
Feature activation+0.324
know
Token know
Feature activation+0.143
if
Token if
Feature activation+0.578
he
Token he
Feature activation+0.569
did
Token did
Feature activation+1.207
or
Token or
Feature activation+0.185
not
Token not
Feature activation+0.095
âĢĶ
Token âĢĶ
Feature activation+0.000
he
Token he
Feature activation+0.305
wasn
Token wasn
Feature activation+0.269
gives
Token gives
Feature activation+0.000
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.000
to
Token to
Feature activation+0.000
CP
Token CP
Feature activation+0.000
AC
TokenAC
Feature activation+1.196
in
Token in
Feature activation+1.404
which
Token which
Feature activation+0.582
he
Token he
Feature activation+0.482
says
Token says
Feature activation+0.447
he
Token he
Feature activation+0.695
Cinema
Token Cinema
Feature activation+0.000
Con
Token Con
Feature activation+0.000
this
Token this
Feature activation+1.253
month
Token month
Feature activation+1.164
to
Token to
Feature activation+1.167
get
Token get
Feature activation+1.189
theater
Token theater
Feature activation+0.147
owners
Token owners
Feature activation+0.429
hyp
Token hyp
Feature activation+0.014
ed
Tokened
Feature activation+0.051
up
Token up
Feature activation+0.000
at
Token at
Feature activation+0.000
Cinema
Token Cinema
Feature activation+0.000
Con
Token Con
Feature activation+0.000
this
Token this
Feature activation+1.253
month
Token month
Feature activation+1.164
to
Token to
Feature activation+1.167
get
Token get
Feature activation+1.189
theater
Token theater
Feature activation+0.147
owners
Token owners
Feature activation+0.429
hyp
Token hyp
Feature activation+0.014
ed
Tokened
Feature activation+0.051

Top DFA by src position
MAX = 1.796

arc
Tokenarc
Feature activation+0.004
Top resid features:
)
Token)
Feature activation+0.015
Top resid features:
charter
Token charter
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
summit
Token summit
Feature activation+1.106
Top resid features:
cannot
Token cannot
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
held
Token held
Feature activation+0.830
Top resid features:
without
Token without
Feature activation-0.013
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
unveiled
Token unveiled
Feature activation+0.124
Top resid features:
at
Token at
Feature activation+0.056
Top resid features:
Phot
Token Phot
Feature activation+0.067
Top resid features:
ok
Tokenok
Feature activation+0.000
Top resid features:
ina
Tokenina
Feature activation+0.026
Top resid features:
2016
Token 2016
Feature activation+1.677
Top resid features:
this
Token this
Feature activation-0.030
Top resid features:
September
Token September
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Cologne
Token Cologne
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
gives
Token gives
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
speech
Token speech
Feature activation+0.061
Top resid features:
to
Token to
Feature activation+0.048
Top resid features:
CP
Token CP
Feature activation+0.304
Top resid features:
AC
TokenAC
Feature activation+1.626
Top resid features:
in
Token in
Feature activation-0.154
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
addresses
Token addresses
Feature activation+0.170
Top resid features:
The
Token The
Feature activation+0.030
Top resid features:
Women
Token Women
Feature activation-0.004
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
Conference
Token Conference
Feature activation+0.473
Top resid features:
2008
Token 2008
Feature activation+0.691
Top resid features:
in
Token in
Feature activation+0.235
Top resid features:
Long
Token Long
Feature activation+0.005
Top resid features:
Beach
Token Beach
Feature activation+0.121
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
California
Token California
Feature activation+0.014
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
singer
Token singer
Feature activation+0.046
Top resid features:
was
Token was
Feature activation+0.070
Top resid features:
due
Token due
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.060
Top resid features:
perform
Token perform
Feature activation+0.481
Top resid features:
at
Token at
Feature activation+0.450
Top resid features:
this
Token this
Feature activation+0.073
Top resid features:
year
Token year
Feature activation+0.053
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
Friends
Token Friends
Feature activation+0.022
Top resid features:
Prime
Token Prime
Feature activation+0.003
Top resid features:
Minister
Token Minister
Feature activation+0.002
Top resid features:
Theresa
Token Theresa
Feature activation-0.001
Top resid features:
May
Token May
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.463
Top resid features:
attend
Token attend
Feature activation+0.495
Top resid features:
a
Token a
Feature activation+0.095
Top resid features:
major
Token major
Feature activation+0.063
Top resid features:
summit
Token summit
Feature activation+0.187
Top resid features:
in
Token in
Feature activation+0.069
Top resid features:
May
Token May
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.151
Top resid features:
White
Token White
Feature activation+0.013
Top resid features:
House
Token House
Feature activation+0.126
Top resid features:
to
Token to
Feature activation+0.060
Top resid features:
an
Token an
Feature activation+0.091
Top resid features:
event
Token event
Feature activation+0.773
Top resid features:
hosted
Token hosted
Feature activation+0.152
Top resid features:
by
Token by
Feature activation+0.174
Top resid features:
First
Token First
Feature activation+0.005
Top resid features:
Lady
Token Lady
Feature activation+0.041
Top resid features:
Michelle
Token Michelle
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.001
Top resid features:
President
TokenPresident
Feature activation-0.007
Top resid features:
Trump
Token Trump
Feature activation-0.021
Top resid features:
will
Token will
Feature activation+0.054
Top resid features:
travel
Token travel
Feature activation+0.557
Top resid features:
to
Token to
Feature activation+0.745
Top resid features:
Missouri
Token Missouri
Feature activation+0.211
Top resid features:
on
Token on
Feature activation+0.159
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.085
Top resid features:
as
Token as
Feature activation+0.015
Top resid features:
part
Token part
Feature activation-0.014
Top resid features:
Prime
Token Prime
Feature activation+0.006
Top resid features:
Minister
Token Minister
Feature activation+0.007
Top resid features:
Theresa
Token Theresa
Feature activation-0.005
Top resid features:
May
Token May
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.273
Top resid features:
attend
Token attend
Feature activation+0.432
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
major
Token major
Feature activation+0.053
Top resid features:
summit
Token summit
Feature activation+0.175
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
May
Token May
Feature activation+0.021
Top resid features:
company
Token company
Feature activation-0.003
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
presence
Token presence
Feature activation+0.004
Top resid features:
at
Token at
Feature activation-0.061
Top resid features:
the
Token the
Feature activation-0.045
Top resid features:
PAX
Token PAX
Feature activation+1.796
Top resid features:
Prime
Token Prime
Feature activation+0.104
Top resid features:
exp
Token exp
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Valve
Token Valve
Feature activation+0.000
Top resid features:
making
Token making
Feature activation-0.017
Top resid features:
an
Token an
Feature activation-0.006
Top resid features:
appearance
Token appearance
Feature activation+0.046
Top resid features:
at
Token at
Feature activation+0.228
Top resid features:
Cinema
Token Cinema
Feature activation+0.295
Top resid features:
Con
Token Con
Feature activation+1.323
Top resid features:
this
Token this
Feature activation-0.131
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
theater
Token theater
Feature activation+0.000
Top resid features:
F
TokenF
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.007
Top resid features:
one
Tokenone
Feature activation+0.004
Top resid features:
recent
Token recent
Feature activation+0.004
Top resid features:
g
Token g
Feature activation+0.013
Top resid features:
ala
Tokenala
Feature activation+1.161
Top resid features:
in
Token in
Feature activation+0.162
Top resid features:
New
Token New
Feature activation+0.006
Top resid features:
York
Token York
Feature activation+0.028
Top resid features:
raised
Token raised
Feature activation+0.097
Top resid features:
$
Token $
Feature activation+0.046
Top resid features:
borough
Tokenborough
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.001
Top resid features:
has
Tokenhas
Feature activation+0.005
Top resid features:
chosen
Token chosen
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
attend
Token attend
Feature activation+0.780
Top resid features:
the
Token the
Feature activation+0.256
Top resid features:
event
Token event
Feature activation+0.353
Top resid features:
in
Token in
Feature activation+0.181
Top resid features:
hopes
Token hopes
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
who
Token who
Feature activation+0.033
Top resid features:
invited
Token invited
Feature activation+0.062
Top resid features:
them
Token them
Feature activation+0.051
Top resid features:
to
Token to
Feature activation+0.162
Top resid features:
play
Token play
Feature activation+0.646
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
Reading
Token Reading
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
Leeds
Token Leeds
Feature activation+0.023
Top resid features:
festivals
Token festivals
Feature activation+0.423
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
game
Tokengame
Feature activation+0.446
Top resid features:
warm
Token warm
Feature activation+0.213
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
up
Tokenup
Feature activation+0.375
Top resid features:
together
Token together
Feature activation+0.519
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
When
Token When
Feature activation+0.000
Top resid features:
Bob
Token Bob
Feature activation+0.000
Top resid features:
seriously
Token seriously
Feature activation+0.000
Top resid features:
injured
Token injured
Feature activation+0.000
Top resid features:
1991
Token 1991
Feature activation-0.002
Top resid features:
K
Token K
Feature activation+0.005
Top resid features:
ated
Tokenated
Feature activation+0.006
Top resid features:
ra
Tokenra
Feature activation+0.004
Top resid features:
played
Token played
Feature activation+0.182
Top resid features:
at
Token at
Feature activation+0.391
Top resid features:
"
Token "
Feature activation+0.106
Top resid features:
Balt
TokenBalt
Feature activation+0.004
Top resid features:
ic
Tokenic
Feature activation+0.003
Top resid features:
Sea
Token Sea
Feature activation-0.005
Top resid features:
Music
Token Music
Feature activation+0.036
Top resid features:
You
TokenYou
Feature activation+0.006
Top resid features:
know
Token know
Feature activation-0.003
Top resid features:
Bernie
Token Bernie
Feature activation+0.028
Top resid features:
wanted
Token wanted
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.087
Top resid features:
debate
Token debate
Feature activation+1.307
Top resid features:
me
Token me
Feature activation+0.026
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
don
Token don
Feature activation+0.003
Top resid features:
't
Token't
Feature activation-0.006
Top resid features:
gives
Token gives
Feature activation-0.009
Top resid features:
a
Token a
Feature activation-0.009
Top resid features:
speech
Token speech
Feature activation+0.080
Top resid features:
to
Token to
Feature activation-0.229
Top resid features:
CP
Token CP
Feature activation+0.211
Top resid features:
AC
TokenAC
Feature activation+1.621
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
making
Token making
Feature activation-0.019
Top resid features:
an
Token an
Feature activation-0.005
Top resid features:
appearance
Token appearance
Feature activation+0.101
Top resid features:
at
Token at
Feature activation+0.189
Top resid features:
Cinema
Token Cinema
Feature activation+0.295
Top resid features:
Con
Token Con
Feature activation+0.995
Top resid features:
this
Token this
Feature activation+0.049
Top resid features:
month
Token month
Feature activation+0.121
Top resid features:
to
Token to
Feature activation-0.033
Top resid features:
get
Token get
Feature activation-0.016
Top resid features:
theater
Token theater
Feature activation+0.000
Top resid features:
making
Token making
Feature activation-0.022
Top resid features:
an
Token an
Feature activation-0.007
Top resid features:
appearance
Token appearance
Feature activation-0.033
Top resid features:
at
Token at
Feature activation+0.100
Top resid features:
Cinema
Token Cinema
Feature activation+0.274
Top resid features:
Con
Token Con
Feature activation+1.379
Top resid features:
this
Token this
Feature activation+0.023
Top resid features:
month
Token month
Feature activation+0.034
Top resid features:
to
Token to
Feature activation-0.065
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
theater
Token theater
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.05

Head 3: 0.09

Head 4: 0.08

Head 5: 0.10

Head 6: 0.05

Head 7: 0.40

Head 8: 0.05

Head 9: 0.01

Head 10: 0.02

Head 11: 0.03

Positive logits

attendees3.46

attendance3.36

rehearsal3.12

organizers3.08

Attend3.02

organisers3.00

festivities2.99

invitations2.99

Tickets2.86

festival2.83

venue2.80

Concert2.77

invitation2.76

VIP2.75

festive2.74

guests2.73

Tickets2.72

invited2.71

scheduled2.71

concerts2.70

Negative logits

hardness-2.33

エル-2.15

Inher-2.06

resists-2.01

Weak-2.00

etimes-1.88

inherit-1.87

ulnerability-1.87

Serial-1.86

Attributes-1.86

-1.85

immutable-1.82

orius-1.82

Diseases-1.82

crim-1.81

サーティワン-1.81

Dictionary-1.81

traits-1.79

weaken-1.78

Sharp-1.77

INTERVAL 1.378 - 1.531
CONTAINS 0.000%

the
Token the
Feature activation+0.000
summit
Token summit
Feature activation+0.000
cannot
Token cannot
Feature activation+0.032
be
Token be
Feature activation+0.410
held
Token held
Feature activation+0.438
without
Token without
Feature activation+1.531
all
Token all
Feature activation+0.420
the
Token the
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
(
Token (
Feature activation+0.043
heads
Tokenheads
Feature activation+0.000
at
Token at
Feature activation+0.000
Phot
Token Phot
Feature activation+0.000
ok
Tokenok
Feature activation+0.000
ina
Tokenina
Feature activation+0.000
2016
Token 2016
Feature activation+0.375
this
Token this
Feature activation+1.470
September
Token September
Feature activation+1.006
in
Token in
Feature activation+0.872
Cologne
Token Cologne
Feature activation+0.056
,
Token,
Feature activation+0.256
Germany
Token Germany
Feature activation+0.419
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.000
to
Token to
Feature activation+0.000
CP
Token CP
Feature activation+0.000
AC
TokenAC
Feature activation+1.196
in
Token in
Feature activation+1.404
which
Token which
Feature activation+0.582
he
Token he
Feature activation+0.482
says
Token says
Feature activation+0.447
he
Token he
Feature activation+0.695
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.225 - 1.378
CONTAINS 0.001%

in
Token in
Feature activation+0.283
Long
Token Long
Feature activation+0.571
Beach
Token Beach
Feature activation+0.376
,
Token,
Feature activation+0.303
California
Token California
Feature activation+0.725
October
Token October
Feature activation+1.372
22
Token 22
Feature activation+0.698
,
Token,
Feature activation+0.217
2008
Token 2008
Feature activation+0.356
.
Token.
Feature activation+0.818
RE
TokenRE
Feature activation+0.000
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000
China
Token China
Feature activation+0.000
this
Token this
Feature activation+0.107
year
Token year
Feature activation+0.000
.
Token.
Feature activation+1.280
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FILE
TokenFILE
Feature activation+0.000
PHOTO
Token PHOTO
Feature activation+0.000
:
Token:
Feature activation+0.000
an
Token an
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
at
Token at
Feature activation+0.000
Cinema
Token Cinema
Feature activation+0.000
Con
Token Con
Feature activation+0.000
this
Token this
Feature activation+1.253
month
Token month
Feature activation+1.164
to
Token to
Feature activation+1.167
get
Token get
Feature activation+1.189
theater
Token theater
Feature activation+0.147
owners
Token owners
Feature activation+0.429
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.332
the
Token the
Feature activation+0.033
event
Token event
Feature activation+0.354
in
Token in
Feature activation+0.491
hopes
Token hopes
Feature activation+1.228
of
Token of
Feature activation+0.557
using
Token using
Feature activation+0.828
his
Token his
Feature activation+0.351
star
Token star
Feature activation+0.000
power
Token power
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.224
sources
Token sources
Feature activation+0.260
told
Token told
Feature activation+0.000
Reuters
Token Reuters
Feature activation+0.000
,
Token,
Feature activation+0.392
as
Token as
Feature activation+1.320
London
Token London
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000

INTERVAL 1.072 - 1.225
CONTAINS 0.002%

]
Token]
Feature activation+0.000
"
Token "
Feature activation+0.343
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.065
hand
Token hand
Feature activation+1.122
his
Token his
Feature activation+0.171
discourse
Token discourse
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
don
Token don
Feature activation+0.310
't
Token't
Feature activation+0.324
know
Token know
Feature activation+0.143
if
Token if
Feature activation+0.578
he
Token he
Feature activation+0.569
did
Token did
Feature activation+1.207
or
Token or
Feature activation+0.185
not
Token not
Feature activation+0.095
âĢĶ
Token âĢĶ
Feature activation+0.000
he
Token he
Feature activation+0.305
wasn
Token wasn
Feature activation+0.269
bash
Token bash
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.493
the
Token the
Feature activation+0.161
same
Token same
Feature activation+1.111
night
Token night
Feature activation+0.269
the
Token the
Feature activation+0.040
Hide
Token Hide
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.284
Boss
Token Boss
Feature activation+0.008
ert
Tokenert
Feature activation+0.000
said
Token said
Feature activation+0.702
.
Token.
Feature activation+1.092
Ċ
TokenĊ
Feature activation+0.075
Ċ
TokenĊ
Feature activation+0.036
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
gives
Token gives
Feature activation+0.000
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.000
to
Token to
Feature activation+0.000
CP
Token CP
Feature activation+0.000
AC
TokenAC
Feature activation+1.196
in
Token in
Feature activation+1.404
which
Token which
Feature activation+0.582
he
Token he
Feature activation+0.482
says
Token says
Feature activation+0.447
he
Token he
Feature activation+0.695

INTERVAL 0.919 - 1.072
CONTAINS 0.004%

speech
Token speech
Feature activation+0.000
on
Token on
Feature activation+0.000
June
Token June
Feature activation+0.679
13
Token 13
Feature activation+0.366
,
Token,
Feature activation+0.615
but
Token but
Feature activation+1.053
decided
Token decided
Feature activation+0.901
to
Token to
Feature activation+0.473
postpone
Token postpone
Feature activation+0.433
it
Token it
Feature activation+0.174
after
Token after
Feature activation+0.105
Valley
Token Valley
Feature activation+0.035
Music
Token Music
Feature activation+0.000
and
Token and
Feature activation+0.161
Arts
Token Arts
Feature activation+0.404
Festival
Token Festival
Feature activation+0.467
in
Token in
Feature activation+0.921
2008
Token 2008
Feature activation+0.821
,
Token,
Feature activation+0.586
and
Token and
Feature activation+0.560
was
Token was
Feature activation+0.585
taken
Token taken
Feature activation+0.341
exercises
Token exercises
Feature activation+0.000
that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.007
take
Token take
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.926
according
Token according
Feature activation+1.050
to
Token to
Feature activation+1.094
their
Token their
Feature activation+0.345
own
Token own
Feature activation+0.648
maps
Token maps
Feature activation+0.065
sold
Token sold
Feature activation+0.868
out
Token out
Feature activation+0.310
for
Token for
Feature activation+0.606
2
Token 2
Feature activation+0.610
weeks
Token weeks
Feature activation+0.601
now
Token now
Feature activation+0.977
,
Token,
Feature activation+0.647
with
Token with
Feature activation+0.863
participation
Token participation
Feature activation+0.034
from
Token from
Feature activation+0.000
many
Token many
Feature activation+0.163
the
Token the
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
and
Token and
Feature activation+0.170
Leeds
Token Leeds
Feature activation+0.000
festivals
Token festivals
Feature activation+0.000
last
Token last
Feature activation+1.032
year
Token year
Feature activation+0.774
.
Token.
Feature activation+1.218
Ċ
TokenĊ
Feature activation+0.217
Ċ
TokenĊ
Feature activation+0.353
The
TokenThe
Feature activation+0.194

INTERVAL 0.765 - 0.919
CONTAINS 0.010%

i
Tokeni
Feature activation+0.000
O
TokenO
Feature activation+0.000
meet
Token meet
Feature activation+0.053
up
Tokenup
Feature activation+0.274
this
Token this
Feature activation+0.719
past
Token past
Feature activation+0.860
Saturday
Token Saturday
Feature activation+0.316
was
Token was
Feature activation+0.805
a
Token a
Feature activation+0.745
lot
Token lot
Feature activation+0.645
of
Token of
Feature activation+0.764
Mississippi
Token Mississippi
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
gig
Token gig
Feature activation+0.248
.
Token.
Feature activation+0.805
As
Token As
Feature activation+0.399
they
Token they
Feature activation+0.194
arrived
Token arrived
Feature activation+0.024
at
Token at
Feature activation+0.049
the
Token the
Feature activation+0.040
was
Token was
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.868
get
Token get
Feature activation+0.848
drunk
Token drunk
Feature activation+0.175
,
Token,
Feature activation+0.091
and
Token and
Feature activation+0.261
make
Token make
Feature activation+0.191
conducted
Token conducted
Feature activation+0.020
an
Token an
Feature activation+0.000
annual
Token annual
Feature activation+0.000
military
Token military
Feature activation+0.000
parade
Token parade
Feature activation+0.122
,
Token,
Feature activation+0.777
featuring
Token featuring
Feature activation+0.165
a
Token a
Feature activation+0.000
display
Token display
Feature activation+0.000
of
Token of
Feature activation+0.000
missiles
Token missiles
Feature activation+0.000
a
Token a
Feature activation+0.000
march
Token march
Feature activation+0.000
,
Token,
Feature activation+0.104
was
Token was
Feature activation+0.526
part
Token part
Feature activation+0.269
of
Token of
Feature activation+0.886
a
Token a
Feature activation+0.563
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Power
TokenPower
Feature activation+0.000
Up
Token Up
Feature activation+0.000

INTERVAL 0.612 - 0.765
CONTAINS 0.020%

you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
Matt
Token Matt
Feature activation+0.000
,''
Token,''
Feature activation+0.438
he
Token he
Feature activation+0.333
said
Token said
Feature activation+0.640
with
Token with
Feature activation+0.314
a
Token a
Feature activation+0.000
firm
Token firm
Feature activation+0.000
handshake
Token handshake
Feature activation+0.000
.
Token.
Feature activation+0.328
College
Token College
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
event
Token event
Feature activation+0.000
on
Token on
Feature activation+0.000
campus
Token campus
Feature activation+0.000
.
Token.
Feature activation+0.690
Ċ
TokenĊ
Feature activation+0.327
Ċ
TokenĊ
Feature activation+0.388
The
TokenThe
Feature activation+0.199
CR
Token CR
Feature activation+0.000
chapter
Token chapter
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
added
Token added
Feature activation+0.342
Next
Token Next
Feature activation+0.000
Gen
TokenGen
Feature activation+0.000
events
Token events
Feature activation+0.075
onto
Token onto
Feature activation+0.625
the
Token the
Feature activation+0.794
official
Token official
Feature activation+0.781
calendar
Token calendar
Feature activation+0.309
,
Token,
Feature activation+0.000
bypass
Token bypass
Feature activation+0.000
Cheney
Token Cheney
Feature activation+0.000
invited
Token invited
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
once
Token once
Feature activation+0.617
.
Token.
Feature activation+0.862
Mrs
Token Mrs
Feature activation+0.242
.
Token.
Feature activation+0.000
Cheney
Token Cheney
Feature activation+0.234
served
Token served
Feature activation+0.243
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
works
Token works
Feature activation+0.000
on
Token on
Feature activation+0.000
sets
Token sets
Feature activation+0.000
,
Token,
Feature activation+0.625
both
Token both
Feature activation+0.017
commercial
Token commercial
Feature activation+0.135
and
Token and
Feature activation+0.000
editorial
Token editorial
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.459 - 0.612
CONTAINS 0.038%

oct
Token oct
Feature activation+0.000
ober
Tokenober
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ests
Tokenests
Feature activation+0.000
,
Token,
Feature activation+0.106
and
Token and
Feature activation+0.499
other
Token other
Feature activation+1.044
huge
Token huge
Feature activation+0.704
beer
Token beer
Feature activation+0.000
events
Token events
Feature activation+0.000
throughout
Token throughout
Feature activation+0.239
locker
Token locker
Feature activation+0.000
room
Token room
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
event
Token event
Feature activation+0.457
.
Token.
Feature activation+0.559
Ċ
TokenĊ
Feature activation+0.388
Ċ
TokenĊ
Feature activation+0.385
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.041
followed
Token followed
Feature activation+0.331
by
Token by
Feature activation+0.249
a
Token a
Feature activation+0.000
march
Token march
Feature activation+0.000
,
Token,
Feature activation+0.104
was
Token was
Feature activation+0.526
part
Token part
Feature activation+0.269
of
Token of
Feature activation+0.886
a
Token a
Feature activation+0.563
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
had
Token had
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
class
Token class
Feature activation+0.000
earlier
Token earlier
Feature activation+0.462
that
Token that
Feature activation+0.058
semester
Token semester
Feature activation+0.152
and
Token and
Feature activation+0.155
talked
Token talked
Feature activation+0.000
about
Token about
Feature activation+0.000
up
Tokenup
Feature activation+0.000
which
Token which
Feature activation+0.613
I
Token I
Feature activation+0.770
'll
Token'll
Feature activation+0.488
be
Token be
Feature activation+0.656
attending
Token attending
Feature activation+0.538
.
Token.
Feature activation+0.974
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
guide
Token guide
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.306 - 0.459
CONTAINS 0.091%

a
Token a
Feature activation+0.000
cast
Token cast
Feature activation+0.000
party
Token party
Feature activation+0.108
screening
Token screening
Feature activation+0.228
,
Token,
Feature activation+1.027
the
Token the
Feature activation+0.313
film
Token film
Feature activation+0.028
sat
Token sat
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
shelf
Token shelf
Feature activation+0.000
at
Token at
Feature activation+0.231
the
Token the
Feature activation+0.169
World
Token World
Feature activation+0.000
Health
Token Health
Feature activation+0.000
Organization
Token Organization
Feature activation+0.000
.
Token.
Feature activation+0.356
Ċ
TokenĊ
Feature activation+0.007
Ċ
TokenĊ
Feature activation+0.104
Un
TokenUn
Feature activation+0.000
able
Tokenable
Feature activation+0.007
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.107
We
TokenWe
Feature activation+0.335
wanted
Token wanted
Feature activation+0.712
it
Token it
Feature activation+0.419
to
Token to
Feature activation+0.199
be
Token be
Feature activation+0.180
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
at
Token at
Feature activation+0.386
the
Token the
Feature activation+0.295
Washington
Token Washington
Feature activation+0.009
Convention
Token Convention
Feature activation+0.000
Center
Token Center
Feature activation+0.211
a
Token a
Feature activation+0.323
few
Token few
Feature activation+0.453
blocks
Token blocks
Feature activation+0.129
away
Token away
Feature activation+0.311
.
Token.
Feature activation+0.503
âĢ
Token âĢ
Feature activation+0.000
A
TokenA
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
April
Token April
Feature activation+0.265
25
Token 25
Feature activation+0.000
.
Token.
Feature activation+0.444
The
Token The
Feature activation+0.268
game
Token game
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
played
Token played
Feature activation+0.000

INTERVAL 0.153 - 0.306
CONTAINS 0.204%

against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
despised
Token despised
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
Canucks
Token Canucks
Feature activation+0.000
.
Token.
Feature activation+0.289
Boston
Token Boston
Feature activation+0.000
lost
Token lost
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
two
Token two
Feature activation+0.000
the
Token the
Feature activation+0.000
protest
Token protest
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
and
Token and
Feature activation+0.183
plan
Token plan
Feature activation+0.207
to
Token to
Feature activation+0.220
return
Token return
Feature activation+0.041
to
Token to
Feature activation+0.000
Madison
Token Madison
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
and
Token and
Feature activation+0.000
studying
Token studying
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.160
Ċ
TokenĊ
Feature activation+0.078
The
TokenThe
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
also
Token also
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
Judith
Token Judith
Feature activation+0.000
Crow
Token Crow
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
,
Token,
Feature activation+0.000
shook
Token shook
Feature activation+0.000
hands
Token hands
Feature activation+0.306
with
Token with
Feature activation+0.650
A
Token A
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
is
Tokenis
Feature activation+0.000
'
Token'
Feature activation+0.110
Werner
Token Werner
Feature activation+0.000
Herz
Token Herz
Feature activation+0.000
og
Tokenog
Feature activation+0.019
in
Token in
Feature activation+0.222
person
Token person
Feature activation+0.359
at
Token at
Feature activation+0.163
varying
Token varying
Feature activation+0.165
locations
Token locations
Feature activation+0.426
and
Token and
Feature activation+0.250
at
Token at
Feature activation+0.000
inf
Token inf
Feature activation+0.040

INTERVAL 0.000 - 0.153
CONTAINS 99.631%

cent
Tokencent
Feature activation+0.000
individual
Token individual
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
by
Token by
Feature activation+0.000
pub
Token pub
Feature activation+0.000
escent
Tokenescent
Feature activation+0.000
or
Token or
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
each
Token each
Feature activation+0.000
received
Token received
Feature activation+0.000
70
Token 70
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
votes
Token votes
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
early
Token early
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
on
Token on
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
report
Token report
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
earth
Token earth
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
in
Token in
Feature activation+0.000
force
Token force
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
people
Token people
Feature activation+0.000
standing
Token standing
Feature activation+0.000
behind
Token behind
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Sometimes
TokenSometimes
Feature activation+0.000
in
Token in
Feature activation+0.000
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
how
Token how
Feature activation+0.000
you
Token you
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H6.7: (feature 5658)

TOP ACTIVATIONS
MAX = 1.981

though
Token though
Feature activation+0.000
13
Token 13
Feature activation+0.137
.
Token.
Feature activation+0.225
5
Token5
Feature activation+0.114
percent
Token percent
Feature activation+1.043
is
Token is
Feature activation+1.981
just
Token just
Feature activation+1.837
3
Token 3
Feature activation+0.628
percentage
Token percentage
Feature activation+0.302
points
Token points
Feature activation+0.755
higher
Token higher
Feature activation+0.894
8
Token 8
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.667
down
Token down
Feature activation+1.841
from
Token from
Feature activation+1.280
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
percent
Token percent
Feature activation+0.000
13
Token 13
Feature activation+0.137
.
Token.
Feature activation+0.225
5
Token5
Feature activation+0.114
percent
Token percent
Feature activation+1.043
is
Token is
Feature activation+1.981
just
Token just
Feature activation+1.837
3
Token 3
Feature activation+0.628
percentage
Token percentage
Feature activation+0.302
points
Token points
Feature activation+0.755
higher
Token higher
Feature activation+0.894
than
Token than
Feature activation+0.324
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
a
Token a
Feature activation+0.602
non
Token non
Feature activation+0.000
background
Token background
Feature activation+0.000
is
Token is
Feature activation+0.000
162
Token 162
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+1.570
means
Token means
Feature activation+1.744
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
around
Token around
Feature activation+0.000
850
Token 850
Feature activation+0.000
MW
Token MW
Feature activation+0.000
).
Token).
Feature activation+0.584
Which
Token Which
Feature activation+0.922
is
Token is
Feature activation+1.727
why
Token why
Feature activation+0.999
it
Token it
Feature activation+0.550
's
Token's
Feature activation+0.363
good
Token good
Feature activation+0.236
news
Token news
Feature activation+0.111
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
a
Token a
Feature activation+0.602
.
Token.
Feature activation+0.634
That
Token That
Feature activation+1.192
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.453
nearly
Token nearly
Feature activation+1.601
half
Token half
Feature activation+0.523
of
Token of
Feature activation+0.182
the
Token the
Feature activation+0.250
players
Token players
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
in
Token in
Feature activation+0.000
20
Token 20
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.203
That
Token That
Feature activation+1.304
means
Token means
Feature activation+1.586
by
Token by
Feature activation+0.689
buying
Token buying
Feature activation+0.000
meat
Token meat
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token17
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.217
down
Token down
Feature activation+1.584
from
Token from
Feature activation+1.284
last
Token last
Feature activation+0.399
week
Token week
Feature activation+0.114
's
Token's
Feature activation+0.278
3
Token 3
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
background
Token background
Feature activation+0.000
is
Token is
Feature activation+0.000
162
Token 162
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+1.570
means
Token means
Feature activation+1.744
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.107
video
Token video
Feature activation+0.142
card
Token card
Feature activation+0.173
,
Token,
Feature activation+0.712
which
Token which
Feature activation+1.310
is
Token is
Feature activation+1.495
much
Token much
Feature activation+1.063
faster
Token faster
Feature activation+0.714
than
Token than
Feature activation+0.435
I
Token I
Feature activation+0.414
could
Token could
Feature activation+0.195
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
subscribers
Token subscribers
Feature activation+0.000
.
Token.
Feature activation+0.634
That
Token That
Feature activation+1.192
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.453
nearly
Token nearly
Feature activation+1.601
half
Token half
Feature activation+0.523
of
Token of
Feature activation+0.182
the
Token the
Feature activation+0.250
players
Token players
Feature activation+0.000
was
Token was
Feature activation+0.000
rising
Token rising
Feature activation+0.000
toward
Token toward
Feature activation+0.000
2
Token 2
Feature activation+0.000
percent
Token percent
Feature activation+0.000
would
Token would
Feature activation+1.400
be
Token be
Feature activation+0.935
an
Token an
Feature activation+0.748
important
Token important
Feature activation+0.489
element
Token element
Feature activation+0.000
of
Token of
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
.
Token.
Feature activation+0.553
That
Token That
Feature activation+1.051
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.381
a
Token a
Feature activation+1.183
net
Token net
Feature activation+0.170
figure
Token figure
Feature activation+0.315
.
Token.
Feature activation+0.576
So
Token So
Feature activation+0.627
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
per
Token per
Feature activation+0.019
cent
Token cent
Feature activation+0.007
,
Token,
Feature activation+1.290
or
Token or
Feature activation+1.374
lower
Token lower
Feature activation+0.912
.
Token.
Feature activation+1.054
Ċ
TokenĊ
Feature activation+0.297
Ċ
TokenĊ
Feature activation+0.473
The
TokenThe
Feature activation+0.368
a
Token a
Feature activation+0.319
government
Token government
Feature activation+0.000
agency
Token agency
Feature activation+0.000
.
Token.
Feature activation+1.310
By
Token By
Feature activation+0.901
comparison
Token comparison
Feature activation+1.366
,
Token,
Feature activation+0.751
coal
Token coal
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
37
Token 37
Feature activation+0.000
percent
Token percent
Feature activation+0.000
33
Token 33
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
feet
Token feet
Feature activation+0.000
-
Token -
Feature activation+0.566
an
Token an
Feature activation+1.353
altitude
Token altitude
Feature activation+0.905
considered
Token considered
Feature activation+0.914
by
Token by
Feature activation+0.320
those
Token those
Feature activation+0.336
within
Token within
Feature activation+0.048
a
Token a
Feature activation+0.000
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.516
holding
Token holding
Feature activation+0.000
would
Token would
Feature activation+1.313
give
Token give
Feature activation+1.207
a
Token a
Feature activation+0.632
shareholder
Token shareholder
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000

Top DFA by src position
MAX = 1.921

,
Token,
Feature activation+0.011
Top resid features:
though
Token though
Feature activation+0.002
Top resid features:
13
Token 13
Feature activation+0.488
Top resid features:
.
Token.
Feature activation+0.145
Top resid features:
5
Token5
Feature activation+0.696
Top resid features:
percent
Token percent
Feature activation+0.916
Top resid features:
is
Token is
Feature activation-0.026
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
percentage
Token percentage
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
average
Token average
Feature activation+0.044
Top resid features:
at
Token at
Feature activation+0.055
Top resid features:
8
Token 8
Feature activation+0.369
Top resid features:
.
Token.
Feature activation+0.102
Top resid features:
8
Token8
Feature activation+0.846
Top resid features:
percent
Token percent
Feature activation+0.846
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
down
Token down
Feature activation-0.026
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
though
Token though
Feature activation-0.006
Top resid features:
13
Token 13
Feature activation+0.432
Top resid features:
.
Token.
Feature activation+0.119
Top resid features:
5
Token5
Feature activation+0.477
Top resid features:
percent
Token percent
Feature activation+1.028
Top resid features:
is
Token is
Feature activation-0.055
Top resid features:
just
Token just
Feature activation+0.012
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
percentage
Token percentage
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
show
Token show
Feature activation-0.008
Top resid features:
garnered
Token garnered
Feature activation-0.018
Top resid features:
just
Token just
Feature activation+0.007
Top resid features:
3
Token 3
Feature activation+0.260
Top resid features:
.
Token.
Feature activation+0.116
Top resid features:
17
Token17
Feature activation+0.697
Top resid features:
million
Token million
Feature activation+0.642
Top resid features:
viewers
Token viewers
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.072
Top resid features:
down
Token down
Feature activation+0.017
Top resid features:
from
Token from
Feature activation-0.002
Top resid features:
with
Token with
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
criminal
Token criminal
Feature activation-0.007
Top resid features:
background
Token background
Feature activation-0.010
Top resid features:
is
Token is
Feature activation+0.034
Top resid features:
162
Token 162
Feature activation+1.921
Top resid features:
,
Token,
Feature activation+0.282
Top resid features:
which
Token which
Feature activation+0.015
Top resid features:
means
Token means
Feature activation-0.034
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.213
Top resid features:
average
Token average
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
around
Token around
Feature activation+0.043
Top resid features:
850
Token 850
Feature activation+1.183
Top resid features:
MW
Token MW
Feature activation+0.791
Top resid features:
).
Token).
Feature activation+0.064
Top resid features:
Which
Token Which
Feature activation+0.047
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
why
Token why
Feature activation+0.000
Top resid features:
show
Token show
Feature activation-0.008
Top resid features:
garnered
Token garnered
Feature activation-0.039
Top resid features:
just
Token just
Feature activation+0.002
Top resid features:
3
Token 3
Feature activation+0.273
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
17
Token17
Feature activation+0.696
Top resid features:
million
Token million
Feature activation+0.672
Top resid features:
viewers
Token viewers
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
down
Token down
Feature activation+0.030
Top resid features:
from
Token from
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
mere
Token mere
Feature activation+0.021
Top resid features:
6
Token 6
Feature activation+0.461
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
8
Token8
Feature activation+0.424
Top resid features:
million
Token million
Feature activation+0.732
Top resid features:
subscribers
Token subscribers
Feature activation+0.231
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
That
Token That
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
unit
Token unit
Feature activation-0.005
Top resid features:
is
Token is
Feature activation+0.028
Top resid features:
one
Token one
Feature activation+0.044
Top resid features:
in
Token in
Feature activation+0.123
Top resid features:
20
Token 20
Feature activation+0.997
Top resid features:
million
Token million
Feature activation+0.816
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
That
Token That
Feature activation+0.019
Top resid features:
means
Token means
Feature activation+0.041
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
show
Token show
Feature activation-0.018
Top resid features:
garnered
Token garnered
Feature activation-0.020
Top resid features:
just
Token just
Feature activation+0.007
Top resid features:
3
Token 3
Feature activation+0.235
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
17
Token17
Feature activation+1.116
Top resid features:
million
Token million
Feature activation+0.421
Top resid features:
viewers
Token viewers
Feature activation+0.112
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
down
Token down
Feature activation-0.031
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
criminal
Token criminal
Feature activation-0.001
Top resid features:
background
Token background
Feature activation-0.009
Top resid features:
is
Token is
Feature activation+0.029
Top resid features:
162
Token 162
Feature activation+1.758
Top resid features:
,
Token,
Feature activation+0.255
Top resid features:
which
Token which
Feature activation-0.027
Top resid features:
means
Token means
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
Yad
Token Yad
Feature activation+0.005
Top resid features:
if
Tokenif
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.025
Top resid features:
take
Token take
Feature activation-0.006
Top resid features:
about
Token about
Feature activation+0.046
Top resid features:
6
Token 6
Feature activation+0.670
Top resid features:
-
Token-
Feature activation+0.013
Top resid features:
8
Token8
Feature activation+0.127
Top resid features:
ms
Tokenms
Feature activation+0.515
Top resid features:
/
Token/
Feature activation+0.078
Top resid features:
frame
Tokenframe
Feature activation+0.054
Top resid features:
garnered
Token garnered
Feature activation-0.036
Top resid features:
just
Token just
Feature activation+0.014
Top resid features:
3
Token 3
Feature activation+0.172
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
17
Token17
Feature activation+0.522
Top resid features:
million
Token million
Feature activation+0.691
Top resid features:
viewers
Token viewers
Feature activation+0.094
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
down
Token down
Feature activation+0.035
Top resid features:
from
Token from
Feature activation+0.013
Top resid features:
last
Token last
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
mere
Token mere
Feature activation+0.060
Top resid features:
6
Token 6
Feature activation+0.391
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
8
Token8
Feature activation+0.415
Top resid features:
million
Token million
Feature activation+0.586
Top resid features:
subscribers
Token subscribers
Feature activation+0.137
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
That
Token That
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
inflation
Token inflation
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.024
Top resid features:
rising
Token rising
Feature activation+0.067
Top resid features:
toward
Token toward
Feature activation+0.046
Top resid features:
2
Token 2
Feature activation+0.679
Top resid features:
percent
Token percent
Feature activation+0.754
Top resid features:
would
Token would
Feature activation+0.014
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
element
Token element
Feature activation+0.000
Top resid features:
net
Token net
Feature activation+0.029
Top resid features:
migration
Token migration
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
70
Token 70
Feature activation+0.763
Top resid features:
,
Token,
Feature activation+0.114
Top resid features:
000
Token000
Feature activation+0.800
Top resid features:
into
Token into
Feature activation+0.026
Top resid features:
New
Token New
Feature activation-0.003
Top resid features:
Zealand
Token Zealand
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
That
Token That
Feature activation-0.007
Top resid features:
expansion
Token expansion
Feature activation-0.010
Top resid features:
cut
Token cut
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
0
Token 0
Feature activation+0.323
Top resid features:
.
Token.
Feature activation+0.172
Top resid features:
9
Token9
Feature activation+0.574
Top resid features:
per
Token per
Feature activation+0.339
Top resid features:
cent
Token cent
Feature activation+0.290
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
or
Token or
Feature activation-0.013
Top resid features:
lower
Token lower
Feature activation+0.000
Top resid features:
provided
Token provided
Feature activation-0.010
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
mere
Token mere
Feature activation+0.070
Top resid features:
0
Token 0
Feature activation+0.348
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
11
Token11
Feature activation+0.932
Top resid features:
percent
Token percent
Feature activation+0.234
Top resid features:
of
Token of
Feature activation+0.118
Top resid features:
U
Token U
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
S
TokenS
Feature activation-0.002
Top resid features:
altitude
Token altitude
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
about
Token about
Feature activation+0.051
Top resid features:
33
Token 33
Feature activation+0.444
Top resid features:
,
Token,
Feature activation+0.167
Top resid features:
000
Token000
Feature activation+0.691
Top resid features:
feet
Token feet
Feature activation+0.437
Top resid features:
-
Token -
Feature activation+0.017
Top resid features:
an
Token an
Feature activation+0.007
Top resid features:
altitude
Token altitude
Feature activation+0.000
Top resid features:
considered
Token considered
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
30
Token 30
Feature activation+0.334
Top resid features:
per
Token per
Feature activation+0.260
Top resid features:
cent
Token cent
Feature activation+0.796
Top resid features:
holding
Token holding
Feature activation+0.258
Top resid features:
would
Token would
Feature activation-0.003
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
shareholder
Token shareholder
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.03

Head 3: 0.10

Head 4: 0.06

Head 5: 0.09

Head 6: 0.10

Head 7: 0.40

Head 8: 0.05

Head 9: 0.01

Head 10: 0.03

Head 11: 0.05

Positive logits

averages2.50

equate2.31

calculates2.29

maximum2.27

Maximum2.26

benchmark2.25

threshold2.25

calculations2.23

infinity2.21

decimal2.21

estimate2.20

equivalent2.18

elsius2.17

ratio2.17

ratios2.14

cutoff2.14

average2.11

compared2.08

Ratio2.08

dwar2.04

Negative logits

ettings-1.97

ivery-1.96

present-1.94

ovie-1.92

iscover-1.92

ective-1.90

Cosponsors-1.84

Merch-1.83

Emails-1.81

ablishment-1.81

hops-1.77

Catalog-1.76

OWN-1.73

agonists-1.72

Lobby-1.71

voic-1.70

atform-1.70

ACTION-1.70

own-1.69

illance-1.69

INTERVAL 1.783 - 1.981
CONTAINS 0.000%

though
Token though
Feature activation+0.000
13
Token 13
Feature activation+0.137
.
Token.
Feature activation+0.225
5
Token5
Feature activation+0.114
percent
Token percent
Feature activation+1.043
is
Token is
Feature activation+1.981
just
Token just
Feature activation+1.837
3
Token 3
Feature activation+0.628
percentage
Token percentage
Feature activation+0.302
points
Token points
Feature activation+0.755
higher
Token higher
Feature activation+0.894
13
Token 13
Feature activation+0.137
.
Token.
Feature activation+0.225
5
Token5
Feature activation+0.114
percent
Token percent
Feature activation+1.043
is
Token is
Feature activation+1.981
just
Token just
Feature activation+1.837
3
Token 3
Feature activation+0.628
percentage
Token percentage
Feature activation+0.302
points
Token points
Feature activation+0.755
higher
Token higher
Feature activation+0.894
than
Token than
Feature activation+0.324
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
a
Token a
Feature activation+0.602
non
Token non
Feature activation+0.000
8
Token 8
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.667
down
Token down
Feature activation+1.841
from
Token from
Feature activation+1.280
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
percent
Token percent
Feature activation+0.000

INTERVAL 1.585 - 1.783
CONTAINS 0.001%

.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
a
Token a
Feature activation+0.602
around
Token around
Feature activation+0.000
850
Token 850
Feature activation+0.000
MW
Token MW
Feature activation+0.000
).
Token).
Feature activation+0.584
Which
Token Which
Feature activation+0.922
is
Token is
Feature activation+1.727
why
Token why
Feature activation+0.999
it
Token it
Feature activation+0.550
's
Token's
Feature activation+0.363
good
Token good
Feature activation+0.236
news
Token news
Feature activation+0.111
in
Token in
Feature activation+0.000
20
Token 20
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.203
That
Token That
Feature activation+1.304
means
Token means
Feature activation+1.586
by
Token by
Feature activation+0.689
buying
Token buying
Feature activation+0.000
meat
Token meat
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.634
That
Token That
Feature activation+1.192
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.453
nearly
Token nearly
Feature activation+1.601
half
Token half
Feature activation+0.523
of
Token of
Feature activation+0.182
the
Token the
Feature activation+0.250
players
Token players
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
background
Token background
Feature activation+0.000
is
Token is
Feature activation+0.000
162
Token 162
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+1.570
means
Token means
Feature activation+1.744
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000

INTERVAL 1.387 - 1.585
CONTAINS 0.001%

.
Token.
Feature activation+0.000
17
Token17
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.217
down
Token down
Feature activation+1.584
from
Token from
Feature activation+1.284
last
Token last
Feature activation+0.399
week
Token week
Feature activation+0.114
's
Token's
Feature activation+0.278
3
Token 3
Feature activation+0.000
this
Token this
Feature activation+0.107
video
Token video
Feature activation+0.142
card
Token card
Feature activation+0.173
,
Token,
Feature activation+0.712
which
Token which
Feature activation+1.310
is
Token is
Feature activation+1.495
much
Token much
Feature activation+1.063
faster
Token faster
Feature activation+0.714
than
Token than
Feature activation+0.435
I
Token I
Feature activation+0.414
could
Token could
Feature activation+0.195
subscribers
Token subscribers
Feature activation+0.000
.
Token.
Feature activation+0.634
That
Token That
Feature activation+1.192
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.453
nearly
Token nearly
Feature activation+1.601
half
Token half
Feature activation+0.523
of
Token of
Feature activation+0.182
the
Token the
Feature activation+0.250
players
Token players
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
was
Token was
Feature activation+0.000
rising
Token rising
Feature activation+0.000
toward
Token toward
Feature activation+0.000
2
Token 2
Feature activation+0.000
percent
Token percent
Feature activation+0.000
would
Token would
Feature activation+1.400
be
Token be
Feature activation+0.935
an
Token an
Feature activation+0.748
important
Token important
Feature activation+0.489
element
Token element
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.189 - 1.387
CONTAINS 0.003%

You
TokenYou
Feature activation+0.000
're
Token're
Feature activation+0.000
doing
Token doing
Feature activation+0.000
150
Token 150
Feature activation+0.000
and
Token and
Feature activation+0.134
you
Token you
Feature activation+1.195
're
Token're
Feature activation+0.981
driving
Token driving
Feature activation+0.000
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.000
absolute
Token absolute
Feature activation+0.000
.
Token.
Feature activation+0.181
That
Token That
Feature activation+0.869
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.231
a
Token a
Feature activation+1.297
relatively
Token relatively
Feature activation+0.537
long
Token long
Feature activation+0.467
time
Token time
Feature activation+0.283
to
Token to
Feature activation+0.000
wait
Token wait
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
.
Token.
Feature activation+0.553
That
Token That
Feature activation+1.051
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.381
a
Token a
Feature activation+1.183
net
Token net
Feature activation+0.170
figure
Token figure
Feature activation+0.315
.
Token.
Feature activation+0.576
So
Token So
Feature activation+0.627
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
April
Token April
Feature activation+0.000
,
Token,
Feature activation+0.699
just
Token just
Feature activation+1.196
barely
Token barely
Feature activation+0.946
below
Token below
Feature activation+0.658
Nevada
Token Nevada
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.667
down
Token down
Feature activation+1.841
from
Token from
Feature activation+1.280
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
percent
Token percent
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.991 - 1.189
CONTAINS 0.005%

million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.509
That
Token That
Feature activation+1.461
's
Token's
Feature activation+1.651
a
Token a
Feature activation+1.804
new
Token new
Feature activation+1.127
low
Token low
Feature activation+1.045
for
Token for
Feature activation+0.944
a
Token a
Feature activation+0.602
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
second
Token second
Feature activation+0.000
.
Token.
Feature activation+0.162
Ċ
TokenĊ
Feature activation+0.047
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.490
means
Token means
Feature activation+1.034
that
Token that
Feature activation+0.429
you
Token you
Feature activation+0.052
can
Token can
Feature activation+0.198
more
Token more
Feature activation+0.105
accurately
Token accurately
Feature activation+0.113
.
Token.
Feature activation+0.553
That
Token That
Feature activation+1.051
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.381
a
Token a
Feature activation+1.183
net
Token net
Feature activation+0.170
figure
Token figure
Feature activation+0.315
.
Token.
Feature activation+0.576
So
Token So
Feature activation+0.627
the
Token the
Feature activation+0.134
5
Token5
Feature activation+0.000
degrees
Token degrees
Feature activation+0.000
south
Token south
Feature activation+0.000
latitude
Token latitude
Feature activation+0.000
.
Token.
Feature activation+0.357
That
Token That
Feature activation+1.010
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.042
a
Token a
Feature activation+1.031
band
Token band
Feature activation+0.000
850
Token 850
Feature activation+0.000
MW
Token MW
Feature activation+0.000
).
Token).
Feature activation+0.584
Which
Token Which
Feature activation+0.922
is
Token is
Feature activation+1.727
why
Token why
Feature activation+0.999
it
Token it
Feature activation+0.550
's
Token's
Feature activation+0.363
good
Token good
Feature activation+0.236
news
Token news
Feature activation+0.111
that
Token that
Feature activation+0.210

INTERVAL 0.792 - 0.991
CONTAINS 0.012%

/
Token/
Feature activation+0.000
FB
TokenFB
Feature activation+0.000
?
Token?
Feature activation+0.548
Yeah
Token Yeah
Feature activation+0.116
,
Token,
Feature activation+0.438
that
Token that
Feature activation+0.835
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.021
go
Token go
Feature activation+0.290
up
Token up
Feature activation+0.323
to
Token to
Feature activation+0.295
the
Token the
Feature activation+0.292
Energy
Token Energy
Feature activation+0.000
Information
Token Information
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
,
Token,
Feature activation+0.811
a
Token a
Feature activation+0.319
government
Token government
Feature activation+0.000
agency
Token agency
Feature activation+0.000
.
Token.
Feature activation+1.310
By
Token By
Feature activation+0.901
found
Token found
Feature activation+0.000
.
Token.
Feature activation+0.012
That
Token That
Feature activation+0.831
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.003
s
Tokens
Feature activation+0.834
up
Token up
Feature activation+0.874
substantially
Token substantially
Feature activation+0.000
from
Token from
Feature activation+0.075
the
Token the
Feature activation+0.000
42
Token 42
Feature activation+0.000
.
Token.
Feature activation+0.012
That
Token That
Feature activation+0.831
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.003
s
Tokens
Feature activation+0.834
up
Token up
Feature activation+0.874
substantially
Token substantially
Feature activation+0.000
from
Token from
Feature activation+0.075
the
Token the
Feature activation+0.000
42
Token 42
Feature activation+0.000
percent
Token percent
Feature activation+0.017
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
April
Token April
Feature activation+0.000
,
Token,
Feature activation+0.699
just
Token just
Feature activation+1.196
barely
Token barely
Feature activation+0.946
below
Token below
Feature activation+0.658
Nevada
Token Nevada
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.594 - 0.792
CONTAINS 0.029%

exceeding
Token exceeding
Feature activation+0.000
24
Token 24
Feature activation+0.000
°
Token°
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.761
is
Token is
Feature activation+0.988
the
Token the
Feature activation+0.648
salmon
Token salmon
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.447
of
Token of
Feature activation+0.440
mic
Token mic
Feature activation+0.000
rons
Tokenrons
Feature activation+0.000
,
Token,
Feature activation+0.586
and
Token and
Feature activation+0.730
have
Token have
Feature activation+0.733
maintained
Token maintained
Feature activation+0.725
liver
Token liver
Feature activation+0.000
tissue
Token tissue
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
fully
Token fully
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
eters
Tokeneters
Feature activation+0.000
across
Token across
Feature activation+0.556
.
Token.
Feature activation+0.756
(
Token (
Feature activation+0.181
A
TokenA
Feature activation+0.683
human
Token human
Feature activation+0.251
hair
Token hair
Feature activation+0.000
is
Token is
Feature activation+0.000
usually
Token usually
Feature activation+0.000
somewhere
Token somewhere
Feature activation+0.000
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+0.000
power
Token power
Feature activation+0.000
supply
Token supply
Feature activation+0.000
.
Token.
Feature activation+0.127
But
Token But
Feature activation+0.674
the
Token the
Feature activation+0.030
benefits
Token benefits
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
added
Token added
Feature activation+0.000
met
Token met
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
markets
Token markets
Feature activation+0.000
.
Token.
Feature activation+0.117
That
Token That
Feature activation+0.701
makes
Token makes
Feature activation+0.782
it
Token it
Feature activation+0.655
the
Token the
Feature activation+0.212
lowest
Token lowest
Feature activation+0.334
rated
Token rated
Feature activation+0.000
M
Token M
Feature activation+0.000

INTERVAL 0.396 - 0.594
CONTAINS 0.051%

mile
Token mile
Feature activation+0.000
to
Token to
Feature activation+0.000
operate
Token operate
Feature activation+0.000
,
Token,
Feature activation+0.519
compared
Token compared
Feature activation+0.612
to
Token to
Feature activation+0.447
60
Token 60
Feature activation+0.153
cents
Token cents
Feature activation+0.000
for
Token for
Feature activation+0.000
personal
Token personal
Feature activation+0.000
cars
Token cars
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.730
is
Token is
Feature activation+0.778
expected
Token expected
Feature activation+0.751
to
Token to
Feature activation+0.511
decrease
Token decrease
Feature activation+0.490
to
Token to
Feature activation+0.073
around
Token around
Feature activation+0.055
$
Token $
Feature activation+0.000
9
Token9
Feature activation+0.000
.
Token.
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.378
was
Token was
Feature activation+0.609
much
Token much
Feature activation+0.508
tougher
Token tougher
Feature activation+0.492
competition
Token competition
Feature activation+0.000
.
Token.
Feature activation+0.020
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
second
Token second
Feature activation+0.056
in
Token in
Feature activation+0.035
Fritz
Token Fritz
Feature activation+0.035
Chess
Token Chess
Feature activation+0.000
benchmark
Token benchmark
Feature activation+0.161
,
Token,
Feature activation+0.500
while
Token while
Feature activation+0.765
C
Token C
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
bench
Tokenbench
Feature activation+0.000
R
Token R
Feature activation+0.000
with
Token with
Feature activation+0.000
475
Token 475
Feature activation+0.000
gold
Token gold
Feature activation+0.000
,
Token,
Feature activation+0.022
for
Token for
Feature activation+0.544
some
Token some
Feature activation+0.416
reason
Token reason
Feature activation+0.000
you
Token you
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.198 - 0.396
CONTAINS 0.112%

query
Token query
Feature activation+0.000
every
Token every
Feature activation+0.000
15
Token 15
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.237
excessive
Token excessive
Feature activation+0.000
CPU
Token CPU
Feature activation+0.000
usage
Token usage
Feature activation+0.000
(
Token (
Feature activation+0.060
and
Tokenand
Feature activation+0.000
£
Token £
Feature activation+0.000
30
Token30
Feature activation+0.000
m
Tokenm
Feature activation+0.000
under
Token under
Feature activation+0.000
its
Token its
Feature activation+0.000
projected
Token projected
Feature activation+0.292
budget
Token budget
Feature activation+0.000
and
Token and
Feature activation+0.236
had
Token had
Feature activation+0.531
"
Token "
Feature activation+0.000
put
Tokenput
Feature activation+0.018
45
Token 45
Feature activation+0.000
%
Token%
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
diseases
Token diseases
Feature activation+0.000
even
Token even
Feature activation+0.246
though
Token though
Feature activation+0.346
we
Token we
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
medicine
Token medicine
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
GHz
Token GHz
Feature activation+0.000
band
Token band
Feature activation+0.231
than
Token than
Feature activation+0.114
the
Token the
Feature activation+0.165
current
Token current
Feature activation+0.417
generation
Token generation
Feature activation+0.188
of
Token of
Feature activation+0.000
Germans
Token Germans
Feature activation+0.000
are
Token are
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
is
Token is
Feature activation+0.385
hardly
Token hardly
Feature activation+0.449
surprising
Token surprising
Feature activation+0.157
.
Token.
Feature activation+0.064
Who
Token Who
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.198
CONTAINS 99.787%

is
Token is
Feature activation+0.000
significant
Token significant
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
has
Token has
Feature activation+0.000
resources
Token resources
Feature activation+0.000
that
Token that
Feature activation+0.000
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
research
Token research
Feature activation+0.000
hub
Token hub
Feature activation+0.000
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
Tech
Token Tech
Feature activation+0.000
Square
Token Square
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
really
Token really
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
substance
Token substance
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
was
Token was
Feature activation+0.000
already
Token already
Feature activation+0.000
doing
Token doing
Feature activation+0.000
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.000
identities
Token identities
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
security
Token security
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
International
Token International
Feature activation+0.000
Organization
Token Organization
Feature activation+0.000
for
Token for
Feature activation+0.000
Standard
Token Standard
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