H7.8 top features

Top feature 0 in H7.8: (feature 649)

TOP ACTIVATIONS
MAX = 4.777

situation
Token situation
Feature activation+0.000
today
Token today
Feature activation+2.098
isn
Token isn
Feature activation+1.599
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+4.777
analogous
Token analogous
Feature activation+1.940
.
Token.
Feature activation+0.084
Unlike
Token Unlike
Feature activation+0.000
the
Token the
Feature activation+0.387
Asian
Token Asian
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
If
TokenIf
Feature activation+0.000
their
Token their
Feature activation+0.000
situation
Token situation
Feature activation+1.827
's
Token's
Feature activation+4.647
like
Token like
Feature activation+3.652
mine
Token mine
Feature activation+3.919
âĢ¦
TokenâĢ¦
Feature activation+0.104
I
Token I
Feature activation+0.011
had
Token had
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
has
Token has
Feature activation+4.251
returned
Token returned
Feature activation+3.846
to
Token to
Feature activation+4.594
what
Token what
Feature activation+1.161
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
till
Token till
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.444
is
Token is
Feature activation+4.480
completely
Token completely
Feature activation+4.551
peaceful
Token peaceful
Feature activation+0.506
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
till
Token till
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.444
is
Token is
Feature activation+4.480
completely
Token completely
Feature activation+4.551
peaceful
Token peaceful
Feature activation+0.506
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+1.300
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+4.457
shines
Token shines
Feature activation+0.000
a
Token a
Feature activation+0.000
bright
Token bright
Feature activation+0.000
light
Token light
Feature activation+0.000
on
Token on
Feature activation+0.000
just
Token just
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+4.385
not
Token not
Feature activation+4.057
getting
Token getting
Feature activation+2.520
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.091
is
Token is
Feature activation+4.326
less
Token less
Feature activation+4.352
clear
Token clear
Feature activation+1.301
.
Token.
Feature activation+0.119
PS
Token PS
Feature activation+0.000
G
TokenG
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.019
is
Token is
Feature activation+4.313
currently
Token currently
Feature activation+4.176
calm
Token calm
Feature activation+1.144
,
Token,
Feature activation+0.913
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
00
Token00
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
has
Token has
Feature activation+4.251
returned
Token returned
Feature activation+3.846
to
Token to
Feature activation+4.594
what
Token what
Feature activation+1.161
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.019
is
Token is
Feature activation+4.313
currently
Token currently
Feature activation+4.176
calm
Token calm
Feature activation+1.144
,
Token,
Feature activation+0.913
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+1.384
continues
Token continues
Feature activation+3.621
to
Token to
Feature activation+4.138
be
Token be
Feature activation+3.997
a
Token a
Feature activation+2.171
concern
Token concern
Feature activation+0.213
,
Token,
Feature activation+0.000
Earn
Token Earn
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+4.385
not
Token not
Feature activation+4.057
getting
Token getting
Feature activation+2.520
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
no
Token no
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+1.384
continues
Token continues
Feature activation+3.621
to
Token to
Feature activation+4.138
be
Token be
Feature activation+3.997
a
Token a
Feature activation+2.171
concern
Token concern
Feature activation+0.213
,
Token,
Feature activation+0.000
Earn
Token Earn
Feature activation+0.000
est
Tokenest
Feature activation+0.000
family
Token family
Feature activation+0.000
members
Token members
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+3.956
severe
Token severe
Feature activation+1.237
enough
Token enough
Feature activation+0.584
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
won
Token won
Feature activation+0.000
If
TokenIf
Feature activation+0.000
their
Token their
Feature activation+0.000
situation
Token situation
Feature activation+1.827
's
Token's
Feature activation+4.647
like
Token like
Feature activation+3.652
mine
Token mine
Feature activation+3.919
âĢ¦
TokenâĢ¦
Feature activation+0.104
I
Token I
Feature activation+0.011
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
clue
Token clue
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
whose
Token whose
Feature activation+3.897
horribly
Token horribly
Feature activation+1.034
circular
Token circular
Feature activation+0.119
reality
Token reality
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
has
Token has
Feature activation+4.251
returned
Token returned
Feature activation+3.846
to
Token to
Feature activation+4.594
what
Token what
Feature activation+1.161
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
,"
Token,"
Feature activation+0.000
"
Token"
Feature activation+0.000
If
TokenIf
Feature activation+0.000
their
Token their
Feature activation+0.000
situation
Token situation
Feature activation+1.827
's
Token's
Feature activation+4.647
like
Token like
Feature activation+3.652
mine
Token mine
Feature activation+3.919
âĢ¦
TokenâĢ¦
Feature activation+0.104
I
Token I
Feature activation+0.011
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+1.384
continues
Token continues
Feature activation+3.621
to
Token to
Feature activation+4.138
be
Token be
Feature activation+3.997
a
Token a
Feature activation+2.171
concern
Token concern
Feature activation+0.213
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 6.581

<|endoftext|>
Token<|endoftext|>
Feature activation+0.496
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
The
Token The
Feature activation+0.042
Top resid features:
situation
Token situation
Feature activation+5.264
Top resid features:
today
Token today
Feature activation+0.309
Top resid features:
isn
Token isn
Feature activation+0.893
Top resid features:
âĢ
TokenâĢ
Feature activation+0.120
Top resid features:
Ļ
TokenĻ
Feature activation+0.084
Top resid features:
t
Tokent
Feature activation+0.117
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
"
Token"
Feature activation+0.001
Top resid features:
If
TokenIf
Feature activation+0.200
Top resid features:
their
Token their
Feature activation+0.128
Top resid features:
situation
Token situation
Feature activation+6.050
Top resid features:
's
Token's
Feature activation+0.165
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
mine
Token mine
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
00
Token00
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
"
Token "
Feature activation+0.041
Top resid features:
The
TokenThe
Feature activation+0.097
Top resid features:
situation
Token situation
Feature activation+5.775
Top resid features:
has
Token has
Feature activation+0.256
Top resid features:
returned
Token returned
Feature activation+0.203
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Valley
Token Valley
Feature activation-0.015
Top resid features:
till
Token till
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
situation
Token situation
Feature activation+5.864
Top resid features:
is
Token is
Feature activation+0.251
Top resid features:
completely
Token completely
Feature activation+0.025
Top resid features:
peaceful
Token peaceful
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Valley
Token Valley
Feature activation-0.010
Top resid features:
till
Token till
Feature activation+0.124
Top resid features:
the
Token the
Feature activation+0.110
Top resid features:
situation
Token situation
Feature activation+5.894
Top resid features:
is
Token is
Feature activation+0.082
Top resid features:
completely
Token completely
Feature activation+0.000
Top resid features:
peaceful
Token peaceful
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Nature
Token Nature
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation+0.055
Top resid features:
situation
Token situation
Feature activation+6.581
Top resid features:
,
Token,
Feature activation+0.266
Top resid features:
he
Token he
Feature activation-0.010
Top resid features:
says
Token says
Feature activation+0.143
Top resid features:
,
Token,
Feature activation+0.120
Top resid features:
shines
Token shines
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.012
Top resid features:
just
Token just
Feature activation+0.057
Top resid features:
means
Token means
Feature activation+0.191
Top resid features:
that
Token that
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.158
Top resid features:
situation
Token situation
Feature activation+6.178
Top resid features:
is
Token is
Feature activation+0.091
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
worse
Token worse
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
G
TokenG
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.110
Top resid features:
Now
Token Now
Feature activation+0.272
Top resid features:
,
Token,
Feature activation+0.120
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
situation
Token situation
Feature activation+4.766
Top resid features:
is
Token is
Feature activation+0.110
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
clear
Token clear
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
PS
Token PS
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.014
Top resid features:
âĢ
Token âĢ
Feature activation+0.060
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation+0.188
Top resid features:
situation
Token situation
Feature activation+4.945
Top resid features:
is
Token is
Feature activation+0.228
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
calm
Token calm
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.005
Top resid features:
00
Token00
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.026
Top resid features:
"
Token "
Feature activation+0.112
Top resid features:
The
TokenThe
Feature activation+0.145
Top resid features:
situation
Token situation
Feature activation+5.581
Top resid features:
has
Token has
Feature activation+0.077
Top resid features:
returned
Token returned
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
âĢ
Token âĢ
Feature activation+0.020
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation+0.130
Top resid features:
situation
Token situation
Feature activation+4.641
Top resid features:
is
Token is
Feature activation+0.563
Top resid features:
currently
Token currently
Feature activation+0.182
Top resid features:
calm
Token calm
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
Ass
TokenAss
Feature activation-0.000
Top resid features:
ert
Tokenert
Feature activation-0.011
Top resid features:
ing
Tokening
Feature activation-0.016
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
situation
Token situation
Feature activation+4.980
Top resid features:
in
Token in
Feature activation+0.598
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.043
Top resid features:
continues
Token continues
Feature activation+0.379
Top resid features:
to
Token to
Feature activation+0.065
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.013
Top resid features:
just
Token just
Feature activation+0.057
Top resid features:
means
Token means
Feature activation+0.135
Top resid features:
that
Token that
Feature activation+0.079
Top resid features:
the
Token the
Feature activation+0.152
Top resid features:
situation
Token situation
Feature activation+5.492
Top resid features:
is
Token is
Feature activation+0.480
Top resid features:
not
Token not
Feature activation+0.027
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
worse
Token worse
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ass
TokenAss
Feature activation-0.001
Top resid features:
ert
Tokenert
Feature activation-0.008
Top resid features:
ing
Tokening
Feature activation-0.006
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
situation
Token situation
Feature activation+4.534
Top resid features:
in
Token in
Feature activation+0.697
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.033
Top resid features:
continues
Token continues
Feature activation+0.397
Top resid features:
to
Token to
Feature activation+0.088
Top resid features:
be
Token be
Feature activation+0.069
Top resid features:
close
Token close
Feature activation+0.047
Top resid features:
family
Token family
Feature activation-0.053
Top resid features:
members
Token members
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.068
Top resid features:
The
Token The
Feature activation+0.120
Top resid features:
situation
Token situation
Feature activation+5.388
Top resid features:
is
Token is
Feature activation+0.332
Top resid features:
severe
Token severe
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
"
Token"
Feature activation+0.019
Top resid features:
If
TokenIf
Feature activation+0.198
Top resid features:
their
Token their
Feature activation+0.107
Top resid features:
situation
Token situation
Feature activation+3.726
Top resid features:
's
Token's
Feature activation+0.824
Top resid features:
like
Token like
Feature activation+1.087
Top resid features:
mine
Token mine
Feature activation-0.134
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
It
TokenIt
Feature activation+0.018
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
situation
Token situation
Feature activation+5.453
Top resid features:
whose
Token whose
Feature activation+0.162
Top resid features:
horribly
Token horribly
Feature activation+0.000
Top resid features:
circular
Token circular
Feature activation+0.000
Top resid features:
reality
Token reality
Feature activation+0.000
Top resid features:
means
Token means
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
00
Token00
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
"
Token "
Feature activation+0.072
Top resid features:
The
TokenThe
Feature activation+0.108
Top resid features:
situation
Token situation
Feature activation+5.072
Top resid features:
has
Token has
Feature activation+0.262
Top resid features:
returned
Token returned
Feature activation+0.034
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
"
Token"
Feature activation+0.014
Top resid features:
If
TokenIf
Feature activation+0.085
Top resid features:
their
Token their
Feature activation+0.299
Top resid features:
situation
Token situation
Feature activation+4.054
Top resid features:
's
Token's
Feature activation+0.861
Top resid features:
like
Token like
Feature activation+0.138
Top resid features:
mine
Token mine
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
Ass
TokenAss
Feature activation-0.001
Top resid features:
ert
Tokenert
Feature activation-0.009
Top resid features:
ing
Tokening
Feature activation-0.024
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
situation
Token situation
Feature activation+4.273
Top resid features:
in
Token in
Feature activation+0.737
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.071
Top resid features:
continues
Token continues
Feature activation+0.308
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.01

Head 3: 0.09

Head 4: 0.04

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.58

Head 9: 0.06

Head 10: 0.02

Head 11: 0.01

Positive logits

worsened2.08

Situation2.00

stable1.90

unfavorable1.87

dire1.84

Conditions1.76

bender1.76

manager1.73

anger1.73

conflic1.67

ppe1.67

Petro1.66

worsening1.65

sted1.64

Anxiety1.63

conditions1.62

intolerable1.61

mma1.61

Ukrain1.60

abuse1.58

Negative logits

salute-1.99

gesture-1.86

commem-1.80

suffix-1.79

acknowled-1.74

swipe-1.71

batteries-1.68

sockets-1.65

tears-1.62

pilgr-1.60

skipping-1.59

vowel-1.58

oaded-1.58

inserted-1.57

telescopes-1.57

socket-1.57

commemor-1.57

deed-1.56

projects-1.56

chip-1.55

INTERVAL 4.300 - 4.777
CONTAINS 0.001%

:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.019
is
Token is
Feature activation+4.313
currently
Token currently
Feature activation+4.176
calm
Token calm
Feature activation+1.144
,
Token,
Feature activation+0.913
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
till
Token till
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.444
is
Token is
Feature activation+4.480
completely
Token completely
Feature activation+4.551
peaceful
Token peaceful
Feature activation+0.506
there
Token there
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
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.091
is
Token is
Feature activation+4.326
less
Token less
Feature activation+4.352
clear
Token clear
Feature activation+1.301
.
Token.
Feature activation+0.119
PS
Token PS
Feature activation+0.000
G
TokenG
Feature activation+0.000
the
Token the
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
till
Token till
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.444
is
Token is
Feature activation+4.480
completely
Token completely
Feature activation+4.551
peaceful
Token peaceful
Feature activation+0.506
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+1.300
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+4.457
shines
Token shines
Feature activation+0.000
a
Token a
Feature activation+0.000
bright
Token bright
Feature activation+0.000
light
Token light
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 3.822 - 4.300
CONTAINS 0.001%

means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+4.385
not
Token not
Feature activation+4.057
getting
Token getting
Feature activation+2.520
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
no
Token no
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.019
is
Token is
Feature activation+4.313
currently
Token currently
Feature activation+4.176
calm
Token calm
Feature activation+1.144
,
Token,
Feature activation+0.913
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
family
Token family
Feature activation+0.000
members
Token members
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+3.956
severe
Token severe
Feature activation+1.237
enough
Token enough
Feature activation+0.584
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
won
Token won
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
situation
Token situation
Feature activation+0.000
has
Token has
Feature activation+4.251
returned
Token returned
Feature activation+3.846
to
Token to
Feature activation+4.594
what
Token what
Feature activation+1.161
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
,"
Token,"
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+1.384
continues
Token continues
Feature activation+3.621
to
Token to
Feature activation+4.138
be
Token be
Feature activation+3.997
a
Token a
Feature activation+2.171
concern
Token concern
Feature activation+0.213
,
Token,
Feature activation+0.000
Earn
Token Earn
Feature activation+0.000
est
Tokenest
Feature activation+0.000

INTERVAL 3.344 - 3.822
CONTAINS 0.001%

"
Token"
Feature activation+0.000
If
TokenIf
Feature activation+0.000
their
Token their
Feature activation+0.000
situation
Token situation
Feature activation+1.827
's
Token's
Feature activation+4.647
like
Token like
Feature activation+3.652
mine
Token mine
Feature activation+3.919
âĢ¦
TokenâĢ¦
Feature activation+0.104
I
Token I
Feature activation+0.011
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+3.586
what
Token what
Feature activation+2.267
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
disastrous
Token disastrous
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+1.384
continues
Token continues
Feature activation+3.621
to
Token to
Feature activation+4.138
be
Token be
Feature activation+3.997
a
Token a
Feature activation+2.171
concern
Token concern
Feature activation+0.213
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.959
is
Token is
Feature activation+3.571
strictly
Token strictly
Feature activation+2.562
an
Token an
Feature activation+0.954
occupation
Token occupation
Feature activation+0.000
is
Token is
Feature activation+0.000
irrelevant
Token irrelevant
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
projects
Token projects
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
that
Token that
Feature activation+3.615
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
pot
Tokenpot
Feature activation+0.000
ential
Tokenential
Feature activation+0.000
)
Token)
Feature activation+0.000

INTERVAL 2.866 - 3.344
CONTAINS 0.001%

the
Token the
Feature activation+0.000
design
Token design
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
which
Token which
Feature activation+3.131
continued
Token continued
Feature activation+2.368
by
Token by
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
?
Token?
Feature activation+0.000
Rice
Token Rice
Feature activation+0.000
's
Token's
Feature activation+0.000
legal
Token legal
Feature activation+0.000
situation
Token situation
Feature activation+0.000
was
Token was
Feature activation+2.919
wrapped
Token wrapped
Feature activation+0.390
up
Token up
Feature activation+0.164
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.000
20
Token 20
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
your
Token your
Feature activation+0.000
condition
Token condition
Feature activation+0.000
to
Token to
Feature activation+3.272
be
Token be
Feature activation+2.921
taken
Token taken
Feature activation+1.738
seriously
Token seriously
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
your
Token your
Feature activation+0.000
condition
Token condition
Feature activation+0.000
to
Token to
Feature activation+3.272
be
Token be
Feature activation+2.921
taken
Token taken
Feature activation+1.738
seriously
Token seriously
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+1.685
be
Token be
Feature activation+3.581
put
Token put
Feature activation+3.249
on
Token on
Feature activation+1.557
the
Token the
Feature activation+1.005
agenda
Token agenda
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000

INTERVAL 2.389 - 2.866
CONTAINS 0.001%

that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+4.385
not
Token not
Feature activation+4.057
getting
Token getting
Feature activation+2.520
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
no
Token no
Feature activation+0.000
one
Token one
Feature activation+0.000
tent
Token tent
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
his
Token his
Feature activation+0.000
condition
Token condition
Feature activation+0.000
quickly
Token quickly
Feature activation+2.577
deteriorated
Token deteriorated
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
several
Token several
Feature activation+0.000
situation
Token situation
Feature activation+0.000
you
Token you
Feature activation+1.878
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.598
in
Token in
Feature activation+2.735
doesn
Token doesn
Feature activation+0.916
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.369
really
Token really
Feature activation+2.074
intelligence
Token intelligence
Feature activation+0.000
methods
Token methods
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
that
Token that
Feature activation+2.653
is
Token is
Feature activation+2.588
a
Token a
Feature activation+2.064
chronic
Token chronic
Feature activation+0.594
issue
Token issue
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.299
ever
Token ever
Feature activation+0.379
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.474
be
Token be
Feature activation+0.862
,
Token,
Feature activation+2.497
is
Token is
Feature activation+1.821
strike
Token strike
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.911 - 2.389
CONTAINS 0.001%

family
Token family
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
every
Token every
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+2.131
different
Token different
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
design
Token design
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
which
Token which
Feature activation+3.131
continued
Token continued
Feature activation+2.368
by
Token by
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
post
Token post
Feature activation+0.000
in
Token in
Feature activation+2.735
doesn
Token doesn
Feature activation+0.916
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.369
really
Token really
Feature activation+2.074
resonate
Token resonate
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
ideals
Token ideals
Feature activation+0.000
and
Token and
Feature activation+0.000
today
Token today
Feature activation+2.098
isn
Token isn
Feature activation+1.599
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+4.777
analogous
Token analogous
Feature activation+1.940
.
Token.
Feature activation+0.084
Unlike
Token Unlike
Feature activation+0.000
the
Token the
Feature activation+0.387
Asian
Token Asian
Feature activation+0.000
countries
Token countries
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
you
Token you
Feature activation+0.679
'd
Token'd
Feature activation+0.406
only
Token only
Feature activation+2.067
think
Token think
Feature activation+2.076
happened
Token happened
Feature activation+0.080
in
Token in
Feature activation+0.013
overd
Token overd
Feature activation+0.000
ram
Tokenram
Feature activation+0.000

INTERVAL 1.433 - 1.911
CONTAINS 0.002%

situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+1.685
be
Token be
Feature activation+3.581
put
Token put
Feature activation+3.249
on
Token on
Feature activation+1.557
the
Token the
Feature activation+1.005
agenda
Token agenda
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
future
Token future
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
prog
Token prog
Feature activation+0.000
nosis
Tokennosis
Feature activation+0.000
has
Token has
Feature activation+1.754
turned
Token turned
Feature activation+1.653
grim
Token grim
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
situation
Token situation
Feature activation+0.000
today
Token today
Feature activation+2.098
isn
Token isn
Feature activation+1.599
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+4.777
analogous
Token analogous
Feature activation+1.940
.
Token.
Feature activation+0.084
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
destined
Token destined
Feature activation+0.000
to
Token to
Feature activation+1.476
get
Token get
Feature activation+0.766
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
situation
Token situation
Feature activation+1.085
played
Token played
Feature activation+1.664
out
Token out
Feature activation+0.349
with
Token with
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
George
Token George
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.955 - 1.433
CONTAINS 0.003%

years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
have
Token have
Feature activation+1.252
gotten
Token gotten
Feature activation+0.790
more
Token more
Feature activation+1.073
dangerous
Token dangerous
Feature activation+0.000
here
Token here
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
southern
Token southern
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
initial
Token initial
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
are
Token are
Feature activation+1.851
nearly
Token nearly
Feature activation+1.144
identical
Token identical
Feature activation+0.798
to
Token to
Feature activation+1.011
every
Token every
Feature activation+0.000
other
Token other
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.000
situation
Token situation
Feature activation+0.000
with
Token with
Feature activation+0.000
Qatar
Token Qatar
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.963
Cairo
Token Cairo
Feature activation+0.000
,
Token,
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.000
,
Token,
Feature activation+0.000
July
Token July
Feature activation+0.000
Honor
Token Honor
Feature activation+0.000
quest
Token quest
Feature activation+0.000
for
Token for
Feature activation+0.000
A
Token A
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
ill
Tokenill
Feature activation+1.157
Park
Token Park
Feature activation+0.000
's
Token's
Feature activation+0.000
George
Token George
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
amo
Tokenamo
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
have
Token have
Feature activation+1.252
gotten
Token gotten
Feature activation+0.790
more
Token more
Feature activation+1.073
dangerous
Token dangerous
Feature activation+0.000
here
Token here
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.478 - 0.955
CONTAINS 0.004%

you
Token you
Feature activation+1.878
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.598
in
Token in
Feature activation+2.735
doesn
Token doesn
Feature activation+0.916
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.369
really
Token really
Feature activation+2.074
resonate
Token resonate
Feature activation+0.000
Hunt
TokenHunt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
fate
Token fate
Feature activation+0.000
is
Token is
Feature activation+0.603
one
Token one
Feature activation+0.285
of
Token of
Feature activation+0.202
the
Token the
Feature activation+0.000
examples
Token examples
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
are
Token are
Feature activation+0.601
deteriorating
Token deteriorating
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
recent
Token recent
Feature activation+0.000
report
Token report
Feature activation+0.000
This
Token This
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+2.510
far
Token far
Feature activation+1.324
more
Token more
Feature activation+1.772
chaotic
Token chaotic
Feature activation+0.837
than
Token than
Feature activation+1.487
it
Token it
Feature activation+0.299
ever
Token ever
Feature activation+0.379
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.474
for
Token for
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
case
Token case
Feature activation+0.000
remains
Token remains
Feature activation+0.664
under
Token under
Feature activation+0.101
investigation
Token investigation
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Cherokee
Token Cherokee
Feature activation+0.000

INTERVAL 0.000 - 0.478
CONTAINS 99.986%

criminal
Token criminal
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
all
Token all
Feature activation+0.000
costing
Token costing
Feature activation+0.000
the
Token the
Feature activation+0.000
consumers
Token consumers
Feature activation+0.000
and
Token and
Feature activation+0.000
taxpayers
Token taxpayers
Feature activation+0.000
billions
Token billions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
simplistic
Token simplistic
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
by
Token by
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
want
Token want
Feature activation+0.000
S
TokenS
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
briefly
Token briefly
Feature activation+0.000
spiked
Token spiked
Feature activation+0.000
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000
highest
Token highest
Feature activation+0.000
in
Token in
Feature activation+0.000
almost
Token almost
Feature activation+0.000
a
Token a
Feature activation+0.000
plate
Token plate
Feature activation+0.000
or
Token or
Feature activation+0.000
buying
Token buying
Feature activation+0.000
her
Token her
Feature activation+0.000
a
Token a
Feature activation+0.000
wide
Token wide
Feature activation+0.000
,
Token,
Feature activation+0.000
flat
Token flat
Feature activation+0.000
feeding
Token feeding
Feature activation+0.000
bowl
Token bowl
Feature activation+0.000
.
Token.
Feature activation+0.000
cabbage
Token cabbage
Feature activation+0.000
and
Token and
Feature activation+0.000
cook
Token cook
Feature activation+0.000
until
Token until
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
tender
Token tender
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
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 H7.8: (feature 23968)

TOP ACTIVATIONS
MAX = 5.062

Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+3.006
commission
Token commission
Feature activation+5.041
had
Token had
Feature activation+4.639
to
Token to
Feature activation+3.386
make
Token make
Feature activation+3.730
was
Token was
Feature activation+1.774
,
Token,
Feature activation+1.534
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
the
Token the
Feature activation+1.659
terrorist
Token terrorist
Feature activation+0.000
group
Token group
Feature activation+0.467
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
the
Token the
Feature activation+1.659
terrorist
Token terrorist
Feature activation+0.000
surgical
Token surgical
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
we
Token we
Feature activation+4.727
have
Token have
Feature activation+4.746
had
Token had
Feature activation+4.654
to
Token to
Feature activation+2.521
make
Token make
Feature activation+2.769
.
Token.
Feature activation+0.599
Some
Token Some
Feature activation+0.553
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
surgical
Token surgical
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
we
Token we
Feature activation+4.727
have
Token have
Feature activation+4.746
had
Token had
Feature activation+4.654
to
Token to
Feature activation+2.521
make
Token make
Feature activation+2.769
.
Token.
Feature activation+0.599
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
we
Token we
Feature activation+4.727
have
Token have
Feature activation+4.746
had
Token had
Feature activation+4.654
to
Token to
Feature activation+2.521
make
Token make
Feature activation+2.769
.
Token.
Feature activation+0.599
Some
Token Some
Feature activation+0.553
of
Token of
Feature activation+0.823
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+3.006
commission
Token commission
Feature activation+5.041
had
Token had
Feature activation+4.639
to
Token to
Feature activation+3.386
make
Token make
Feature activation+3.730
was
Token was
Feature activation+1.774
,
Token,
Feature activation+1.534
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Certainly
Token Certainly
Feature activation+0.000
the
Token the
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
decision
Token decision
Feature activation+0.621
rested
Token rested
Feature activation+4.594
with
Token with
Feature activation+2.484
team
Token team
Feature activation+0.000
owner
Token owner
Feature activation+0.000
and
Token and
Feature activation+0.000
MSG
Token MSG
Feature activation+0.000
examine
Token examine
Feature activation+0.000
how
Token how
Feature activation+0.000
students
Token students
Feature activation+0.000
'
Token'
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
are
Token are
Feature activation+4.589
affected
Token affected
Feature activation+0.000
by
Token by
Feature activation+0.200
external
Token external
Feature activation+0.000
cues
Token cues
Feature activation+0.000
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
major
Token major
Feature activation+0.000
decision
Token decision
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
Even
Token Even
Feature activation+0.277
ask
Token ask
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
was
Token was
Feature activation+4.492
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.022
pretty
Tokenpretty
Feature activation+3.661
easy
Token easy
Feature activation+2.335
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decision
Token decision
Feature activation+0.000
is
Token is
Feature activation+4.448
significant
Token significant
Feature activation+2.186
since
Token since
Feature activation+0.000
it
Token it
Feature activation+3.833
slams
Token slams
Feature activation+0.000
the
Token the
Feature activation+0.000
rebounds
Token rebounds
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
is
Token is
Feature activation+4.386
paying
Token paying
Feature activation+0.000
dividends
Token dividends
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
major
Token major
Feature activation+0.000
decision
Token decision
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
Even
Token Even
Feature activation+0.277
carpet
Token carpet
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
the
Token the
Feature activation+1.659
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.462
One
Token One
Feature activation+4.074
thing
Token thing
Feature activation+0.450
you
Token you
Feature activation+0.901
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
s
Tokens
Feature activation+0.000
any
Token any
Feature activation+0.000
major
Token major
Feature activation+0.000
decision
Token decision
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
h
Tokenh
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
Mississippi
Token Mississippi
Feature activation+0.000
,
Token,
Feature activation+1.580
is
Token is
Feature activation+3.526
going
Token going
Feature activation+2.340
to
Token to
Feature activation+2.242
be
Token be
Feature activation+3.893
made
Token made
Feature activation+3.791
in
Token in
Feature activation+2.119
the
Token the
Feature activation+1.623
Republican
Token Republican
Feature activation+0.000
primary
Token primary
Feature activation+0.000
and
Token and
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
this
Token this
Feature activation+0.000
decision
Token decision
Feature activation+0.000
,
Token,
Feature activation+3.259
which
Token which
Feature activation+3.866
is
Token is
Feature activation+2.482
going
Token going
Feature activation+2.168
to
Token to
Feature activation+1.839
affect
Token affect
Feature activation+0.000
every
Token every
Feature activation+0.000

Top DFA by src position
MAX = 6.256

:
Token:
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
"
Token"
Feature activation+0.014
Top resid features:
The
TokenThe
Feature activation+0.014
Top resid features:
decision
Token decision
Feature activation+6.256
Top resid features:
the
Token the
Feature activation+0.122
Top resid features:
commission
Token commission
Feature activation-0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
ye
Tokenye
Feature activation+0.001
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
final
Token final
Feature activation+0.177
Top resid features:
decision
Token decision
Feature activation+5.779
Top resid features:
has
Token has
Feature activation+0.233
Top resid features:
not
Token not
Feature activation+0.031
Top resid features:
yet
Token yet
Feature activation+0.047
Top resid features:
been
Token been
Feature activation+0.025
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
ye
Tokenye
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
final
Token final
Feature activation+0.194
Top resid features:
decision
Token decision
Feature activation+5.790
Top resid features:
has
Token has
Feature activation+0.208
Top resid features:
not
Token not
Feature activation+0.057
Top resid features:
yet
Token yet
Feature activation+0.026
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.200
Top resid features:
surgical
Token surgical
Feature activation-0.017
Top resid features:
in
Token in
Feature activation-0.059
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
decisions
Token decisions
Feature activation+5.965
Top resid features:
we
Token we
Feature activation+0.076
Top resid features:
have
Token have
Feature activation+0.043
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.225
Top resid features:
surgical
Token surgical
Feature activation-0.010
Top resid features:
in
Token in
Feature activation-0.063
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
decisions
Token decisions
Feature activation+6.016
Top resid features:
we
Token we
Feature activation+0.035
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.192
Top resid features:
surgical
Token surgical
Feature activation-0.034
Top resid features:
in
Token in
Feature activation-0.064
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
decisions
Token decisions
Feature activation+5.754
Top resid features:
we
Token we
Feature activation+0.111
Top resid features:
have
Token have
Feature activation+0.068
Top resid features:
had
Token had
Feature activation+0.085
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
"
Token"
Feature activation+0.010
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
decision
Token decision
Feature activation+5.702
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
commission
Token commission
Feature activation-0.009
Top resid features:
had
Token had
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
gone
Token gone
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.071
Top resid features:
Certainly
Token Certainly
Feature activation+0.091
Top resid features:
the
Token the
Feature activation+0.084
Top resid features:
ultimate
Token ultimate
Feature activation+0.078
Top resid features:
decision
Token decision
Feature activation+5.246
Top resid features:
rested
Token rested
Feature activation+0.093
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
owner
Token owner
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.002
Top resid features:
examine
Token examine
Feature activation-0.045
Top resid features:
how
Token how
Feature activation-0.189
Top resid features:
students
Token students
Feature activation-0.014
Top resid features:
'
Token'
Feature activation+0.014
Top resid features:
decisions
Token decisions
Feature activation+5.786
Top resid features:
are
Token are
Feature activation+0.076
Top resid features:
affected
Token affected
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
external
Token external
Feature activation+0.000
Top resid features:
cues
Token cues
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation-0.010
Top resid features:
any
Token any
Feature activation-0.040
Top resid features:
major
Token major
Feature activation+0.037
Top resid features:
decision
Token decision
Feature activation+5.554
Top resid features:
that
Token that
Feature activation+0.142
Top resid features:
I
Token I
Feature activation+0.059
Top resid features:
put
Token put
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
ask
Token ask
Feature activation-0.005
Top resid features:
him
Token him
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
decision
Token decision
Feature activation+5.307
Top resid features:
was
Token was
Feature activation+0.184
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
pretty
Tokenpretty
Feature activation+0.000
Top resid features:
easy
Token easy
Feature activation+0.000
Top resid features:
listener
Token listener
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
decision
Token decision
Feature activation+5.395
Top resid features:
is
Token is
Feature activation+0.276
Top resid features:
significant
Token significant
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
slams
Token slams
Feature activation+0.000
Top resid features:
7
Token7
Feature activation-0.000
Top resid features:
rebounds
Token rebounds
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
but
Token but
Feature activation-0.083
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
decision
Token decision
Feature activation+5.587
Top resid features:
is
Token is
Feature activation+0.148
Top resid features:
paying
Token paying
Feature activation+0.000
Top resid features:
dividends
Token dividends
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
any
Token any
Feature activation-0.018
Top resid features:
major
Token major
Feature activation+0.040
Top resid features:
decision
Token decision
Feature activation+4.589
Top resid features:
that
Token that
Feature activation+0.146
Top resid features:
I
Token I
Feature activation+0.071
Top resid features:
put
Token put
Feature activation+0.241
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
ye
Tokenye
Feature activation+0.001
Top resid features:
h
Tokenh
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
final
Token final
Feature activation+0.366
Top resid features:
decision
Token decision
Feature activation+4.973
Top resid features:
has
Token has
Feature activation+0.299
Top resid features:
not
Token not
Feature activation+0.021
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.040
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation-0.011
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
big
Token big
Feature activation+0.096
Top resid features:
decision
Token decision
Feature activation+4.874
Top resid features:
.
Token.
Feature activation+0.299
Top resid features:
One
Token One
Feature activation+0.035
Top resid features:
thing
Token thing
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
consider
Token consider
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.012
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation-0.020
Top resid features:
any
Token any
Feature activation-0.066
Top resid features:
major
Token major
Feature activation+0.055
Top resid features:
decision
Token decision
Feature activation+5.171
Top resid features:
that
Token that
Feature activation+0.162
Top resid features:
I
Token I
Feature activation+0.011
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
ye
Tokenye
Feature activation+0.002
Top resid features:
h
Tokenh
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.073
Top resid features:
final
Token final
Feature activation+0.352
Top resid features:
decision
Token decision
Feature activation+4.786
Top resid features:
has
Token has
Feature activation+0.125
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
senator
Token senator
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
therefore
Token therefore
Feature activation-0.007
Top resid features:
this
Token this
Feature activation+0.098
Top resid features:
decision
Token decision
Feature activation+4.446
Top resid features:
,
Token,
Feature activation+0.153
Top resid features:
which
Token which
Feature activation+0.134
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
going
Token going
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
senator
Token senator
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
therefore
Token therefore
Feature activation+0.010
Top resid features:
this
Token this
Feature activation+0.059
Top resid features:
decision
Token decision
Feature activation+4.672
Top resid features:
,
Token,
Feature activation+0.216
Top resid features:
which
Token which
Feature activation+0.193
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.01

Head 3: 0.12

Head 4: 0.03

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.57

Head 9: 0.07

Head 10: 0.01

Head 11: 0.01

Positive logits

decisions2.41

deliber2.11

deliberations2.02

deciding1.82

democratically1.82

dictated1.81

Decision1.80

decision1.75

Replay1.70

irreversible1.68

regretted1.67

discretionary1.67

judgments1.67

responsibility1.64

regret1.64

subconscious1.61

Inquiry1.61

abus1.59

FINAL1.59

retrospect1.58

Negative logits

λ-1.74

gel-1.64

width-1.46

SourceFile-1.45

xs-1.41

slang-1.40

rica-1.40

-1.40

tease-1.39

roaring-1.36

escent-1.36

rier-1.36

bs-1.36

teased-1.34

nn-1.34

chlor-1.34

gd-1.34

aunt-1.34

bloom-1.33

Baltic-1.33

INTERVAL 4.556 - 5.062
CONTAINS 0.001%

the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
the
Token the
Feature activation+1.659
terrorist
Token terrorist
Feature activation+0.000
.
Token.
Feature activation+0.000
Certainly
Token Certainly
Feature activation+0.000
the
Token the
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
decision
Token decision
Feature activation+0.621
rested
Token rested
Feature activation+4.594
with
Token with
Feature activation+2.484
team
Token team
Feature activation+0.000
owner
Token owner
Feature activation+0.000
and
Token and
Feature activation+0.000
MSG
Token MSG
Feature activation+0.000
surgical
Token surgical
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
we
Token we
Feature activation+4.727
have
Token have
Feature activation+4.746
had
Token had
Feature activation+4.654
to
Token to
Feature activation+2.521
make
Token make
Feature activation+2.769
.
Token.
Feature activation+0.599
Some
Token Some
Feature activation+0.553
examine
Token examine
Feature activation+0.000
how
Token how
Feature activation+0.000
students
Token students
Feature activation+0.000
'
Token'
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
are
Token are
Feature activation+4.589
affected
Token affected
Feature activation+0.000
by
Token by
Feature activation+0.200
external
Token external
Feature activation+0.000
cues
Token cues
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+3.006
commission
Token commission
Feature activation+5.041
had
Token had
Feature activation+4.639
to
Token to
Feature activation+3.386
make
Token make
Feature activation+3.730
was
Token was
Feature activation+1.774
,
Token,
Feature activation+1.534

INTERVAL 4.050 - 4.556
CONTAINS 0.001%

rebounds
Token rebounds
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
is
Token is
Feature activation+4.386
paying
Token paying
Feature activation+0.000
dividends
Token dividends
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
major
Token major
Feature activation+0.000
decision
Token decision
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
Even
Token Even
Feature activation+0.277
carpet
Token carpet
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.462
One
Token One
Feature activation+4.074
thing
Token thing
Feature activation+0.450
you
Token you
Feature activation+0.901
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
any
Token any
Feature activation+0.000
major
Token major
Feature activation+0.000
decision
Token decision
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
Even
Token Even
Feature activation+0.277
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+3.924
not
Token not
Feature activation+4.271
yet
Token yet
Feature activation+4.894
been
Token been
Feature activation+4.988
made
Token made
Feature activation+2.429
by
Token by
Feature activation+1.961
the
Token the
Feature activation+1.659

INTERVAL 3.543 - 4.050
CONTAINS 0.002%

decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+3.006
commission
Token commission
Feature activation+5.041
had
Token had
Feature activation+4.639
to
Token to
Feature activation+3.386
make
Token make
Feature activation+3.730
was
Token was
Feature activation+1.774
,
Token,
Feature activation+1.534
are
Token are
Feature activation+0.000
we
Token we
Feature activation+0.000
going
Token going
Feature activation+0.000
public
Token public
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
as
Token as
Feature activation+3.456
the
Token the
Feature activation+3.676
cause
Token cause
Feature activation+0.000
of
Token of
Feature activation+0.181
uncertainty
Token uncertainty
Feature activation+0.145
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
that
Token that
Feature activation+0.000
IBM
Token IBM
Feature activation+0.000
made
Token made
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
so
Token so
Feature activation+3.600
slowly
Token slowly
Feature activation+1.468
that
Token that
Feature activation+0.188
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
tested
Token tested
Feature activation+0.000
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+0.000
life
Tokenlife
Feature activation+0.000
decision
Token decision
Feature activation+0.000
should
Token should
Feature activation+3.694
remain
Token remain
Feature activation+2.936
with
Token with
Feature activation+1.943
the
Token the
Feature activation+0.132
individual
Token individual
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
this
Token this
Feature activation+0.000
decision
Token decision
Feature activation+0.000
,
Token,
Feature activation+3.259
which
Token which
Feature activation+3.866
is
Token is
Feature activation+2.482
going
Token going
Feature activation+2.168
to
Token to
Feature activation+1.839
affect
Token affect
Feature activation+0.000
every
Token every
Feature activation+0.000

INTERVAL 3.037 - 3.543
CONTAINS 0.001%

and
Token and
Feature activation+0.000
Goodell
Token Goodell
Feature activation+0.000
described
Token described
Feature activation+0.000
that
Token that
Feature activation+0.000
decision
Token decision
Feature activation+0.000
as
Token as
Feature activation+3.490
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
high
Tokenhigh
Feature activation+0.289
risk
Token risk
Feature activation+1.830
,
Token,
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+2.526
my
Token my
Feature activation+1.934
own
Token own
Feature activation+3.492
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.531
publicly
Token publicly
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
a
Tokena
Feature activation+0.000
decision
Token decision
Feature activation+0.090
I
Token I
Feature activation+2.175
had
Token had
Feature activation+3.504
made
Token made
Feature activation+2.190
fifteen
Token fifteen
Feature activation+0.269
years
Token years
Feature activation+0.286
earlier
Token earlier
Feature activation+0.344
âĢĶ
TokenâĢĶ
Feature activation+0.703
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
big
Token big
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+3.217
make
Token make
Feature activation+2.814
a
Token a
Feature activation+1.118
change
Token change
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.624
They
TokenThey
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
was
Token was
Feature activation+3.437
taken
Token taken
Feature activation+1.420
in
Token in
Feature activation+1.435
a
Token a
Feature activation+1.170
high
Token high
Feature activation+0.556
-
Token-
Feature activation+0.000

INTERVAL 2.531 - 3.037
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+3.006
commission
Token commission
Feature activation+5.041
had
Token had
Feature activation+4.639
to
Token to
Feature activation+3.386
make
Token make
Feature activation+3.730
was
Token was
Feature activation+1.774
So
Token So
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
decide
Token decide
Feature activation+0.000
for
Token for
Feature activation+2.699
yourself
Token yourself
Feature activation+2.554
on
Token on
Feature activation+0.441
the
Token the
Feature activation+1.506
slippery
Token slippery
Feature activation+0.000
slope
Token slope
Feature activation+0.000
."
Token."
Feature activation+0.000
Libya
Token Libya
Feature activation+0.000
(
Token (
Feature activation+0.000
a
Tokena
Feature activation+0.000
decision
Token decision
Feature activation+0.000
Obama
Token Obama
Feature activation+2.639
now
Token now
Feature activation+2.812
regrets
Token regrets
Feature activation+2.142
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
day
Tokenday
Feature activation+0.000
visa
Token visa
Feature activation+0.000
to
Token to
Feature activation+0.000
Ai
Token Ai
Feature activation+0.000
would
Token would
Feature activation+1.557
be
Token be
Feature activation+2.628
reversed
Token reversed
Feature activation+0.477
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
an
Token an
Feature activation+0.000
illusion
Token illusion
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
had
Token had
Feature activation+2.796
preceded
Token preceded
Feature activation+0.701
the
Token the
Feature activation+0.501
color
Token color
Feature activation+0.000
change
Token change
Feature activation+0.000
when
Token when
Feature activation+0.000

INTERVAL 2.025 - 2.531
CONTAINS 0.004%

in
Token in
Feature activation+0.000
Mississippi
Token Mississippi
Feature activation+0.000
,
Token,
Feature activation+1.580
is
Token is
Feature activation+3.526
going
Token going
Feature activation+2.340
to
Token to
Feature activation+2.242
be
Token be
Feature activation+3.893
made
Token made
Feature activation+3.791
in
Token in
Feature activation+2.119
the
Token the
Feature activation+1.623
Republican
Token Republican
Feature activation+0.000
that
Token that
Feature activation+3.736
I
Token I
Feature activation+4.008
put
Token put
Feature activation+4.506
in
Token in
Feature activation+4.282
my
Token my
Feature activation+1.268
life
Token life
Feature activation+2.168
.
Token.
Feature activation+0.277
Even
Token Even
Feature activation+0.277
carpet
Token carpet
Feature activation+0.000
ing
Tokening
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
and
Token and
Feature activation+0.000
decided
Token decided
Feature activation+0.000
it
Token it
Feature activation+1.628
at
Token at
Feature activation+2.376
a
Token a
Feature activation+2.281
time
Token time
Feature activation+0.000
when
Token when
Feature activation+0.371
it
Token it
Feature activation+0.572
was
Token was
Feature activation+0.535
,
Token,
Feature activation+0.000
re
Token re
Feature activation+0.000
thinking
Tokenthinking
Feature activation+0.000
every
Token every
Feature activation+0.000
choice
Token choice
Feature activation+0.000
I
Token I
Feature activation+2.042
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+1.892
ever
Token ever
Feature activation+2.197
made
Token made
Feature activation+2.064
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
decision
Token decision
Feature activation+0.000
was
Token was
Feature activation+2.162
a
Token a
Feature activation+1.396
reaction
Token reaction
Feature activation+0.000
to
Token to
Feature activation+0.000
days
Token days
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.519 - 2.025
CONTAINS 0.006%

3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
0
Token0
Feature activation+0.000
decision
Token decision
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+1.737
,
Token,
Feature activation+1.306
the
Token the
Feature activation+0.021
NL
Token NL
Feature activation+0.000
RB
TokenRB
Feature activation+0.000
found
Token found
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
and
Token and
Feature activation+0.000
decided
Token decided
Feature activation+0.000
it
Token it
Feature activation+1.628
at
Token at
Feature activation+2.376
a
Token a
Feature activation+2.281
time
Token time
Feature activation+0.000
when
Token when
Feature activation+0.371
it
Token it
Feature activation+0.572
affect
Token affect
Feature activation+0.000
every
Token every
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
in
Token in
Feature activation+0.000
Mississippi
Token Mississippi
Feature activation+0.000
,
Token,
Feature activation+1.580
is
Token is
Feature activation+3.526
going
Token going
Feature activation+2.340
to
Token to
Feature activation+2.242
be
Token be
Feature activation+3.893
made
Token made
Feature activation+3.791
hate
Tokenhate
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
particularly
Token particularly
Feature activation+1.685
susceptible
Token susceptible
Feature activation+1.837
to
Token to
Feature activation+2.459
political
Token political
Feature activation+0.000
influences
Token influences
Feature activation+0.025
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
the
Token the
Feature activation+0.000
decisions
Token decisions
Feature activation+0.113
and
Token and
Feature activation+1.632
debates
Token debates
Feature activation+2.270
of
Token of
Feature activation+1.468
the
Token the
Feature activation+1.872
last
Token last
Feature activation+1.296
weeks
Token weeks
Feature activation+1.127

INTERVAL 1.012 - 1.519
CONTAINS 0.009%

by
Token by
Feature activation+2.750
Friday
Token Friday
Feature activation+1.104
,
Token,
Feature activation+0.241
November
Token November
Feature activation+0.000
16
Token 16
Feature activation+1.182
,
Token,
Feature activation+1.135
whether
Token whether
Feature activation+0.000
their
Token their
Feature activation+0.000
state
Token state
Feature activation+0.000
will
Token will
Feature activation+0.000
create
Token create
Feature activation+0.000
next
Token next
Feature activation+0.000
B
Token B
Feature activation+0.000
achel
Tokenachel
Feature activation+0.000
oret
Tokenoret
Feature activation+0.000
te
Tokente
Feature activation+0.000
may
Token may
Feature activation+1.261
have
Token have
Feature activation+1.486
been
Token been
Feature activation+1.546
more
Token more
Feature activation+1.132
of
Token of
Feature activation+1.492
a
Token a
Feature activation+1.351
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
spread
Token spread
Feature activation+1.051
death
Token death
Feature activation+0.000
,
Token,
Feature activation+0.000
destruction
Token destruction
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
perplex
Token perplex
Feature activation+0.000
ing
Tokening
Feature activation+0.000
decision
Token decision
Feature activation+0.000
making
Token making
Feature activation+1.037
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
a
Token a
Feature activation+0.000
tone
Token tone
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
was
Token was
Feature activation+3.437
taken
Token taken
Feature activation+1.420
in
Token in
Feature activation+1.435
a
Token a
Feature activation+1.170
high
Token high
Feature activation+0.556
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+0.584
consult
Token consult
Feature activation+0.000
ative
Tokenative
Feature activation+0.139

INTERVAL 0.506 - 1.012
CONTAINS 0.017%

t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
say
Token say
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.601
.
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
great
Token great
Feature activation+0.000
vision
Token vision
Feature activation+0.000
and
Token and
Feature activation+0.000
decision
Token decision
Feature activation+0.000
-
Token-
Feature activation+3.341
making
Tokenmaking
Feature activation+0.899
ability
Token ability
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.000
got
Token got
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
their
Token their
Feature activation+0.000
potential
Token potential
Feature activation+0.000
decisions
Token decisions
Feature activation+0.192
with
Token with
Feature activation+0.536
Jose
Token Jose
Feature activation+0.000
B
Token B
Feature activation+0.000
aut
Tokenaut
Feature activation+0.000
ista
Tokenista
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
this
Token this
Feature activation+0.000
decision
Token decision
Feature activation+0.546
isn
Token isn
Feature activation+1.770
't
Token't
Feature activation+2.225
reversed
Token reversed
Feature activation+0.271
,
Token,
Feature activation+0.000
Music
Token Music
Feature activation+0.000
making
Token making
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
little
Token little
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
through
Token through
Feature activation+0.844
the
Token the
Feature activation+0.717
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.441
mic
Token mic
Feature activation+0.000
roman
Tokenroman
Feature activation+0.000

INTERVAL 0.000 - 0.506
CONTAINS 99.956%

security
Token security
Feature activation+0.000
services
Token services
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
power
Token power
Feature activation+0.000
and
Token and
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
even
Token even
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
rights
Token rights
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
creating
Token creating
Feature activation+0.000
an
Token an
Feature activation+0.000
argument
Token argument
Feature activation+0.000
AGA
Token AGA
Feature activation+0.000
INST
TokenINST
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
st
Token st
Feature activation+0.000
adia
Tokenadia
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
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
Tuesday
Token Tuesday
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Heavy
TokenHeavy
Feature activation+0.000
snow
Token snow
Feature activation+0.000
,
Token,
Feature activation+0.000
gunmen
Token gunmen
Feature activation+0.000
amb
Token amb
Feature activation+0.000
ushed
Tokenushed
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
's
Token's
Feature activation+0.000
bus
Token bus
Feature activation+0.000
,
Token,
Feature activation+0.000
firing
Token firing
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Imm
TokenImm
Feature activation+0.000
igration
Tokenigration
Feature activation+0.000
dropped
Token dropped
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
66
Token66
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 2 in H7.8: (feature 38262)

TOP ACTIVATIONS
MAX = 5.235

.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+3.566
very
Token very
Feature activation+0.883
easily
Token easily
Feature activation+5.235
go
Token go
Feature activation+3.224
from
Token from
Feature activation+3.121
bad
Token bad
Feature activation+0.000
to
Token to
Feature activation+0.132
much
Token much
Feature activation+0.000
the
Token the
Feature activation+0.000
date
Token date
Feature activation+0.000
when
Token when
Feature activation+0.000
things
Token things
Feature activation+0.203
started
Token started
Feature activation+4.574
to
Token to
Feature activation+4.842
go
Token go
Feature activation+3.766
in
Token in
Feature activation+2.540
a
Token a
Feature activation+0.271
different
Token different
Feature activation+1.078
direction
Token direction
Feature activation+0.659
pinpoint
Token pinpoint
Feature activation+0.000
the
Token the
Feature activation+0.000
date
Token date
Feature activation+0.000
when
Token when
Feature activation+0.000
things
Token things
Feature activation+0.203
started
Token started
Feature activation+4.574
to
Token to
Feature activation+4.842
go
Token go
Feature activation+3.766
in
Token in
Feature activation+2.540
a
Token a
Feature activation+0.271
different
Token different
Feature activation+1.078
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.819
not
Token not
Feature activation+4.562
completely
Token completely
Feature activation+2.834
fine
Token fine
Feature activation+0.000
:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
had
Token had
Feature activation+3.386
not
Token not
Feature activation+4.064
yet
Token yet
Feature activation+4.494
been
Token been
Feature activation+3.177
final
Token final
Feature activation+0.000
ised
Tokenised
Feature activation+0.277
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
or
Token or
Feature activation+0.000
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
want
Token want
Feature activation+1.380
to
Token to
Feature activation+4.442
work
Token work
Feature activation+1.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Consider
TokenConsider
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
have
Token have
Feature activation+4.341
changed
Token changed
Feature activation+1.168
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
time
Token time
Feature activation+0.000
things
Token things
Feature activation+0.000
haven
Token haven
Feature activation+1.890
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.394
t
Tokent
Feature activation+4.327
gone
Token gone
Feature activation+3.714
smoothly
Token smoothly
Feature activation+0.980
for
Token for
Feature activation+0.006
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
had
Token had
Feature activation+3.386
not
Token not
Feature activation+4.064
yet
Token yet
Feature activation+4.494
been
Token been
Feature activation+3.177
final
Token final
Feature activation+0.000
ised
Tokenised
Feature activation+0.277
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
why
Tokenwhy
Feature activation+0.000
things
Token things
Feature activation+0.030
tend
Token tend
Feature activation+1.221
to
Token to
Feature activation+4.039
be
Token be
Feature activation+3.149
much
Token much
Feature activation+2.062
less
Token less
Feature activation+2.235
lively
Token lively
Feature activation+0.000
on
Token on
Feature activation+0.000
burg
Tokenburg
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
things
Token things
Feature activation+0.000
turn
Token turn
Feature activation+3.927
out
Token out
Feature activation+3.033
as
Token as
Feature activation+2.361
they
Token they
Feature activation+1.956
should
Token should
Feature activation+1.378
he
Token he
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
weren
Token weren
Feature activation+1.392
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.058
t
Tokent
Feature activation+3.822
as
Token as
Feature activation+2.294
dramatic
Token dramatic
Feature activation+0.654
,
Token,
Feature activation+0.002
K
Token K
Feature activation+0.000
atic
Tokenatic
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.819
not
Token not
Feature activation+4.562
completely
Token completely
Feature activation+2.834
fine
Token fine
Feature activation+0.000
:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
op
Tokenop
Feature activation+0.000
and
Token and
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.795
weird
Token weird
Feature activation+2.169
but
Token but
Feature activation+0.685
they
Token they
Feature activation+0.981
could
Token could
Feature activation+1.378
always
Token always
Feature activation+0.513
date
Token date
Feature activation+0.000
when
Token when
Feature activation+0.000
things
Token things
Feature activation+0.203
started
Token started
Feature activation+4.574
to
Token to
Feature activation+4.842
go
Token go
Feature activation+3.766
in
Token in
Feature activation+2.540
a
Token a
Feature activation+0.271
different
Token different
Feature activation+1.078
direction
Token direction
Feature activation+0.659
âĢĶ
Token âĢĶ
Feature activation+0.000
things
Token things
Feature activation+0.000
haven
Token haven
Feature activation+1.890
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.394
t
Tokent
Feature activation+4.327
gone
Token gone
Feature activation+3.714
smoothly
Token smoothly
Feature activation+0.980
for
Token for
Feature activation+0.006
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
.
Token.
Feature activation+0.000
once
Token once
Feature activation+0.000
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+3.566
very
Token very
Feature activation+0.883
easily
Token easily
Feature activation+5.235
go
Token go
Feature activation+3.224
from
Token from
Feature activation+3.121
bad
Token bad
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
made
Token made
Feature activation+0.000
things
Token things
Feature activation+0.444
a
Token a
Feature activation+2.389
lot
Token lot
Feature activation+3.556
easier
Token easier
Feature activation+1.912
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
married
Token married
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+2.909
beginning
Token beginning
Feature activation+2.808
to
Token to
Feature activation+3.526
click
Token click
Feature activation+0.193
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
became
Token became
Feature activation+0.000
president
Token president
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
were
Token were
Feature activation+3.502
more
Token more
Feature activation+2.560
polarized
Token polarized
Feature activation+0.104
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000

Top DFA by src position
MAX = 5.859

ship
Token ship
Feature activation+0.010
Top resid features:
once
Token once
Feature activation+0.001
Top resid features:
again
Token again
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
But
Token But
Feature activation+0.025
Top resid features:
things
Token things
Feature activation+5.859
Top resid features:
could
Token could
Feature activation+0.322
Top resid features:
very
Token very
Feature activation-0.033
Top resid features:
easily
Token easily
Feature activation+0.149
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
pinpoint
Token pinpoint
Feature activation+0.046
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
date
Token date
Feature activation+0.010
Top resid features:
when
Token when
Feature activation+0.065
Top resid features:
things
Token things
Feature activation+5.541
Top resid features:
started
Token started
Feature activation+0.164
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.074
Top resid features:
pinpoint
Token pinpoint
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
date
Token date
Feature activation+0.025
Top resid features:
when
Token when
Feature activation+0.130
Top resid features:
things
Token things
Feature activation+5.268
Top resid features:
started
Token started
Feature activation+0.120
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Italy
Token Italy
Feature activation-0.008
Top resid features:
right
Token right
Feature activation+0.003
Top resid features:
now
Token now
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Things
Token Things
Feature activation+4.507
Top resid features:
are
Token are
Feature activation+1.050
Top resid features:
not
Token not
Feature activation+0.102
Top resid features:
completely
Token completely
Feature activation+0.000
Top resid features:
fine
Token fine
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.003
Top resid features:
Singapore
Token Singapore
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
Thursday
Token Thursday
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
things
Token things
Feature activation+5.089
Top resid features:
had
Token had
Feature activation+0.210
Top resid features:
not
Token not
Feature activation-0.002
Top resid features:
yet
Token yet
Feature activation+0.071
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
final
Token final
Feature activation+0.000
Top resid features:
For
TokenFor
Feature activation-0.009
Top resid features:
better
Token better
Feature activation-0.013
Top resid features:
or
Token or
Feature activation-0.003
Top resid features:
worse
Token worse
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
things
Token things
Feature activation+5.069
Top resid features:
want
Token want
Feature activation+0.528
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.022
Top resid features:
time
Token time
Feature activation-0.016
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
though
Token though
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.174
Top resid features:
things
Token things
Feature activation+5.471
Top resid features:
have
Token have
Feature activation+0.063
Top resid features:
changed
Token changed
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
But
TokenBut
Feature activation+0.050
Top resid features:
since
Token since
Feature activation-0.054
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
time
Token time
Feature activation+0.211
Top resid features:
things
Token things
Feature activation+4.980
Top resid features:
haven
Token haven
Feature activation+0.471
Top resid features:
âĢ
TokenâĢ
Feature activation-0.128
Top resid features:
Ļ
TokenĻ
Feature activation+0.129
Top resid features:
t
Tokent
Feature activation+0.085
Top resid features:
gone
Token gone
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.005
Top resid features:
Singapore
Token Singapore
Feature activation-0.000
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
Thursday
Token Thursday
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
things
Token things
Feature activation+4.331
Top resid features:
had
Token had
Feature activation+0.314
Top resid features:
not
Token not
Feature activation+0.087
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
final
Token final
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.011
Top resid features:
sort
Tokensort
Feature activation-0.017
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.017
Top resid features:
why
Tokenwhy
Feature activation+0.079
Top resid features:
things
Token things
Feature activation+4.969
Top resid features:
tend
Token tend
Feature activation+0.093
Top resid features:
to
Token to
Feature activation+0.081
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
Stras
Token Stras
Feature activation-0.023
Top resid features:
burg
Tokenburg
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
but
Token but
Feature activation+0.020
Top resid features:
if
Token if
Feature activation-0.036
Top resid features:
things
Token things
Feature activation+4.990
Top resid features:
turn
Token turn
Feature activation+0.136
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
Behind
Token Behind
Feature activation-0.131
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
scenes
Token scenes
Feature activation+0.406
Top resid features:
,
Token,
Feature activation+0.178
Top resid features:
things
Token things
Feature activation+3.914
Top resid features:
weren
Token weren
Feature activation+0.795
Top resid features:
âĢ
TokenâĢ
Feature activation-0.042
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
t
Tokent
Feature activation+0.027
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Italy
Token Italy
Feature activation-0.015
Top resid features:
right
Token right
Feature activation+0.002
Top resid features:
now
Token now
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Things
Token Things
Feature activation+4.667
Top resid features:
are
Token are
Feature activation+0.214
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
completely
Token completely
Feature activation+0.000
Top resid features:
fine
Token fine
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
rop
Tokenrop
Feature activation-0.010
Top resid features:
op
Tokenop
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
industrial
Token industrial
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
Things
Token Things
Feature activation+4.509
Top resid features:
are
Token are
Feature activation+0.234
Top resid features:
weird
Token weird
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.056
Top resid features:
pinpoint
Token pinpoint
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
date
Token date
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.096
Top resid features:
things
Token things
Feature activation+4.086
Top resid features:
started
Token started
Feature activation+0.217
Top resid features:
to
Token to
Feature activation+0.151
Top resid features:
go
Token go
Feature activation+0.123
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
But
TokenBut
Feature activation+0.112
Top resid features:
since
Token since
Feature activation-0.086
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
time
Token time
Feature activation+0.060
Top resid features:
things
Token things
Feature activation+4.107
Top resid features:
haven
Token haven
Feature activation+0.473
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
t
Tokent
Feature activation+0.104
Top resid features:
gone
Token gone
Feature activation+0.086
Top resid features:
ship
Token ship
Feature activation+0.009
Top resid features:
once
Token once
Feature activation-0.003
Top resid features:
again
Token again
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.179
Top resid features:
But
Token But
Feature activation+0.029
Top resid features:
things
Token things
Feature activation+4.157
Top resid features:
could
Token could
Feature activation+0.158
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
easily
Token easily
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Clayton
Token Clayton
Feature activation+0.006
Top resid features:
;
Token;
Feature activation+0.011
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
just
Token just
Feature activation+0.022
Top resid features:
made
Token made
Feature activation+0.115
Top resid features:
things
Token things
Feature activation+4.334
Top resid features:
a
Token a
Feature activation+0.182
Top resid features:
lot
Token lot
Feature activation+0.076
Top resid features:
easier
Token easier
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation-0.010
Top resid features:
never
Token never
Feature activation-0.006
Top resid features:
be
Token be
Feature activation-0.010
Top resid features:
married
Token married
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Things
Token Things
Feature activation+3.896
Top resid features:
are
Token are
Feature activation+0.492
Top resid features:
beginning
Token beginning
Feature activation+0.116
Top resid features:
to
Token to
Feature activation+0.066
Top resid features:
click
Token click
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Dub
Token Dub
Feature activation-0.017
Top resid features:
ya
Tokenya
Feature activation-0.007
Top resid features:
became
Token became
Feature activation-0.004
Top resid features:
president
Token president
Feature activation-0.085
Top resid features:
,
Token,
Feature activation+0.132
Top resid features:
things
Token things
Feature activation+4.305
Top resid features:
were
Token were
Feature activation+0.115
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
polarized
Token polarized
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.01

Head 3: 0.07

Head 4: 0.03

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.55

Head 9: 0.07

Head 10: 0.02

Head 11: 0.03

Positive logits

unravel2.04

unfold2.03

tighten1.90

transpired1.87

downhill1.83

unfolded1.77

snowball1.72

predictable1.69

unfolding1.65

tumble1.62

Diff1.60

tightened1.59

én1.55

icky1.54

happening1.54

oodoo1.54

complicated1.54

Happ1.53

tighter1.53

tightening1.50

Negative logits

elig-2.26

inval-1.81

Joined-1.66

asio-1.65

otto-1.64

acknowled-1.61

aye-1.59

subscrib-1.58

substitute-1.55

badge-1.52

igible-1.52

ename-1.51

Fenrir-1.50

explorer-1.49

designation-1.49

substitutes-1.49

descriptor-1.49

solitude-1.48

Patron-1.48

Reader-1.46

INTERVAL 4.711 - 5.235
CONTAINS 0.000%

the
Token the
Feature activation+0.000
date
Token date
Feature activation+0.000
when
Token when
Feature activation+0.000
things
Token things
Feature activation+0.203
started
Token started
Feature activation+4.574
to
Token to
Feature activation+4.842
go
Token go
Feature activation+3.766
in
Token in
Feature activation+2.540
a
Token a
Feature activation+0.271
different
Token different
Feature activation+1.078
direction
Token direction
Feature activation+0.659
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+3.566
very
Token very
Feature activation+0.883
easily
Token easily
Feature activation+5.235
go
Token go
Feature activation+3.224
from
Token from
Feature activation+3.121
bad
Token bad
Feature activation+0.000
to
Token to
Feature activation+0.132
much
Token much
Feature activation+0.000

INTERVAL 4.188 - 4.711
CONTAINS 0.001%

pinpoint
Token pinpoint
Feature activation+0.000
the
Token the
Feature activation+0.000
date
Token date
Feature activation+0.000
when
Token when
Feature activation+0.000
things
Token things
Feature activation+0.203
started
Token started
Feature activation+4.574
to
Token to
Feature activation+4.842
go
Token go
Feature activation+3.766
in
Token in
Feature activation+2.540
a
Token a
Feature activation+0.271
different
Token different
Feature activation+1.078
time
Token time
Feature activation+0.000
things
Token things
Feature activation+0.000
haven
Token haven
Feature activation+1.890
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.394
t
Tokent
Feature activation+4.327
gone
Token gone
Feature activation+3.714
smoothly
Token smoothly
Feature activation+0.980
for
Token for
Feature activation+0.006
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
have
Token have
Feature activation+4.341
changed
Token changed
Feature activation+1.168
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
or
Token or
Feature activation+0.000
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
want
Token want
Feature activation+1.380
to
Token to
Feature activation+4.442
work
Token work
Feature activation+1.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Consider
TokenConsider
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.819
not
Token not
Feature activation+4.562
completely
Token completely
Feature activation+2.834
fine
Token fine
Feature activation+0.000
:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 3.664 - 4.188
CONTAINS 0.001%

op
Tokenop
Feature activation+0.000
and
Token and
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.795
weird
Token weird
Feature activation+2.169
but
Token but
Feature activation+0.685
they
Token they
Feature activation+0.981
could
Token could
Feature activation+1.378
always
Token always
Feature activation+0.513
burg
Tokenburg
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
things
Token things
Feature activation+0.000
turn
Token turn
Feature activation+3.927
out
Token out
Feature activation+3.033
as
Token as
Feature activation+2.361
they
Token they
Feature activation+1.956
should
Token should
Feature activation+1.378
he
Token he
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.819
not
Token not
Feature activation+4.562
completely
Token completely
Feature activation+2.834
fine
Token fine
Feature activation+0.000
:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
had
Token had
Feature activation+3.386
not
Token not
Feature activation+4.064
yet
Token yet
Feature activation+4.494
been
Token been
Feature activation+3.177
final
Token final
Feature activation+0.000
ised
Tokenised
Feature activation+0.277
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
weren
Token weren
Feature activation+1.392
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.058
t
Tokent
Feature activation+3.822
as
Token as
Feature activation+2.294
dramatic
Token dramatic
Feature activation+0.654
,
Token,
Feature activation+0.002
K
Token K
Feature activation+0.000
atic
Tokenatic
Feature activation+0.000

INTERVAL 3.141 - 3.664
CONTAINS 0.001%

for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
start
Token start
Feature activation+2.702
to
Token to
Feature activation+3.480
...
Token...
Feature activation+1.585
well
Token well
Feature activation+0.076
,
Token,
Feature activation+2.317
not
Token not
Feature activation+2.824
to
Token to
Feature activation+1.234
once
Token once
Feature activation+0.000
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+3.566
very
Token very
Feature activation+0.883
easily
Token easily
Feature activation+5.235
go
Token go
Feature activation+3.224
from
Token from
Feature activation+3.121
bad
Token bad
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
became
Token became
Feature activation+0.000
president
Token president
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
were
Token were
Feature activation+3.502
more
Token more
Feature activation+2.560
polarized
Token polarized
Feature activation+0.104
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000
Singapore
Token Singapore
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
had
Token had
Feature activation+3.386
not
Token not
Feature activation+4.064
yet
Token yet
Feature activation+4.494
been
Token been
Feature activation+3.177
final
Token final
Feature activation+0.000
ised
Tokenised
Feature activation+0.277
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
had
Token had
Feature activation+3.386
not
Token not
Feature activation+4.064
yet
Token yet
Feature activation+4.494
been
Token been
Feature activation+3.177
final
Token final
Feature activation+0.000
ised
Tokenised
Feature activation+0.277
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.617 - 3.141
CONTAINS 0.002%

would
Token would
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
things
Token things
Feature activation+0.000
really
Token really
Feature activation+2.969
open
Token open
Feature activation+1.431
up
Token up
Feature activation+1.681
and
Token and
Feature activation+0.220
just
Token just
Feature activation+0.000
be
Token be
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+3.819
not
Token not
Feature activation+4.562
completely
Token completely
Feature activation+2.834
fine
Token fine
Feature activation+0.000
:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
slipped
Token slipped
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.000
married
Token married
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+2.909
beginning
Token beginning
Feature activation+2.808
to
Token to
Feature activation+3.526
click
Token click
Feature activation+0.193
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
then
Token then
Feature activation+0.000
things
Token things
Feature activation+0.000
started
Token started
Feature activation+2.250
to
Token to
Feature activation+2.817
happen
Token happen
Feature activation+0.080
very
Token very
Feature activation+1.435
quickly
Token quickly
Feature activation+0.723
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
's
Token's
Feature activation+0.000
better
Token better
Feature activation+0.000
as
Token as
Feature activation+0.000
things
Token things
Feature activation+0.000
don
Token don
Feature activation+0.192
't
Token't
Feature activation+2.804
often
Token often
Feature activation+2.311
end
Token end
Feature activation+2.486
up
Token up
Feature activation+2.780
well
Token well
Feature activation+1.413
when
Token when
Feature activation+0.336

INTERVAL 2.094 - 2.617
CONTAINS 0.003%

anco
Tokenanco
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
then
Token then
Feature activation+0.000
things
Token things
Feature activation+0.000
started
Token started
Feature activation+2.250
to
Token to
Feature activation+2.817
happen
Token happen
Feature activation+0.080
very
Token very
Feature activation+1.435
quickly
Token quickly
Feature activation+0.723
.
Token.
Feature activation+0.000
meetings
Token meetings
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+1.308
really
Token really
Feature activation+2.349
moving
Token moving
Feature activation+1.131
forward
Token forward
Feature activation+0.000
!
Token!
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
legalization
Token legalization
Feature activation+0.000
things
Token things
Feature activation+0.000
will
Token will
Feature activation+2.978
have
Token have
Feature activation+2.467
to
Token to
Feature activation+2.570
be
Token be
Feature activation+2.302
adjusted
Token adjusted
Feature activation+0.030
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
became
Token became
Feature activation+0.000
president
Token president
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
were
Token were
Feature activation+3.502
more
Token more
Feature activation+2.560
polarized
Token polarized
Feature activation+0.104
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000
so
Token so
Feature activation+0.000
A
Token A
Feature activation+0.000
year
Token year
Feature activation+0.000
ago
Token ago
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
were
Token were
Feature activation+2.158
so
Token so
Feature activation+2.837
slow
Token slow
Feature activation+0.000
he
Token he
Feature activation+0.000
'd
Token'd
Feature activation+0.000
often
Token often
Feature activation+0.000

INTERVAL 1.570 - 2.094
CONTAINS 0.003%

so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
remember
Token remember
Feature activation+0.000
things
Token things
Feature activation+0.000
he
Token he
Feature activation+1.626
needed
Token needed
Feature activation+0.008
to
Token to
Feature activation+0.473
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
they
Token they
Feature activation+0.000
distract
Token distract
Feature activation+0.000
us
Token us
Feature activation+0.000
from
Token from
Feature activation+0.000
things
Token things
Feature activation+0.000
Trump
Token Trump
Feature activation+1.644
wants
Token wants
Feature activation+2.064
us
Token us
Feature activation+0.762
to
Token to
Feature activation+1.025
ignore
Token ignore
Feature activation+0.875
.
Token.
Feature activation+0.000
some
Token some
Feature activation+0.000
signs
Token signs
Feature activation+0.000
of
Token of
Feature activation+0.000
things
Token things
Feature activation+0.000
picking
Token picking
Feature activation+0.635
up
Token up
Feature activation+1.803
a
Token a
Feature activation+0.000
month
Token month
Feature activation+0.000
or
Token or
Feature activation+0.000
two
Token two
Feature activation+0.000
ago
Token ago
Feature activation+0.000
my
Token my
Feature activation+0.000
teaser
Token teaser
Feature activation+0.000
page
Token page
Feature activation+0.000
of
Token of
Feature activation+0.000
things
Token things
Feature activation+0.000
to
Token to
Feature activation+1.814
come
Token come
Feature activation+0.000
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
things
Token things
Feature activation+0.000
really
Token really
Feature activation+2.969
open
Token open
Feature activation+1.431
up
Token up
Feature activation+1.681
and
Token and
Feature activation+0.220
just
Token just
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
blending
Token blending
Feature activation+0.000

INTERVAL 1.047 - 1.570
CONTAINS 0.004%

car
Token car
Feature activation+0.000
because
Token because
Feature activation+0.000
things
Token things
Feature activation+0.000
happen
Token happen
Feature activation+1.433
so
Token so
Feature activation+1.292
fast
Token fast
Feature activation+1.144
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
haven
Token haven
Feature activation+0.000
't
Token't
Feature activation+0.000
sort
Tokensort
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
why
Tokenwhy
Feature activation+0.000
things
Token things
Feature activation+0.030
tend
Token tend
Feature activation+1.221
to
Token to
Feature activation+4.039
be
Token be
Feature activation+3.149
much
Token much
Feature activation+2.062
less
Token less
Feature activation+2.235
lively
Token lively
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
weren
Token weren
Feature activation+1.392
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.058
t
Tokent
Feature activation+3.822
as
Token as
Feature activation+2.294
dramatic
Token dramatic
Feature activation+0.654
,
Token,
Feature activation+0.002
K
Token K
Feature activation+0.000
week
Token week
Feature activation+0.000
and
Token and
Feature activation+0.000
see
Token see
Feature activation+0.000
how
Token how
Feature activation+0.000
things
Token things
Feature activation+0.000
go
Token go
Feature activation+1.282
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
relations
Token relations
Feature activation+0.000
between
Token between
Feature activation+0.000
Tokyo
Token Tokyo
Feature activation+0.000
and
Token and
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.000
have
Token have
Feature activation+1.422
been
Token been
Feature activation+1.608
m
Token m
Feature activation+0.144
ired
Tokenired
Feature activation+0.759
in
Token in
Feature activation+0.894
distrust
Token distrust
Feature activation+0.000

INTERVAL 0.523 - 1.047
CONTAINS 0.007%

again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+3.566
very
Token very
Feature activation+0.883
easily
Token easily
Feature activation+5.235
go
Token go
Feature activation+3.224
from
Token from
Feature activation+3.121
bad
Token bad
Feature activation+0.000
to
Token to
Feature activation+0.132
forcing
Token forcing
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
things
Token things
Feature activation+0.000
against
Token against
Feature activation+0.731
their
Token their
Feature activation+0.000
will
Token will
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
matters
Token matters
Feature activation+0.000
into
Token into
Feature activation+0.963
their
Token their
Feature activation+0.089
own
Token own
Feature activation+0.011
hands
Token hands
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
go
Token go
Feature activation+0.000
things
Token things
Feature activation+0.000
like
Token like
Feature activation+0.551
this
Token this
Feature activation+0.653
public
Token public
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
week
Token week
Feature activation+0.000
of
Token of
Feature activation+0.000
April
Token April
Feature activation+0.000
,
Token,
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
will
Token will
Feature activation+0.577
be
Token be
Feature activation+0.842
favorable
Token favorable
Feature activation+0.000
for
Token for
Feature activation+0.000
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.523
CONTAINS 99.979%

other
Token other
Feature activation+0.000
children
Token children
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
twenty
Token twenty
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
8
Token 8
Feature activation+0.000
October
Token October
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
bombed
Token bombed
Feature activation+0.000
the
Token the
Feature activation+0.000
Ze
Token Ze
Feature activation+0.000
ppelin
Tokenppelin
Feature activation+0.000
execute
Token execute
Feature activation+0.000
temp
Token temp
Feature activation+0.000
est
Tokenest
Feature activation+0.000
tests
Token tests
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
collect
Token collect
Feature activation+0.000
logs
Token logs
Feature activation+0.000
,
Token,
Feature activation+0.000
configure
Token configure
Feature activation+0.000
"
Token "
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.000
lost
Token lost
Feature activation+0.000
faith
Token faith
Feature activation+0.000
in
Token in
Feature activation+0.000
Luis
Token Luis
Feature activation+0.000
Enrique
Token Enrique
Feature activation+0.000
plea
Token plea
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Mandatory
Token Mandatory
Feature activation+0.000
public
Token public
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 H7.8: (feature 48052)

TOP ACTIVATIONS
MAX = 4.333

big
Tokenbig
Feature activation+0.000
brother
Token brother
Feature activation+0.000
'
Token'
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.333
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Nation
TokenNation
Feature activation+0.000
wide
Tokenwide
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
happened
Token happened
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.263
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Di
TokenDi
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
window
Token window
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.256
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
does
Token does
Feature activation+0.000
into
Token into
Feature activation+0.000
Spurs
Token Spurs
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
role
Token role
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.236
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Following
TokenFollowing
Feature activation+0.000
towards
Token towards
Feature activation+0.000
a
Token a
Feature activation+0.000
softer
Token softer
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.923
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
follows
Token follows
Feature activation+0.000
as
Token as
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
slows
Token slows
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.887
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.000
Geological
Token Geological
Feature activation+0.000
London
Token London
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
in
Token in
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.441
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
significant
Token significant
Feature activation+0.000
if
Token if
Feature activation+0.000
online
Token online
Feature activation+0.000
child
Token child
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
operation
Token operation
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.541
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
police
Token police
Feature activation+0.000
chief
Token chief
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.536
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
yet
Token yet
Feature activation+0.000
matched
Token matched
Feature activation+0.000
by
Token by
Feature activation+0.000
actions
Token actions
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.495
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.384
Around
Token Around
Feature activation+0.000
The
Token The
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
content
Token content
Feature activation+0.000
on
Token on
Feature activation+1.140
NFL
Token NFL
Feature activation+0.000
NOW
Token NOW
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Google
TokenGoogle
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
latest
Token latest
Feature activation+0.000
Around
Token Around
Feature activation+0.000
The
Token The
Feature activation+0.000
NFL
Token NFL
Feature activation+1.020
Podcast
Token Podcast
Feature activation+0.000
rec
Token rec
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
every
Token every
Feature activation+0.000
Wild
Token Wild
Feature activation+0.000
it
Token it
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
govern
Token govern
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.937
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
data
Token data
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Reading
TokenReading
Feature activation+0.000
this
Token this
Feature activation+0.000
on
Token on
Feature activation+0.416
your
Token your
Feature activation+0.000
phone
Token phone
Feature activation+0.000
or
Token or
Feature activation+0.000
tablet
Token tablet
Feature activation+0.000
?
Token?
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Cowboys
Token Cowboys
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
Share
Token Share
Feature activation+0.000
This
Token This
Feature activation+0.412
Story
Token Story
Feature activation+0.000
On
Token On
Feature activation+0.000
...
Token...
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Division
Token Division
Feature activation+0.000
al
Tokenal
Feature activation+0.000
Round
Token Round
Feature activation+0.000
.
Token.
Feature activation+0.000
Find
Token Find
Feature activation+0.000
more
Token more
Feature activation+0.384
Around
Token Around
Feature activation+0.000
The
Token The
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
content
Token content
Feature activation+0.000
on
Token on
Feature activation+1.140
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
doing
Token doing
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.089
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
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
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
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

Top DFA by src position
MAX = 7.358

<|endoftext|>
Token<|endoftext|>
Feature activation+7.060
Top resid features:
was
Token was
Feature activation-0.061
Top resid features:
recently
Token recently
Feature activation-0.003
Top resid features:
revealed
Token revealed
Feature activation-0.006
Top resid features:
that
Token that
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.148
Top resid features:
s
Tokens
Feature activation-0.011
Top resid features:
motion
Token motion
Feature activation-0.064
Top resid features:
came
Token came
Feature activation-0.022
Top resid features:
less
Token less
Feature activation-0.004
Top resid features:
than
Token than
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.007
Top resid features:
án
Tokenán
Feature activation-0.122
Top resid features:
che
Tokenche
Feature activation+0.005
Top resid features:
z
Tokenz
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.036
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.092
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
club
Token club
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.270
Top resid features:
to
Token to
Feature activation-0.036
Top resid features:
exist
Token exist
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
David
TokenDavid
Feature activation-0.020
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.034
Top resid features:
for
Token for
Feature activation-0.011
Top resid features:
lots
Token lots
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
death
Token death
Feature activation-0.004
Top resid features:
threats
Token threats
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.102
Top resid features:
gold
Token gold
Feature activation-0.027
Top resid features:
flags
Token flags
Feature activation-0.015
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
banners
Token banners
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.129
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
bring
Token bring
Feature activation-0.015
Top resid features:
every
Token every
Feature activation-0.002
Top resid features:
offender
Token offender
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.864
Top resid features:
the
Token the
Feature activation-0.048
Top resid features:
EU
Token EU
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
not
Token not
Feature activation-0.003
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.799
Top resid features:
with
Token with
Feature activation-0.230
Top resid features:
talk
Token talk
Feature activation-0.190
Top resid features:
of
Token of
Feature activation-0.239
Top resid features:
change
Token change
Feature activation-0.057
Top resid features:
not
Token not
Feature activation-0.069
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+5.859
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Tav
Token Tav
Feature activation-0.008
Top resid features:
on
Tokenon
Feature activation-0.002
Top resid features:
Austin
Token Austin
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+5.779
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Tav
Token Tav
Feature activation-0.006
Top resid features:
on
Tokenon
Feature activation-0.002
Top resid features:
Austin
Token Austin
Feature activation-0.005
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.900
Top resid features:
be
Token be
Feature activation+0.012
Top resid features:
exploited
Token exploited
Feature activation-0.033
Top resid features:
by
Token by
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
publishing
Token publishing
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.135
Top resid features:
working
Token working
Feature activation-0.038
Top resid features:
as
Token as
Feature activation-0.014
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
prostitute
Token prostitute
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
player
Token player
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Cowboys
Token Cowboys
Feature activation-0.024
Top resid features:
secondary
Token secondary
Feature activation-0.078
Top resid features:
Share
Token Share
Feature activation+5.658
Top resid features:
This
Token This
Feature activation-0.018
Top resid features:
Story
Token Story
Feature activation+0.000
Top resid features:
On
Token On
Feature activation+0.000
Top resid features:
...
Token...
Feature activation+0.000
Top resid features:
Twitter
Token Twitter
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.197
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
Tav
Token Tav
Feature activation-0.006
Top resid features:
on
Tokenon
Feature activation-0.002
Top resid features:
Austin
Token Austin
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.753
Top resid features:
should
Token should
Feature activation-0.138
Top resid features:
be
Token be
Feature activation-0.067
Top resid features:
doing
Token doing
Feature activation-0.075
Top resid features:
Read
Token Read
Feature activation+2.034
Top resid features:
more
Token more
Feature activation+0.195
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+5.726
Top resid features:
rik
Tokenrik
Feature activation-0.542
Top resid features:
ar
Tokenar
Feature activation-0.266
Top resid features:
said
Token said
Feature activation-1.388
Top resid features:
Saturday
Token Saturday
Feature activation-1.009
Top resid features:
.
Token.
Feature activation-0.332
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.358
Top resid features:
rik
Tokenrik
Feature activation-0.125
Top resid features:
ar
Tokenar
Feature activation+0.009
Top resid features:
said
Token said
Feature activation-0.182
Top resid features:
Saturday
Token Saturday
Feature activation-0.042
Top resid features:
.
Token.
Feature activation-0.186
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+6.675
Top resid features:
rik
Tokenrik
Feature activation-0.629
Top resid features:
ar
Tokenar
Feature activation-0.144
Top resid features:
said
Token said
Feature activation-0.469
Top resid features:
Saturday
Token Saturday
Feature activation-0.050
Top resid features:
.
Token.
Feature activation-0.193
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.03

Head 2: 0.02

Head 3: 0.05

Head 4: 0.04

Head 5: 0.05

Head 6: 0.07

Head 7: 0.01

Head 8: 0.55

Head 9: 0.05

Head 10: 0.01

Head 11: 0.02

Positive logits

ovie1.85

imag1.65

similarities1.63

oneliness1.62

autobiography1.60

tastes1.59

imagining1.56

addictive1.56

vein1.53

impressions1.53

bloodstream1.51

autop1.51

raved1.50

ATED1.50

veins1.49

angler1.48

fantasies1.44

parallels1.43

stimulating1.42

insight1.41

Negative logits

ł-1.76

cific-1.75

nces-1.68

Regist-1.67

ndum-1.64

hw-1.62

arat-1.58

towed-1.55

Measure-1.54

fielded-1.54

cled-1.54

hooting-1.52

decisively-1.51

ruary-1.51

numerical-1.50

pai-1.49

fiat-1.48

ariat-1.47

Reps-1.46

haw-1.46

INTERVAL 3.900 - 4.333
CONTAINS 0.001%

big
Tokenbig
Feature activation+0.000
brother
Token brother
Feature activation+0.000
'
Token'
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.333
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Nation
TokenNation
Feature activation+0.000
wide
Tokenwide
Feature activation+0.000
,
Token,
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
window
Token window
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.256
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
does
Token does
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
happened
Token happened
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.263
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Di
TokenDi
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
into
Token into
Feature activation+0.000
Spurs
Token Spurs
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
role
Token role
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+4.236
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Following
TokenFollowing
Feature activation+0.000
towards
Token towards
Feature activation+0.000
a
Token a
Feature activation+0.000
softer
Token softer
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.923
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
follows
Token follows
Feature activation+0.000

INTERVAL 3.466 - 3.900
CONTAINS 0.000%

as
Token as
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
slows
Token slows
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.887
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.000
Geological
Token Geological
Feature activation+0.000

INTERVAL 3.033 - 3.466
CONTAINS 0.000%

London
Token London
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
in
Token in
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+3.441
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
significant
Token significant
Feature activation+0.000
if
Token if
Feature activation+0.000

INTERVAL 2.600 - 3.033
CONTAINS 0.000%

INTERVAL 2.167 - 2.600
CONTAINS 0.000%

,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.536
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
online
Token online
Feature activation+0.000
child
Token child
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
operation
Token operation
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.541
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
police
Token police
Feature activation+0.000
chief
Token chief
Feature activation+0.000
yet
Token yet
Feature activation+0.000
matched
Token matched
Feature activation+0.000
by
Token by
Feature activation+0.000
actions
Token actions
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+2.495
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 1.733 - 2.167
CONTAINS 0.000%

INTERVAL 1.300 - 1.733
CONTAINS 0.000%

INTERVAL 0.867 - 1.300
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
latest
Token latest
Feature activation+0.000
Around
Token Around
Feature activation+0.000
The
Token The
Feature activation+0.000
NFL
Token NFL
Feature activation+1.020
Podcast
Token Podcast
Feature activation+0.000
rec
Token rec
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
every
Token every
Feature activation+0.000
Wild
Token Wild
Feature activation+0.000
more
Token more
Feature activation+0.384
Around
Token Around
Feature activation+0.000
The
Token The
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
content
Token content
Feature activation+0.000
on
Token on
Feature activation+1.140
NFL
Token NFL
Feature activation+0.000
NOW
Token NOW
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Google
TokenGoogle
Feature activation+0.000
it
Token it
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
govern
Token govern
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.937
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
data
Token data
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.433 - 0.867
CONTAINS 0.000%

INTERVAL 0.000 - 0.433
CONTAINS 99.999%

would
Token would
Feature activation+0.000
reach
Token reach
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
EP
TokenEP
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
conclusion
Token conclusion
Feature activation+0.000
by
Token by
Feature activation+0.000
in
Token in
Feature activation+0.000
Zimbabwe
Token Zimbabwe
Feature activation+0.000
who
Token who
Feature activation+0.000
inspires
Token inspires
Feature activation+0.000
even
Token even
Feature activation+0.000
greater
Token greater
Feature activation+0.000
terror
Token terror
Feature activation+0.000
than
Token than
Feature activation+0.000
Mug
Token Mug
Feature activation+0.000
abe
Tokenabe
Feature activation+0.000
."
Token."
Feature activation+0.000
s
Tokens
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
Yeah
TokenYeah
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
attering
Tokenattering
Feature activation+0.000
amounts
Token amounts
Feature activation+0.000
outside
Token outside
Feature activation+0.000
groups
Token groups
Feature activation+0.000
spent
Token spent
Feature activation+0.000
to
Token to
Feature activation+0.000
oust
Token oust
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
Mor
Token Mor
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
city
Token city
Feature activation+0.000
attorney
Token attorney
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 4 in H7.8: (feature 49013)

TOP ACTIVATIONS
MAX = 4.174

the
Token the
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
issue
Token issue
Feature activation+0.024
not
Token not
Feature activation+3.654
only
Token only
Feature activation+2.729
affects
Token affects
Feature activation+0.176
overseas
Token overseas
Feature activation+0.000
talent
Token talent
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
issue
Token issue
Feature activation+0.000
isn
Token isn
Feature activation+1.003
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+3.543
whether
Token whether
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
once
Token once
Feature activation+0.000
supported
Token supported
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
issue
Token issue
Feature activation+0.000
is
Token is
Feature activation+3.522
too
Token too
Feature activation+2.248
important
Token important
Feature activation+0.636
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
need
Token need
Feature activation+0.000
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384
if
Token if
Feature activation+0.630
any
Token any
Feature activation+0.000
ceasefire
Token ceasefire
Feature activation+0.000
were
Token were
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384
if
Token if
Feature activation+0.630
Child
TokenChild
Feature activation+0.000
pornography
Token pornography
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.016
they
Token they
Feature activation+3.313
understand
Token understand
Feature activation+2.589
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Schl
Token Schl
Feature activation+0.000
issues
Token issues
Feature activation+0.898
that
Token that
Feature activation+2.797
divide
Token divide
Feature activation+0.000
us
Token us
Feature activation+0.652
must
Token must
Feature activation+2.684
be
Token be
Feature activation+3.290
settled
Token settled
Feature activation+0.582
at
Token at
Feature activation+0.320
the
Token the
Feature activation+0.450
federal
Token federal
Feature activation+0.479
level
Token level
Feature activation+0.301
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
should
Token should
Feature activation+2.962
be
Token be
Feature activation+3.239
put
Token put
Feature activation+2.864
to
Token to
Feature activation+1.608
the
Token the
Feature activation+0.847
public
Token public
Feature activation+0.176
through
Token through
Feature activation+0.831
into
Token into
Feature activation+0.000
detail
Token detail
Feature activation+0.000
until
Token until
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.409
came
Token came
Feature activation+3.102
back
Token back
Feature activation+1.749
to
Token to
Feature activation+1.304
the
Token the
Feature activation+1.557
council
Token council
Feature activation+0.000
when
Token when
Feature activation+0.103
like
Token like
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
issue
Token issue
Feature activation+0.000
here
Token here
Feature activation+3.100
is
Token is
Feature activation+2.164
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
and
Token and
Feature activation+0.000
institutional
Token institutional
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
important
Token important
Feature activation+0.000
issue
Token issue
Feature activation+0.571
that
Token that
Feature activation+2.852
was
Token was
Feature activation+2.396
either
Token either
Feature activation+3.088
left
Token left
Feature activation+2.144
out
Token out
Feature activation+0.628
of
Token of
Feature activation+1.924
the
Token the
Feature activation+1.510
presidential
Token presidential
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Nile
Token Nile
Feature activation+0.000
water
Token water
Feature activation+0.000
issue
Token issue
Feature activation+0.270
has
Token has
Feature activation+3.085
paramount
Token paramount
Feature activation+1.318
importance
Token importance
Feature activation+0.887
in
Token in
Feature activation+1.483
all
Token all
Feature activation+0.896
of
Token of
Feature activation+0.848
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
matter
Token matter
Feature activation+0.165
is
Token is
Feature activation+3.044
listed
Token listed
Feature activation+1.465
for
Token for
Feature activation+1.186
hearing
Token hearing
Feature activation+0.274
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
migration
Token migration
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
-
Token -
Feature activation+0.000
issues
Token issues
Feature activation+0.955
that
Token that
Feature activation+2.967
have
Token have
Feature activation+2.957
become
Token become
Feature activation+2.824
more
Token more
Feature activation+2.832
contentious
Token contentious
Feature activation+0.834
since
Token since
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
should
Token should
Feature activation+2.962
be
Token be
Feature activation+3.239
put
Token put
Feature activation+2.864
to
Token to
Feature activation+1.608
the
Token the
Feature activation+0.847
public
Token public
Feature activation+0.176
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
-
Token -
Feature activation+0.000
issues
Token issues
Feature activation+0.955
that
Token that
Feature activation+2.967
have
Token have
Feature activation+2.957
become
Token become
Feature activation+2.824
more
Token more
Feature activation+2.832
contentious
Token contentious
Feature activation+0.834
since
Token since
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
matter
Token matter
Feature activation+0.000
has
Token has
Feature activation+1.927
been
Token been
Feature activation+2.943
fought
Token fought
Feature activation+0.000
in
Token in
Feature activation+0.270
New
Token New
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
's
Token's
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.616
in
Token in
Feature activation+2.940
the
Token the
Feature activation+2.382
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
or
Token or
Feature activation+0.228
in
Token in
Feature activation+1.829
and
Token and
Feature activation+0.000
boys
Token boys
Feature activation+0.000
because
Token because
Feature activation+0.000
that
Token that
Feature activation+0.080
issue
Token issue
Feature activation+0.756
receives
Token receives
Feature activation+2.923
much
Token much
Feature activation+0.874
less
Token less
Feature activation+0.915
attention
Token attention
Feature activation+0.426
than
Token than
Feature activation+2.382
equal
Token equal
Feature activation+0.000

Top DFA by src position
MAX = 5.058

for
Token for
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
conflict
Token conflict
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
an
Token an
Feature activation+0.045
Top resid features:
issue
Token issue
Feature activation+5.058
Top resid features:
that
Token that
Feature activation+0.085
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
This
TokenThis
Feature activation+0.037
Top resid features:
issue
Token issue
Feature activation+4.643
Top resid features:
not
Token not
Feature activation+0.131
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
affects
Token affects
Feature activation+0.000
Top resid features:
overseas
Token overseas
Feature activation+0.000
Top resid features:
talent
Token talent
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
So
TokenSo
Feature activation+0.033
Top resid features:
what
Token what
Feature activation+0.008
Top resid features:
?
Token?
Feature activation+0.148
Top resid features:
The
Token The
Feature activation+0.034
Top resid features:
issue
Token issue
Feature activation+4.024
Top resid features:
isn
Token isn
Feature activation+0.623
Top resid features:
âĢ
TokenâĢ
Feature activation-0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.025
Top resid features:
t
Tokent
Feature activation+0.001
Top resid features:
whether
Token whether
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.007
Top resid features:
once
Token once
Feature activation-0.013
Top resid features:
supported
Token supported
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.096
Top resid features:
This
Token This
Feature activation+0.086
Top resid features:
issue
Token issue
Feature activation+4.614
Top resid features:
is
Token is
Feature activation+0.102
Top resid features:
too
Token too
Feature activation+0.000
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
conflict
Token conflict
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.037
Top resid features:
an
Token an
Feature activation+0.027
Top resid features:
issue
Token issue
Feature activation+4.162
Top resid features:
that
Token that
Feature activation+0.184
Top resid features:
would
Token would
Feature activation+0.045
Top resid features:
have
Token have
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.044
Top resid features:
be
Token be
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
conflict
Token conflict
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.061
Top resid features:
an
Token an
Feature activation+0.056
Top resid features:
issue
Token issue
Feature activation+3.860
Top resid features:
that
Token that
Feature activation+0.358
Top resid features:
would
Token would
Feature activation+0.073
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
Child
TokenChild
Feature activation+0.001
Top resid features:
pornography
Token pornography
Feature activation-0.012
Top resid features:
is
Token is
Feature activation+0.045
Top resid features:
an
Token an
Feature activation+0.091
Top resid features:
issue
Token issue
Feature activation+4.291
Top resid features:
they
Token they
Feature activation+0.022
Top resid features:
understand
Token understand
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:
dehuman
Token dehuman
Feature activation-0.004
Top resid features:
izing
Tokenizing
Feature activation-0.004
Top resid features:
assumption
Token assumption
Feature activation+0.079
Top resid features:
that
Token that
Feature activation+0.164
Top resid features:
all
Token all
Feature activation+0.083
Top resid features:
issues
Token issues
Feature activation+4.092
Top resid features:
that
Token that
Feature activation+0.115
Top resid features:
divide
Token divide
Feature activation+0.113
Top resid features:
us
Token us
Feature activation-0.038
Top resid features:
must
Token must
Feature activation+0.050
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
Abbott
Token Abbott
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.049
Top resid features:
on
Token on
Feature activation+0.005
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
issue
Token issue
Feature activation+4.264
Top resid features:
should
Token should
Feature activation+0.087
Top resid features:
be
Token be
Feature activation+0.038
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
go
Token go
Feature activation-0.001
Top resid features:
into
Token into
Feature activation+0.038
Top resid features:
detail
Token detail
Feature activation+0.054
Top resid features:
until
Token until
Feature activation-0.022
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
matter
Token matter
Feature activation+4.127
Top resid features:
came
Token came
Feature activation+0.084
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
council
Token council
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
like
Token like
Feature activation+0.005
Top resid features:
Obamacare
Token Obamacare
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
The
Token The
Feature activation+0.131
Top resid features:
issue
Token issue
Feature activation+3.978
Top resid features:
here
Token here
Feature activation-0.021
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
role
Token role
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.024
Top resid features:
urgent
Token urgent
Feature activation+0.119
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
hugely
Token hugely
Feature activation-0.002
Top resid features:
important
Token important
Feature activation+0.051
Top resid features:
issue
Token issue
Feature activation+3.223
Top resid features:
that
Token that
Feature activation+0.311
Top resid features:
was
Token was
Feature activation+0.362
Top resid features:
either
Token either
Feature activation+0.016
Top resid features:
left
Token left
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.218
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
Nile
Token Nile
Feature activation+0.004
Top resid features:
water
Token water
Feature activation-0.013
Top resid features:
issue
Token issue
Feature activation+3.629
Top resid features:
has
Token has
Feature activation+0.082
Top resid features:
paramount
Token paramount
Feature activation+0.000
Top resid features:
importance
Token importance
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
functioning
Token functioning
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
The
TokenThe
Feature activation+0.039
Top resid features:
matter
Token matter
Feature activation+3.900
Top resid features:
is
Token is
Feature activation+0.111
Top resid features:
listed
Token listed
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
hearing
Token hearing
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.085
Top resid features:
migration
Token migration
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+0.074
Top resid features:
Saturday
Token Saturday
Feature activation+0.069
Top resid features:
-
Token -
Feature activation+0.071
Top resid features:
issues
Token issues
Feature activation+3.584
Top resid features:
that
Token that
Feature activation+0.094
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
contentious
Token contentious
Feature activation+0.000
Top resid features:
Abbott
Token Abbott
Feature activation-0.005
Top resid features:
said
Token said
Feature activation+0.066
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
issue
Token issue
Feature activation+3.936
Top resid features:
should
Token should
Feature activation+0.077
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.023
Top resid features:
migration
Token migration
Feature activation+0.032
Top resid features:
on
Token on
Feature activation+0.026
Top resid features:
Saturday
Token Saturday
Feature activation+0.020
Top resid features:
-
Token -
Feature activation+0.056
Top resid features:
issues
Token issues
Feature activation+3.583
Top resid features:
that
Token that
Feature activation+0.229
Top resid features:
have
Token have
Feature activation+0.039
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
contentious
Token contentious
Feature activation+0.000
Top resid features:
marriage
Token marriage
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
The
TokenThe
Feature activation+0.008
Top resid features:
matter
Token matter
Feature activation+3.847
Top resid features:
has
Token has
Feature activation+0.180
Top resid features:
been
Token been
Feature activation+0.027
Top resid features:
fought
Token fought
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.117
Top resid features:
They
Token They
Feature activation+0.023
Top resid features:
were
Token were
Feature activation+0.064
Top resid features:
not
Token not
Feature activation+0.039
Top resid features:
an
Token an
Feature activation+0.091
Top resid features:
issue
Token issue
Feature activation+3.951
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
presidential
Token presidential
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
men
Token men
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
boys
Token boys
Feature activation+0.005
Top resid features:
because
Token because
Feature activation+0.051
Top resid features:
that
Token that
Feature activation+0.032
Top resid features:
issue
Token issue
Feature activation+3.902
Top resid features:
receives
Token receives
Feature activation+0.116
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
attention
Token attention
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.01

Head 3: 0.11

Head 4: 0.03

Head 5: 0.06

Head 6: 0.06

Head 7: 0.02

Head 8: 0.55

Head 9: 0.06

Head 10: 0.01

Head 11: 0.01

Positive logits

unresolved2.23

topic2.15

debated2.14

issues1.95

concern1.91

Topic1.89

raged1.87

concerns1.87

topics1.86

igated1.82

thorn1.82

priority1.81

hotly1.81

discussed1.80

matter1.79

priority1.79

debates1.76

questions1.76

discussion1.75

resolved1.74

Negative logits

ramids-1.86

dup-1.77

ramid-1.72

enium-1.70

owment-1.63

parach-1.58

eah-1.50

imitation-1.50

nylon-1.46

Phelps-1.46

stocking-1.46

acc-1.45

gull-1.43

strut-1.43

disg-1.42

urn-1.42

OOL-1.42

footprints-1.40

parachute-1.38

equivalents-1.38

INTERVAL 3.756 - 4.174
CONTAINS 0.000%

the
Token the
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384

INTERVAL 3.339 - 3.756
CONTAINS 0.001%

once
Token once
Feature activation+0.000
supported
Token supported
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
issue
Token issue
Feature activation+0.000
is
Token is
Feature activation+3.522
too
Token too
Feature activation+2.248
important
Token important
Feature activation+0.636
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
need
Token need
Feature activation+0.000
The
Token The
Feature activation+0.000
issue
Token issue
Feature activation+0.000
isn
Token isn
Feature activation+1.003
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+3.543
whether
Token whether
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
issue
Token issue
Feature activation+0.024
not
Token not
Feature activation+3.654
only
Token only
Feature activation+2.729
affects
Token affects
Feature activation+0.176
overseas
Token overseas
Feature activation+0.000
talent
Token talent
Feature activation+0.000
,
Token,
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384
if
Token if
Feature activation+0.630
issue
Token issue
Feature activation+1.908
that
Token that
Feature activation+4.174
would
Token would
Feature activation+3.348
have
Token have
Feature activation+2.782
to
Token to
Feature activation+2.788
be
Token be
Feature activation+3.452
tackled
Token tackled
Feature activation+1.384
if
Token if
Feature activation+0.630
any
Token any
Feature activation+0.000
ceasefire
Token ceasefire
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 2.922 - 3.339
CONTAINS 0.001%

hugely
Token hugely
Feature activation+0.000
important
Token important
Feature activation+0.000
issue
Token issue
Feature activation+0.571
that
Token that
Feature activation+2.852
was
Token was
Feature activation+2.396
either
Token either
Feature activation+3.088
left
Token left
Feature activation+2.144
out
Token out
Feature activation+0.628
of
Token of
Feature activation+1.924
the
Token the
Feature activation+1.510
presidential
Token presidential
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
should
Token should
Feature activation+2.962
be
Token be
Feature activation+3.239
put
Token put
Feature activation+2.864
to
Token to
Feature activation+1.608
the
Token the
Feature activation+0.847
public
Token public
Feature activation+0.176
through
Token through
Feature activation+0.831
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.616
in
Token in
Feature activation+2.940
the
Token the
Feature activation+2.382
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
or
Token or
Feature activation+0.228
in
Token in
Feature activation+1.829
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
matter
Token matter
Feature activation+0.165
is
Token is
Feature activation+3.044
listed
Token listed
Feature activation+1.465
for
Token for
Feature activation+1.186
hearing
Token hearing
Feature activation+0.274
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
Child
TokenChild
Feature activation+0.000
pornography
Token pornography
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.016
they
Token they
Feature activation+3.313
understand
Token understand
Feature activation+2.589
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Schl
Token Schl
Feature activation+0.000

INTERVAL 2.504 - 2.922
CONTAINS 0.003%

Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
will
Token will
Feature activation+2.720
be
Token be
Feature activation+2.774
given
Token given
Feature activation+2.073
proper
Token proper
Feature activation+0.365
consideration
Token consideration
Feature activation+0.401
.
Token.
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
-
Token -
Feature activation+0.000
issues
Token issues
Feature activation+0.955
that
Token that
Feature activation+2.967
have
Token have
Feature activation+2.957
become
Token become
Feature activation+2.824
more
Token more
Feature activation+2.832
contentious
Token contentious
Feature activation+0.834
since
Token since
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
entered
Token entered
Feature activation+0.000
pornography
Token pornography
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.016
they
Token they
Feature activation+3.313
understand
Token understand
Feature activation+2.589
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Schl
Token Schl
Feature activation+0.000
ü
Tokenü
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
status
Token status
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
topic
Token topic
Feature activation+0.494
that
Token that
Feature activation+2.894
prompted
Token prompted
Feature activation+0.692
banter
Token banter
Feature activation+0.000
between
Token between
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token -
Feature activation+0.000
issues
Token issues
Feature activation+0.955
that
Token that
Feature activation+2.967
have
Token have
Feature activation+2.957
become
Token become
Feature activation+2.824
more
Token more
Feature activation+2.832
contentious
Token contentious
Feature activation+0.834
since
Token since
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.087 - 2.504
CONTAINS 0.004%

the
Token the
Feature activation+0.000
important
Token important
Feature activation+0.000
issues
Token issues
Feature activation+0.000
that
Token that
Feature activation+1.805
we
Token we
Feature activation+2.717
need
Token need
Feature activation+2.143
to
Token to
Feature activation+2.424
from
Token from
Feature activation+0.067
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.616
in
Token in
Feature activation+2.940
the
Token the
Feature activation+2.382
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
or
Token or
Feature activation+0.228
in
Token in
Feature activation+1.829
the
Token the
Feature activation+0.887
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
topic
Token topic
Feature activation+0.000
of
Token of
Feature activation+0.000
racism
Token racism
Feature activation+0.000
has
Token has
Feature activation+2.242
arrived
Token arrived
Feature activation+1.076
per
Token per
Feature activation+0.000
force
Token force
Feature activation+0.000
in
Token in
Feature activation+0.286
the
Token the
Feature activation+0.018
if
Token if
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
important
Token important
Feature activation+0.000
question
Token question
Feature activation+0.623
gets
Token gets
Feature activation+2.163
caught
Token caught
Feature activation+1.335
up
Token up
Feature activation+0.466
in
Token in
Feature activation+1.253
party
Token party
Feature activation+0.000
political
Token political
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
topic
Token topic
Feature activation+0.000
of
Token of
Feature activation+0.000
kissing
Token kissing
Feature activation+0.000
came
Token came
Feature activation+2.417
up
Token up
Feature activation+1.330
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.669 - 2.087
CONTAINS 0.006%

's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
safety
Token safety
Feature activation+0.000
issue
Token issue
Feature activation+0.000
that
Token that
Feature activation+1.907
blows
Token blows
Feature activation+0.451
up
Token up
Feature activation+0.230
âĢĶ
Token âĢĶ
Feature activation+0.007
like
Token like
Feature activation+0.810
when
Token when
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
topic
Token topic
Feature activation+0.000
in
Token in
Feature activation+1.744
its
Token its
Feature activation+0.151
own
Token own
Feature activation+0.347
right
Token right
Feature activation+0.550
,
Token,
Feature activation+0.446
but
Token but
Feature activation+0.100
issues
Token issues
Feature activation+0.000
we
Token we
Feature activation+2.792
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.832
got
Token got
Feature activation+1.794
to
Token to
Feature activation+2.196
be
Token be
Feature activation+1.125
able
Token able
Feature activation+0.850
to
Token to
Feature activation+2.452
work
Token work
Feature activation+0.286
most
Tokenmost
Feature activation+0.000
-
Token-
Feature activation+0.000
important
Tokenimportant
Feature activation+0.000
issue
Token issue
Feature activation+0.494
in
Token in
Feature activation+1.519
the
Token the
Feature activation+1.974
election
Token election
Feature activation+0.000
after
Token after
Feature activation+1.598
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
issues
Token issues
Feature activation+0.000
which
Token which
Feature activation+1.749
were
Token were
Feature activation+1.700
not
Token not
Feature activation+1.490
communicated
Token communicated
Feature activation+0.445
to
Token to
Feature activation+0.540
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.154

INTERVAL 1.252 - 1.669
CONTAINS 0.008%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
issues
Token issues
Feature activation+0.000
that
Token that
Feature activation+1.921
does
Token does
Feature activation+0.762
not
Token not
Feature activation+1.607
get
Token get
Feature activation+1.094
talked
Token talked
Feature activation+0.000
about
Token about
Feature activation+0.000
that
Token that
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
topic
Token topic
Feature activation+0.000
is
Token is
Feature activation+1.467
important
Token important
Feature activation+0.000
to
Token to
Feature activation+1.194
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
subject
Token subject
Feature activation+0.000
of
Token of
Feature activation+0.000
violence
Token violence
Feature activation+0.000
is
Token is
Feature activation+0.979
so
Token so
Feature activation+1.447
gigantic
Token gigantic
Feature activation+1.162
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
Pink
Token Pink
Feature activation+0.000
er
Tokener
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
FTC
Token FTC
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
it
Token it
Feature activation+0.777
to
Token to
Feature activation+1.423
court
Token court
Feature activation+0.014
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Another
TokenAnother
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.502
certainly
Token certainly
Feature activation+2.811
doesn
Token doesn
Feature activation+1.309
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.288
t
Tokent
Feature activation+0.303
warrant
Token warrant
Feature activation+0.824
such
Token such
Feature activation+0.000

INTERVAL 0.835 - 1.252
CONTAINS 0.012%

huge
Token huge
Feature activation+0.000
complex
Token complex
Feature activation+0.000
issue
Token issue
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.211
it
Token it
Feature activation+0.995
who
Token who
Feature activation+0.000
stood
Token stood
Feature activation+0.000
against
Token against
Feature activation+0.003
so
Token so
Feature activation+0.224
much
Token much
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
issue
Token issue
Feature activation+0.000
twenty
Token twenty
Feature activation+0.270
years
Token years
Feature activation+1.171
on
Token on
Feature activation+0.738
is
Token is
Feature activation+0.123
not
Token not
Feature activation+0.998
with
Token with
Feature activation+0.000
age
Token age
Feature activation+0.000
voting
Token voting
Feature activation+0.000
and
Token and
Feature activation+0.000
solves
Token solves
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
that
Token that
Feature activation+0.840
doesn
Token doesn
Feature activation+0.694
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.301
t
Tokent
Feature activation+0.756
exist
Token exist
Feature activation+0.933
social
Token social
Feature activation+0.000
and
Token and
Feature activation+0.000
political
Token political
Feature activation+0.135
issues
Token issues
Feature activation+0.000
of
Token of
Feature activation+0.713
our
Token our
Feature activation+1.243
day
Token day
Feature activation+0.776
are
Token are
Feature activation+0.000
nuanced
Token nuanced
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
because
Token because
Feature activation+0.000
that
Token that
Feature activation+0.080
issue
Token issue
Feature activation+0.756
receives
Token receives
Feature activation+2.923
much
Token much
Feature activation+0.874
less
Token less
Feature activation+0.915
attention
Token attention
Feature activation+0.426
than
Token than
Feature activation+2.382
equal
Token equal
Feature activation+0.000
rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.417 - 0.835
CONTAINS 0.034%

off
Token off
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.534
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.298
On
TokenOn
Feature activation+0.000
defence
Token defence
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.053
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.161
find
Token find
Feature activation+0.712
,
Token,
Feature activation+0.247
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
mis
Token mis
Feature activation+0.000
stat
Tokenstat
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
this
Token this
Feature activation+0.000
element
Token element
Feature activation+0.000
that
Token that
Feature activation+0.532
sparked
Token sparked
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
pri
Tokenpri
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
to
Token to
Feature activation+0.000
question
Token question
Feature activation+0.000
of
Token of
Feature activation+0.000
succession
Token succession
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.994
will
Token will
Feature activation+0.673
be
Token be
Feature activation+0.361
addressed
Token addressed
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
shame
Token shame
Feature activation+0.000
if
Token if
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
important
Token important
Feature activation+0.000
question
Token question
Feature activation+0.623
gets
Token gets
Feature activation+2.163
caught
Token caught
Feature activation+1.335
up
Token up
Feature activation+0.466
in
Token in
Feature activation+1.253
party
Token party
Feature activation+0.000

INTERVAL 0.000 - 0.417
CONTAINS 99.932%

seize
Token seize
Feature activation+0.000
with
Token with
Feature activation+0.000
authority
Token authority
Feature activation+0.000
or
Token or
Feature activation+0.000
legal
Token legal
Feature activation+0.000
right
Token right
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
lead
Token lead
Feature activation+0.000
out
Token out
Feature activation+0.000
trains
Token trains
Feature activation+0.000
built
Token built
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
around
Token around
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
key
Token key
Feature activation+0.000
spr
Token spr
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
been
Token been
Feature activation+0.000
touted
Token touted
Feature activation+0.000
to
Token to
Feature activation+0.000
justify
Token justify
Feature activation+0.000
the
Token the
Feature activation+0.000
prof
Token prof
Feature activation+0.000
usion
Tokenusion
Feature activation+0.000
of
Token of
Feature activation+0.000
official
Token official
Feature activation+0.000
posts
Token posts
Feature activation+0.000
to
Token to
Feature activation+0.000
roster
Token roster
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
challenging
Token challenging
Feature activation+0.000
for
Token for
Feature activation+0.000
trophies
Token trophies
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
real
Token real
Feature activation+0.000
complaint
Token complaint
Feature activation+0.000
in
Token in
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
otherwise
Token otherwise
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 H7.8: (feature 10277)

TOP ACTIVATIONS
MAX = 3.452

the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+3.452
are
Token are
Feature activation+3.063
hurt
Token hurt
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+3.374
too
Token too
Feature activation+3.298
short
Token short
Feature activation+0.075
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+3.374
too
Token too
Feature activation+3.298
short
Token short
Feature activation+0.075
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
go
Token go
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
to
Token to
Feature activation+0.294
his
Token his
Feature activation+1.768
Achilles
Token Achilles
Feature activation+0.000
that
Token that
Feature activation+3.228
caused
Token caused
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
miss
Token miss
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+3.452
are
Token are
Feature activation+3.063
hurt
Token hurt
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
so
Token so
Feature activation+0.000
her
Token her
Feature activation+1.896
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
a
Token a
Feature activation+1.987
short
Token short
Feature activation+0.515
military
Token military
Feature activation+0.000
style
Token style
Feature activation+0.459
.
Token.
Feature activation+0.000
24
Token 24
Feature activation+0.000
hours
Token hours
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
-
Token-
Feature activation+2.823
price
Tokenprice
Feature activation+0.000
£
Token £
Feature activation+0.000
6
Token6
Feature activation+0.000
.
Token.
Feature activation+0.000
25
Token25
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
provinces
Token provinces
Feature activation+2.006
put
Token put
Feature activation+1.534
in
Token in
Feature activation+2.391
place
Token place
Feature activation+0.222
stop
Token stop
Feature activation+0.000
gap
Tokengap
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
health
Token health
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
rage
Token rage
Feature activation+0.000
against
Token against
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+2.379
don
Token don
Feature activation+1.479
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.333
cut
Token cut
Feature activation+0.000
's
Token's
Feature activation+0.000
family
Token family
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
-
Token-
Feature activation+2.315
rate
Tokenrate
Feature activation+0.000
wing
Token wing
Feature activation+0.000
nut
Tokennut
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
cut
Token cut
Feature activation+0.000
out
Token out
Feature activation+0.394
with
Token with
Feature activation+2.239
a
Token a
Feature activation+1.881
knife
Token knife
Feature activation+0.045
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
cut
Token cut
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
cut
Token cut
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
chicken
Token chicken
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
already
Token already
Feature activation+0.000
cut
Token cut
Feature activation+0.000
and
Token and
Feature activation+2.058
just
Token just
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
tip
Token tip
Feature activation+0.000
it
Token it
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
,
Token,
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
provinces
Token provinces
Feature activation+2.006
put
Token put
Feature activation+1.534
in
Token in
Feature activation+2.391
place
Token place
Feature activation+0.222
stop
Token stop
Feature activation+0.000
gap
Tokengap
Feature activation+0.000
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
a
Token a
Feature activation+1.987
short
Token short
Feature activation+0.515
military
Token military
Feature activation+0.000
style
Token style
Feature activation+0.459
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
military
Token military
Feature activation+0.000
policemen
Token policemen
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
her
Token her
Feature activation+1.896
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
cut
Token cut
Feature activation+0.000
out
Token out
Feature activation+0.394
with
Token with
Feature activation+2.239
a
Token a
Feature activation+1.881
knife
Token knife
Feature activation+0.045
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
said
Token said
Feature activation+0.000
patients
Token patients
Feature activation+0.000
cut
Token cut
Feature activation+0.000
their
Token their
Feature activation+0.000
gastrointestinal
Token gastrointestinal
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.920
in
Token in
Feature activation+1.881
half
Token half
Feature activation+0.000
when
Token when
Feature activation+0.087
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
21
Token 21
Feature activation+0.000
income
Token income
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
he
Token he
Feature activation+0.000
cut
Token cut
Feature activation+0.000
in
Token in
Feature activation+1.825
this
Token this
Feature activation+1.855
current
Token current
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
budget
Token budget
Feature activation+0.000

Top DFA by src position
MAX = 4.668

sees
Token sees
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
same
Token same
Feature activation-0.007
Top resid features:
thing
Token thing
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.034
Top resid features:
cuts
Token cuts
Feature activation+4.668
Top resid features:
that
Token that
Feature activation+0.038
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
hurt
Token hurt
Feature activation+0.000
Top resid features:
ful
Tokenful
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
his
Token his
Feature activation+0.020
Top resid features:
life
Token life
Feature activation-0.020
Top resid features:
was
Token was
Feature activation-0.005
Top resid features:
cut
Token cut
Feature activation+4.554
Top resid features:
far
Token far
Feature activation+0.031
Top resid features:
too
Token too
Feature activation+0.000
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
My
Token My
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
life
Token life
Feature activation-0.050
Top resid features:
was
Token was
Feature activation+0.022
Top resid features:
cut
Token cut
Feature activation+4.590
Top resid features:
far
Token far
Feature activation+0.044
Top resid features:
too
Token too
Feature activation-0.048
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
My
Token My
Feature activation+0.000
Top resid features:
in
Tokenin
Feature activation-0.003
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
recovering
Token recovering
Feature activation+0.059
Top resid features:
from
Token from
Feature activation+0.049
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
cut
Token cut
Feature activation+3.711
Top resid features:
to
Token to
Feature activation+0.617
Top resid features:
his
Token his
Feature activation+0.024
Top resid features:
Achilles
Token Achilles
Feature activation+0.014
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
caused
Token caused
Feature activation+0.000
Top resid features:
sees
Token sees
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
same
Token same
Feature activation+0.033
Top resid features:
thing
Token thing
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.027
Top resid features:
cuts
Token cuts
Feature activation+4.074
Top resid features:
that
Token that
Feature activation+0.171
Top resid features:
are
Token are
Feature activation+0.023
Top resid features:
hurt
Token hurt
Feature activation+0.000
Top resid features:
ful
Tokenful
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
two
Token two
Feature activation-0.004
Top resid features:
Scottish
Token Scottish
Feature activation+0.016
Top resid features:
military
Token military
Feature activation-0.001
Top resid features:
policemen
Token policemen
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
cut
Token cut
Feature activation+3.631
Top resid features:
her
Token her
Feature activation+0.012
Top resid features:
long
Token long
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
brown
Token brown
Feature activation+0.027
Top resid features:
hair
Token hair
Feature activation+0.208
Top resid features:
next
Token next
Feature activation-0.003
Top resid features:
24
Token 24
Feature activation-0.003
Top resid features:
hours
Token hours
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.057
Top resid features:
a
Token a
Feature activation+0.103
Top resid features:
cut
Token cut
Feature activation+3.716
Top resid features:
-
Token-
Feature activation+0.074
Top resid features:
price
Tokenprice
Feature activation+0.000
Top resid features:
£
Token £
Feature activation+0.000
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
In
TokenIn
Feature activation+0.001
Top resid features:
response
Token response
Feature activation-0.010
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
cuts
Token cuts
Feature activation+3.474
Top resid features:
Ontario
Token Ontario
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Quebec
Token Quebec
Feature activation+0.023
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
other
Token other
Feature activation+0.004
Top resid features:
2
Token2
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
rage
Token rage
Feature activation-0.003
Top resid features:
against
Token against
Feature activation-0.129
Top resid features:
cuts
Token cuts
Feature activation+3.637
Top resid features:
that
Token that
Feature activation+0.005
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:
ly
Tokenly
Feature activation+0.005
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
family
Token family
Feature activation+0.010
Top resid features:
into
Token into
Feature activation+0.037
Top resid features:
a
Token a
Feature activation+0.075
Top resid features:
cut
Token cut
Feature activation+3.201
Top resid features:
-
Token-
Feature activation+0.094
Top resid features:
rate
Tokenrate
Feature activation+0.000
Top resid features:
wing
Token wing
Feature activation+0.000
Top resid features:
nut
Tokennut
Feature activation+0.000
Top resid features:
version
Token version
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
her
Token her
Feature activation+0.031
Top resid features:
eyes
Token eyes
Feature activation+0.001
Top resid features:
had
Token had
Feature activation-0.007
Top resid features:
been
Token been
Feature activation-0.011
Top resid features:
cut
Token cut
Feature activation+2.735
Top resid features:
out
Token out
Feature activation+0.689
Top resid features:
with
Token with
Feature activation+0.010
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
knife
Token knife
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
One
TokenOne
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
them
Token them
Feature activation+0.035
Top resid features:
cut
Token cut
Feature activation+3.218
Top resid features:
my
Token my
Feature activation+0.095
Top resid features:
throat
Token throat
Feature activation-0.023
Top resid features:
with
Token with
Feature activation-0.011
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
razor
Token razor
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
One
TokenOne
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
them
Token them
Feature activation+0.072
Top resid features:
cut
Token cut
Feature activation+3.127
Top resid features:
my
Token my
Feature activation+0.022
Top resid features:
throat
Token throat
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
razor
Token razor
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
chicken
Token chicken
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.024
Top resid features:
already
Token already
Feature activation+0.064
Top resid features:
cut
Token cut
Feature activation+3.010
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
sort
Token sort
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
tip
Token tip
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
In
TokenIn
Feature activation+0.006
Top resid features:
response
Token response
Feature activation-0.127
Top resid features:
to
Token to
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
cuts
Token cuts
Feature activation+3.248
Top resid features:
Ontario
Token Ontario
Feature activation+0.171
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
Quebec
Token Quebec
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
other
Token other
Feature activation-0.038
Top resid features:
two
Token two
Feature activation-0.002
Top resid features:
Scottish
Token Scottish
Feature activation+0.022
Top resid features:
military
Token military
Feature activation+0.004
Top resid features:
policemen
Token policemen
Feature activation-0.015
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
cut
Token cut
Feature activation+2.283
Top resid features:
her
Token her
Feature activation+0.020
Top resid features:
long
Token long
Feature activation+0.056
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
brown
Token brown
Feature activation+0.019
Top resid features:
hair
Token hair
Feature activation+0.361
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
Scottish
Token Scottish
Feature activation+0.015
Top resid features:
military
Token military
Feature activation+0.011
Top resid features:
policemen
Token policemen
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
cut
Token cut
Feature activation+2.759
Top resid features:
her
Token her
Feature activation+0.060
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
brown
Token brown
Feature activation+0.000
Top resid features:
hair
Token hair
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
her
Token her
Feature activation+0.007
Top resid features:
eyes
Token eyes
Feature activation+0.002
Top resid features:
had
Token had
Feature activation-0.018
Top resid features:
been
Token been
Feature activation-0.000
Top resid features:
cut
Token cut
Feature activation+2.096
Top resid features:
out
Token out
Feature activation+0.760
Top resid features:
with
Token with
Feature activation+0.214
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
knife
Token knife
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
30
Token 30
Feature activation+0.013
Top resid features:
I
Token I
Feature activation+0.007
Top resid features:
BS
TokenBS
Feature activation+0.064
Top resid features:
patients
Token patients
Feature activation+0.038
Top resid features:
cut
Token cut
Feature activation+2.885
Top resid features:
their
Token their
Feature activation+0.134
Top resid features:
gastrointestinal
Token gastrointestinal
Feature activation+0.052
Top resid features:
symptoms
Token symptoms
Feature activation-0.029
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
income
Token income
Feature activation+0.009
Top resid features:
taxes
Token taxes
Feature activation-0.003
Top resid features:
he
Token he
Feature activation-0.011
Top resid features:
cut
Token cut
Feature activation+2.974
Top resid features:
in
Token in
Feature activation+0.098
Top resid features:
this
Token this
Feature activation-0.002
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.03

Head 2: 0.02

Head 3: 0.06

Head 4: 0.04

Head 5: 0.06

Head 6: 0.03

Head 7: 0.02

Head 8: 0.55

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

cuts2.25

wounds2.20

knife2.12

scars2.10

teeth2.06

knives1.99

axe1.98

cuts1.90

cle1.89

slit1.88

nails1.85

Cutting1.84

ision1.81

razor1.79

stitches1.79

slash1.77

scissors1.77

Sharp1.76

Cut1.74

foreskin1.73

Negative logits

ruly-1.72

anx-1.70

pired-1.69

urance-1.65

VO-1.60

mn-1.57

Alert-1.55

ylum-1.54

rier-1.54

igue-1.54

Venezuel-1.52

tc-1.52

mAh-1.51

BAT-1.50

arcity-1.50

equ-1.49

sit-1.47

akings-1.47

QUI-1.47

assurance-1.46

INTERVAL 3.106 - 3.452
CONTAINS 0.000%

and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+3.374
too
Token too
Feature activation+3.298
short
Token short
Feature activation+0.075
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+3.374
too
Token too
Feature activation+3.298
short
Token short
Feature activation+0.075
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
go
Token go
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+3.452
are
Token are
Feature activation+3.063
hurt
Token hurt
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
to
Token to
Feature activation+0.294
his
Token his
Feature activation+1.768
Achilles
Token Achilles
Feature activation+0.000
that
Token that
Feature activation+3.228
caused
Token caused
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
miss
Token miss
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.761 - 3.106
CONTAINS 0.000%

her
Token her
Feature activation+1.896
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
a
Token a
Feature activation+1.987
short
Token short
Feature activation+0.515
military
Token military
Feature activation+0.000
style
Token style
Feature activation+0.459
.
Token.
Feature activation+0.000
24
Token 24
Feature activation+0.000
hours
Token hours
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
-
Token-
Feature activation+2.823
price
Tokenprice
Feature activation+0.000
£
Token £
Feature activation+0.000
6
Token6
Feature activation+0.000
.
Token.
Feature activation+0.000
25
Token25
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+3.452
are
Token are
Feature activation+3.063
hurt
Token hurt
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
so
Token so
Feature activation+0.000

INTERVAL 2.416 - 2.761
CONTAINS 0.000%

INTERVAL 2.071 - 2.416
CONTAINS 0.001%

of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
cut
Token cut
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
rage
Token rage
Feature activation+0.000
against
Token against
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
that
Token that
Feature activation+2.379
don
Token don
Feature activation+1.479
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.333
cut
Token cut
Feature activation+0.000
's
Token's
Feature activation+0.000
family
Token family
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
cut
Token cut
Feature activation+0.000
-
Token-
Feature activation+2.315
rate
Tokenrate
Feature activation+0.000
wing
Token wing
Feature activation+0.000
nut
Tokennut
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
cut
Token cut
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
eyes
Token eyes
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
cut
Token cut
Feature activation+0.000
out
Token out
Feature activation+0.394
with
Token with
Feature activation+2.239
a
Token a
Feature activation+1.881
knife
Token knife
Feature activation+0.045
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000

INTERVAL 1.726 - 2.071
CONTAINS 0.002%

before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
sequ
Token sequ
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
went
Token went
Feature activation+1.817
into
Token into
Feature activation+0.467
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
patients
Token patients
Feature activation+0.000
cut
Token cut
Feature activation+0.000
their
Token their
Feature activation+0.000
gastrointestinal
Token gastrointestinal
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.920
in
Token in
Feature activation+1.881
half
Token half
Feature activation+0.000
when
Token when
Feature activation+0.087
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
21
Token 21
Feature activation+0.000
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
a
Token a
Feature activation+1.987
short
Token short
Feature activation+0.515
military
Token military
Feature activation+0.000
style
Token style
Feature activation+0.459
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
them
Token them
Feature activation+0.000
cut
Token cut
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
The
TokenThe
Feature activation+0.000
in
Token in
Feature activation+0.000
income
Token income
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
he
Token he
Feature activation+0.000
cut
Token cut
Feature activation+0.000
in
Token in
Feature activation+1.825
this
Token this
Feature activation+1.855
current
Token current
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000

INTERVAL 1.381 - 1.726
CONTAINS 0.001%

83
Token83
Feature activation+0.000
,
Token,
Feature activation+0.000
proposed
Token proposed
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
25
Token 25
Feature activation+0.118
%
Token%
Feature activation+1.577
of
Token of
Feature activation+0.090
state
Token state
Feature activation+0.000
school
Token school
Feature activation+0.000
teachers
Token teachers
Feature activation+0.000
in
Token in
Feature activation+0.897
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
get
Token get
Feature activation+0.000
cut
Token cut
Feature activation+0.000
in
Token in
Feature activation+1.597
half
Token half
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
cut
Token cut
Feature activation+0.000
her
Token her
Feature activation+1.896
long
Token long
Feature activation+1.260
,
Token,
Feature activation+0.625
brown
Token brown
Feature activation+1.158
hair
Token hair
Feature activation+1.496
in
Token in
Feature activation+2.863
a
Token a
Feature activation+1.987
short
Token short
Feature activation+0.515
military
Token military
Feature activation+0.000
style
Token style
Feature activation+0.459
the
Token the
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
will
Token will
Feature activation+0.895
und
Token und
Feature activation+0.385
oubt
Tokenoubt
Feature activation+0.000
ably
Tokenably
Feature activation+1.548
come
Token come
Feature activation+1.038
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
bloated
Token bloated
Feature activation+0.000
Patch
Token Patch
Feature activation+0.000
,
Token,
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
provinces
Token provinces
Feature activation+2.006
put
Token put
Feature activation+1.534
in
Token in
Feature activation+2.391
place
Token place
Feature activation+0.222
stop
Token stop
Feature activation+0.000
gap
Tokengap
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000

INTERVAL 1.035 - 1.381
CONTAINS 0.003%

ial
Tokenial
Feature activation+0.000
's
Token's
Feature activation+0.000
investors
Token investors
Feature activation+0.000
finally
Token finally
Feature activation+0.000
cut
Token cut
Feature activation+0.000
their
Token their
Feature activation+1.308
losses
Token losses
Feature activation+0.632
and
Token and
Feature activation+0.000
liquid
Token liquid
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
the
Token the
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
cut
Token cut
Feature activation+0.000
your
Token your
Feature activation+0.719
Christmas
Token Christmas
Feature activation+0.000
tree
Token tree
Feature activation+1.141
on
Token on
Feature activation+1.745
the
Token the
Feature activation+1.530
Roosevelt
Token Roosevelt
Feature activation+0.000
National
Token National
Feature activation+0.000
Forest
Token Forest
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
property
Token property
Feature activation+0.000
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.142
by
Token by
Feature activation+1.307
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
an
Token an
Feature activation+0.000
cut
Token cut
Feature activation+0.000
by
Token by
Feature activation+1.222
a
Token a
Feature activation+1.832
slightly
Token slightly
Feature activation+1.084
larger
Token larger
Feature activation+1.212
amount
Token amount
Feature activation+1.115
,
Token,
Feature activation+0.291
the
Token the
Feature activation+0.000
officials
Token officials
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
cut
Token cut
Feature activation+0.000
first
Token first
Feature activation+1.826
with
Token with
Feature activation+1.149
his
Token his
Feature activation+0.551
salary
Token salary
Feature activation+0.000
cap
Token cap
Feature activation+0.000
hit
Token hit
Feature activation+0.000
being
Token being
Feature activation+0.000

INTERVAL 0.690 - 1.035
CONTAINS 0.006%

term
Tokenterm
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
European
Token European
Feature activation+0.000
leaders
Token leaders
Feature activation+0.846
had
Token had
Feature activation+0.932
demanded
Token demanded
Feature activation+0.705
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
I
Token I
Feature activation+0.000
stripped
Token stripped
Feature activation+0.000
him
Token him
Feature activation+0.725
[
Token [
Feature activation+0.000
Johnson
TokenJohnson
Feature activation+0.000
]
Token]
Feature activation+0.945
all
Token all
Feature activation+0.842
the
Token the
Feature activation+0.168
way
Token way
Feature activation+0.000
until
Token until
Feature activation+0.000
I
Token I
Feature activation+0.000
bit
Token bit
Feature activation+0.029
of
Token of
Feature activation+0.000
skin
Token skin
Feature activation+0.729
with
Token with
Feature activation+1.849
clinical
Token clinical
Feature activation+0.000
precision
Token precision
Feature activation+0.818
at
Token at
Feature activation+1.184
the
Token the
Feature activation+0.883
hospital
Token hospital
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ch
TokenCh
Feature activation+0.000
annels
Tokenannels
Feature activation+0.000
cut
Token cut
Feature activation+0.000
through
Token through
Feature activation+0.699
the
Token the
Feature activation+0.445
ether
Token ether
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
spanning
Token spanning
Feature activation+0.000
great
Token great
Feature activation+0.075
Ċ
TokenĊ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
will
Token will
Feature activation+0.895
und
Token und
Feature activation+0.385
oubt
Tokenoubt
Feature activation+0.000
ably
Tokenably
Feature activation+1.548
come
Token come
Feature activation+1.038
from
Token from
Feature activation+0.000

INTERVAL 0.345 - 0.690
CONTAINS 0.008%

also
Token also
Feature activation+0.000
tends
Token tends
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
out
Token out
Feature activation+0.097
some
Token some
Feature activation+0.413
F
Token F
Feature activation+0.000
OD
TokenOD
Feature activation+0.000
MAP
TokenMAP
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
held
Token held
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
many
Token many
Feature activation+0.456
big
Token big
Feature activation+0.122
checks
Token checks
Feature activation+0.000
for
Token for
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
business
Token business
Feature activation+0.000
houses
Token houses
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
split
Token split
Feature activation+0.000
in
Token in
Feature activation+0.599
the
Token the
Feature activation+0.000
period
Token period
Feature activation+0.000
under
Token under
Feature activation+0.000
consideration
Token consideration
Feature activation+0.000
(
Token (
Feature activation+0.000
my
Token my
Feature activation+2.142
throat
Token throat
Feature activation+0.916
with
Token with
Feature activation+2.207
a
Token a
Feature activation+1.762
razor
Token razor
Feature activation+0.000
blade
Token blade
Feature activation+0.668
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
The
TokenThe
Feature activation+0.000
officer
Token officer
Feature activation+0.000
]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.000
'
Token '
Feature activation+0.000
71
Token71
Feature activation+0.000
the
Token the
Feature activation+0.000
trade
Token trade
Feature activation+0.000
was
Token was
Feature activation+0.539
made
Token made
Feature activation+0.000
for
Token for
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
Morgan
Token Morgan
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.000 - 0.345
CONTAINS 99.979%

underlying
Token underlying
Feature activation+0.000
big
Token big
Feature activation+0.000
concept
Token concept
Feature activation+0.000
but
Token but
Feature activation+0.000
on
Token on
Feature activation+0.000
budget
Token budget
Feature activation+0.000
similar
Token similar
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
sci
Token sci
Feature activation+0.000
-
Token-
Feature activation+0.000
marks
Tokenmarks
Feature activation+0.000
With
Token With
Feature activation+0.000
Stock
Token Stock
Feature activation+0.000
and
Token and
Feature activation+0.000
OC
Token OC
Feature activation+0.000
Spe
Token Spe
Feature activation+0.000
eds
Tokeneds
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Intel
Token Intel
Feature activation+0.000
1922
Token 1922
Feature activation+0.000
on
Token on
Feature activation+0.000
Bunker
Token Bunker
Feature activation+0.000
Hill
Token Hill
Feature activation+0.000
in
Token in
Feature activation+0.000
Downtown
Token Downtown
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
,
Token,
Feature activation+0.000
California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
unethical
Token unethical
Feature activation+0.000
to
Token to
Feature activation+0.000
run
Token run
Feature activation+0.000
the
Token the
Feature activation+0.000
risk
Token risk
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
for
Token for
Feature activation+0.000
Games
Token Games
Feature activation+0.000
that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.000
talk
Token talk
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
NI
Token NI
Feature activation+0.000
AC
TokenAC
Feature activation+0.000
Fall
Token Fall
Feature activation+0.000
Sym
Token Sym
Feature activation+0.000
posium
Tokenposium
Feature activation+0.000
last
Token last
Feature activation+0.000
October
Token October
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 H7.8: (feature 34452)

TOP ACTIVATIONS
MAX = 4.758

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
reason
Token reason
Feature activation+0.000
in
Token in
Feature activation+4.758
this
Token this
Feature activation+0.847
world
Token world
Feature activation+2.886
for
Token for
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+4.302
because
Token because
Feature activation+0.000
after
Token after
Feature activation+0.000
an
Token an
Feature activation+0.000
illicit
Token illicit
Feature activation+0.000
drug
Token drug
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
additional
Token additional
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
that
Token that
Feature activation+1.578
will
Token will
Feature activation+4.195
be
Token be
Feature activation+3.876
discussed
Token discussed
Feature activation+0.397
below
Token below
Feature activation+1.966
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
reason
Token reason
Feature activation+0.623
,
Token,
Feature activation+1.713
reasons
Token reasons
Feature activation+1.432
that
Token that
Feature activation+4.191
no
Token no
Feature activation+1.967
longer
Token longer
Feature activation+3.723
exist
Token exist
Feature activation+3.177
(
Token (
Feature activation+0.123
and
Tokenand
Feature activation+0.760
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
second
Token second
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.178
probably
Token probably
Feature activation+3.954
even
Token even
Feature activation+2.334
more
Token more
Feature activation+2.945
compelling
Token compelling
Feature activation+1.966
:
Token:
Feature activation+0.000
weight
Token weight
Feature activation+0.000
to
Token to
Feature activation+0.000
resist
Token resist
Feature activation+0.000
the
Token the
Feature activation+0.000
census
Token census
Feature activation+0.000
,
Token,
Feature activation+2.550
but
Token but
Feature activation+3.906
the
Token the
Feature activation+0.844
awarding
Token awarding
Feature activation+0.000
of
Token of
Feature activation+0.000
census
Token census
Feature activation+0.000
data
Token data
Feature activation+0.000
are
Token are
Feature activation+0.000
additional
Token additional
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
that
Token that
Feature activation+1.578
will
Token will
Feature activation+4.195
be
Token be
Feature activation+3.876
discussed
Token discussed
Feature activation+0.397
below
Token below
Feature activation+1.966
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
reason
Token reason
Feature activation+0.623
,
Token,
Feature activation+1.713
reasons
Token reasons
Feature activation+1.432
that
Token that
Feature activation+4.191
no
Token no
Feature activation+1.967
longer
Token longer
Feature activation+3.723
exist
Token exist
Feature activation+3.177
(
Token (
Feature activation+0.123
and
Tokenand
Feature activation+0.760
a
Token a
Feature activation+1.493
reality
Token reality
Feature activation+0.646
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Reason
TokenReason
Feature activation+0.003
#
Token #
Feature activation+2.471
675
Token675
Feature activation+3.557
663
Token663
Feature activation+1.556
for
Token for
Feature activation+0.137
Sum
Token Sum
Feature activation+0.000
mor
Tokenmor
Feature activation+0.000
um
Tokenum
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.546
fraud
Token fraud
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.672
or
Token or
Feature activation+0.000
from
Token from
Feature activation+0.000
external
Token external
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
),
Token),
Feature activation+3.497
Natural
Token Natural
Feature activation+0.000
family
Token family
Feature activation+0.000
planning
Token planning
Feature activation+0.000
methods
Token methods
Feature activation+0.000
(
Token (
Feature activation+0.000
I
Token I
Feature activation+0.286
race
Token race
Feature activation+0.000
in
Token in
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
is
Token is
Feature activation+3.433
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
cars
Token cars
Feature activation+0.000
give
Token give
Feature activation+0.000
me
Token me
Feature activation+0.000
every
Token every
Feature activation+0.000
soldier
Token soldier
Feature activation+0.000
joins
Token joins
Feature activation+0.000
their
Token their
Feature activation+0.000
military
Token military
Feature activation+0.000
,
Token,
Feature activation+3.408
to
Token to
Feature activation+1.686
defend
Token defend
Feature activation+0.000
their
Token their
Feature activation+0.000
homeland
Token homeland
Feature activation+0.000
.
Token.
Feature activation+0.582
there
Token there
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
other
Token other
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
as
Token as
Feature activation+3.296
well
Token well
Feature activation+3.167
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
reason
Token reason
Feature activation+0.000
given
Token given
Feature activation+3.232
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
discrepancy
Token discrepancy
Feature activation+0.199
was
Token was
Feature activation+1.600
not
Token not
Feature activation+3.210
immediately
Token immediately
Feature activation+2.416
clear
Token clear
Feature activation+1.414
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
was
Token was
Feature activation+3.205
this
Token this
Feature activation+0.000
;
Token;
Feature activation+0.000
it
Token it
Feature activation+0.000
went
Token went
Feature activation+0.000
a
Token a
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
grounded
Token grounded
Feature activation+0.000
reasons
Token reasons
Feature activation+0.412
(
Token (
Feature activation+3.189
ar
Tokenar
Feature activation+0.000
ising
Tokenising
Feature activation+3.173
from
Token from
Feature activation+1.503
the
Token the
Feature activation+0.813
physical
Token physical
Feature activation+0.298
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
second
Token second
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.178
probably
Token probably
Feature activation+3.954
even
Token even
Feature activation+2.334
more
Token more
Feature activation+2.945
compelling
Token compelling
Feature activation+1.966
:
Token:
Feature activation+0.000
,
Token,
Feature activation+1.713
reasons
Token reasons
Feature activation+1.432
that
Token that
Feature activation+4.191
no
Token no
Feature activation+1.967
longer
Token longer
Feature activation+3.723
exist
Token exist
Feature activation+3.177
(
Token (
Feature activation+0.123
and
Tokenand
Feature activation+0.760
a
Token a
Feature activation+1.493
reality
Token reality
Feature activation+0.646
we
Token we
Feature activation+0.000

Top DFA by src position
MAX = 5.808

Ļ
TokenĻ
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation-0.013
Top resid features:
not
Token not
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.033
Top resid features:
good
Token good
Feature activation-0.014
Top resid features:
reason
Token reason
Feature activation+5.808
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
why
Token why
Feature activation+0.000
Top resid features:
end
Token end
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation+0.034
Top resid features:
reason
Token reason
Feature activation+4.787
Top resid features:
it
Token it
Feature activation-0.025
Top resid features:
didn
Token didn
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.023
Top resid features:
t
Tokent
Feature activation+0.035
Top resid features:
friendly
Tokenfriendly
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
There
Token There
Feature activation+0.021
Top resid features:
are
Token are
Feature activation-0.004
Top resid features:
additional
Token additional
Feature activation+0.020
Top resid features:
reasons
Token reasons
Feature activation+4.850
Top resid features:
that
Token that
Feature activation+0.228
Top resid features:
will
Token will
Feature activation+0.058
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
discussed
Token discussed
Feature activation+0.000
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
very
Token very
Feature activation+0.006
Top resid features:
good
Token good
Feature activation+0.031
Top resid features:
reason
Token reason
Feature activation+0.380
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
reasons
Token reasons
Feature activation+4.546
Top resid features:
that
Token that
Feature activation+0.085
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
longer
Token longer
Feature activation+0.000
Top resid features:
exist
Token exist
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
The
TokenThe
Feature activation+0.053
Top resid features:
second
Token second
Feature activation+0.104
Top resid features:
reason
Token reason
Feature activation+4.166
Top resid features:
is
Token is
Feature activation+0.417
Top resid features:
probably
Token probably
Feature activation+0.092
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
compelling
Token compelling
Feature activation+0.000
Top resid features:
forms
Token forms
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.084
Top resid features:
There
Token There
Feature activation+0.008
Top resid features:
are
Token are
Feature activation-0.046
Top resid features:
many
Token many
Feature activation+0.011
Top resid features:
reasons
Token reasons
Feature activation+4.317
Top resid features:
for
Token for
Feature activation+0.228
Top resid features:
people
Token people
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
resist
Token resist
Feature activation-0.070
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
friendly
Tokenfriendly
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
There
Token There
Feature activation+0.002
Top resid features:
are
Token are
Feature activation-0.009
Top resid features:
additional
Token additional
Feature activation-0.031
Top resid features:
reasons
Token reasons
Feature activation+4.505
Top resid features:
that
Token that
Feature activation+0.275
Top resid features:
will
Token will
Feature activation+0.080
Top resid features:
be
Token be
Feature activation+0.015
Top resid features:
discussed
Token discussed
Feature activation+0.000
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
very
Token very
Feature activation+0.007
Top resid features:
good
Token good
Feature activation+0.045
Top resid features:
reason
Token reason
Feature activation+0.466
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
reasons
Token reasons
Feature activation+3.923
Top resid features:
that
Token that
Feature activation+0.206
Top resid features:
no
Token no
Feature activation+0.005
Top resid features:
longer
Token longer
Feature activation-0.057
Top resid features:
exist
Token exist
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Church
Token Church
Feature activation+0.006
Top resid features:
intends
Token intends
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
Reason
TokenReason
Feature activation+4.105
Top resid features:
#
Token #
Feature activation+0.071
Top resid features:
675
Token675
Feature activation+0.019
Top resid features:
663
Token663
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Sum
Token Sum
Feature activation+0.000
Top resid features:
ak
Tokenak
Feature activation-0.016
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
âĢ
Token âĢ
Feature activation+0.039
Top resid features:
ľ
Tokenľ
Feature activation+0.017
Top resid features:
The
TokenThe
Feature activation+0.092
Top resid features:
reason
Token reason
Feature activation+4.176
Top resid features:
is
Token is
Feature activation+0.200
Top resid features:
fraud
Token fraud
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:
think
Token think
Feature activation+0.000
Top resid features:
If
Token If
Feature activation-0.044
Top resid features:
there
Token there
Feature activation+0.038
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
well
Token well
Feature activation-0.033
Top resid features:
grounded
Token grounded
Feature activation+0.042
Top resid features:
reasons
Token reasons
Feature activation+4.256
Top resid features:
(
Token (
Feature activation+0.064
Top resid features:
ar
Tokenar
Feature activation+0.004
Top resid features:
ising
Tokenising
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
supermarket
Token supermarket
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.032
Top resid features:
reason
Token reason
Feature activation+4.551
Top resid features:
I
Token I
Feature activation-0.052
Top resid features:
race
Token race
Feature activation-0.182
Top resid features:
in
Token in
Feature activation-0.021
Top resid features:
F
Token F
Feature activation-0.002
Top resid features:
1
Token1
Feature activation+0.028
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
concentrate
Token concentrate
Feature activation-0.036
Top resid features:
on
Token on
Feature activation-0.054
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
real
Token real
Feature activation+0.083
Top resid features:
reason
Token reason
Feature activation+4.611
Top resid features:
every
Token every
Feature activation+0.013
Top resid features:
soldier
Token soldier
Feature activation-0.013
Top resid features:
joins
Token joins
Feature activation+0.006
Top resid features:
their
Token their
Feature activation-0.022
Top resid features:
military
Token military
Feature activation+0.002
Top resid features:
but
Token but
Feature activation+0.130
Top resid features:
there
Token there
Feature activation+0.051
Top resid features:
could
Token could
Feature activation+0.063
Top resid features:
be
Token be
Feature activation+0.013
Top resid features:
other
Token other
Feature activation+0.385
Top resid features:
reasons
Token reasons
Feature activation+3.559
Top resid features:
as
Token as
Feature activation+0.047
Top resid features:
well
Token well
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:
said
Token said
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
ľ
Tokenľ
Feature activation+0.014
Top resid features:
No
TokenNo
Feature activation+0.076
Top resid features:
reason
Token reason
Feature activation+3.996
Top resid features:
given
Token given
Feature activation-0.035
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
received
Token received
Feature activation+0.000
Top resid features:
Metro
Token Metro
Feature activation-0.000
Top resid features:
Jail
Token Jail
Feature activation-0.001
Top resid features:
records
Token records
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
The
Token The
Feature activation-0.002
Top resid features:
reason
Token reason
Feature activation+3.432
Top resid features:
for
Token for
Feature activation+0.309
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
discrepancy
Token discrepancy
Feature activation+0.038
Top resid features:
was
Token was
Feature activation+0.374
Top resid features:
not
Token not
Feature activation+0.039
Top resid features:
Orbit
Token Orbit
Feature activation+0.004
Top resid features:
er
Tokener
Feature activation-0.028
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.071
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
reason
Token reason
Feature activation+4.311
Top resid features:
was
Token was
Feature activation+0.082
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
went
Token went
Feature activation+0.000
Top resid features:
If
Token If
Feature activation+0.009
Top resid features:
there
Token there
Feature activation+0.006
Top resid features:
are
Token are
Feature activation-0.017
Top resid features:
well
Token well
Feature activation-0.057
Top resid features:
grounded
Token grounded
Feature activation+0.197
Top resid features:
reasons
Token reasons
Feature activation+4.295
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
ar
Tokenar
Feature activation+0.000
Top resid features:
ising
Tokenising
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.064
Top resid features:
second
Token second
Feature activation+0.045
Top resid features:
reason
Token reason
Feature activation+3.760
Top resid features:
is
Token is
Feature activation+0.112
Top resid features:
probably
Token probably
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
compelling
Token compelling
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
very
Token very
Feature activation+0.028
Top resid features:
good
Token good
Feature activation+0.066
Top resid features:
reason
Token reason
Feature activation+0.569
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
reasons
Token reasons
Feature activation+3.264
Top resid features:
that
Token that
Feature activation+0.238
Top resid features:
no
Token no
Feature activation-0.005
Top resid features:
longer
Token longer
Feature activation-0.143
Top resid features:
exist
Token exist
Feature activation+0.012
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.01

Head 3: 0.06

Head 4: 0.06

Head 5: 0.06

Head 6: 0.05

Head 7: 0.02

Head 8: 0.55

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

explanations2.29

explanation2.04

Explan2.03

Reason2.03

explain1.91

WHY1.89

Reason1.83

pleading1.80

plead1.79

explaining1.79

why1.74

justification1.73

understandable1.73

excuses1.71

excuse1.67

arguments1.64

stemming1.63

summar1.62

impl1.61

reasons1.61

Negative logits

ateurs-1.91

athering-1.91

ateur-1.69

seiz-1.63

asured-1.62

asure-1.61

ignty-1.59

ドラ-1.57

efeated-1.56

ersive-1.55

outdoors-1.55

ennial-1.54

rift-1.52

abad-1.52

stores-1.51

iership-1.51

ership-1.51

kel-1.50

ossus-1.50

liberated-1.49

INTERVAL 4.282 - 4.758
CONTAINS 0.000%

didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+4.302
because
Token because
Feature activation+0.000
after
Token after
Feature activation+0.000
an
Token an
Feature activation+0.000
illicit
Token illicit
Feature activation+0.000
drug
Token drug
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
reason
Token reason
Feature activation+0.000
in
Token in
Feature activation+4.758
this
Token this
Feature activation+0.847
world
Token world
Feature activation+2.886
for
Token for
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 3.806 - 4.282
CONTAINS 0.001%

There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
additional
Token additional
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
that
Token that
Feature activation+1.578
will
Token will
Feature activation+4.195
be
Token be
Feature activation+3.876
discussed
Token discussed
Feature activation+0.397
below
Token below
Feature activation+1.966
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
are
Token are
Feature activation+0.000
additional
Token additional
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
that
Token that
Feature activation+1.578
will
Token will
Feature activation+4.195
be
Token be
Feature activation+3.876
discussed
Token discussed
Feature activation+0.397
below
Token below
Feature activation+1.966
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
second
Token second
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.178
probably
Token probably
Feature activation+3.954
even
Token even
Feature activation+2.334
more
Token more
Feature activation+2.945
compelling
Token compelling
Feature activation+1.966
:
Token:
Feature activation+0.000
weight
Token weight
Feature activation+0.000
to
Token to
Feature activation+0.000
resist
Token resist
Feature activation+0.000
the
Token the
Feature activation+0.000
census
Token census
Feature activation+0.000
,
Token,
Feature activation+2.550
but
Token but
Feature activation+3.906
the
Token the
Feature activation+0.844
awarding
Token awarding
Feature activation+0.000
of
Token of
Feature activation+0.000
census
Token census
Feature activation+0.000
data
Token data
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
reason
Token reason
Feature activation+0.623
,
Token,
Feature activation+1.713
reasons
Token reasons
Feature activation+1.432
that
Token that
Feature activation+4.191
no
Token no
Feature activation+1.967
longer
Token longer
Feature activation+3.723
exist
Token exist
Feature activation+3.177
(
Token (
Feature activation+0.123
and
Tokenand
Feature activation+0.760

INTERVAL 3.330 - 3.806
CONTAINS 0.001%

.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.546
fraud
Token fraud
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
soldier
Token soldier
Feature activation+0.000
joins
Token joins
Feature activation+0.000
their
Token their
Feature activation+0.000
military
Token military
Feature activation+0.000
,
Token,
Feature activation+3.408
to
Token to
Feature activation+1.686
defend
Token defend
Feature activation+0.000
their
Token their
Feature activation+0.000
homeland
Token homeland
Feature activation+0.000
.
Token.
Feature activation+0.582
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Reason
TokenReason
Feature activation+0.003
#
Token #
Feature activation+2.471
675
Token675
Feature activation+3.557
663
Token663
Feature activation+1.556
for
Token for
Feature activation+0.137
Sum
Token Sum
Feature activation+0.000
mor
Tokenmor
Feature activation+0.000
um
Tokenum
Feature activation+0.000
I
Token I
Feature activation+0.286
race
Token race
Feature activation+0.000
in
Token in
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
is
Token is
Feature activation+3.433
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
cars
Token cars
Feature activation+0.000
give
Token give
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.672
or
Token or
Feature activation+0.000
from
Token from
Feature activation+0.000
external
Token external
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
),
Token),
Feature activation+3.497
Natural
Token Natural
Feature activation+0.000
family
Token family
Feature activation+0.000
planning
Token planning
Feature activation+0.000
methods
Token methods
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 2.855 - 3.330
CONTAINS 0.003%

there
Token there
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
other
Token other
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
as
Token as
Feature activation+3.296
well
Token well
Feature activation+3.167
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
reason
Token reason
Feature activation+0.000
in
Token in
Feature activation+4.758
this
Token this
Feature activation+0.847
world
Token world
Feature activation+2.886
for
Token for
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
reported
Token reported
Feature activation+0.000
reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
seems
Token seems
Feature activation+3.069
awfully
Token awfully
Feature activation+1.430
bizarre
Token bizarre
Feature activation+1.033
.
Token.
Feature activation+0.081
Law
Token Law
Feature activation+0.000
did
Token did
Feature activation+0.000
reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
discrepancy
Token discrepancy
Feature activation+0.199
was
Token was
Feature activation+1.600
not
Token not
Feature activation+3.210
immediately
Token immediately
Feature activation+2.416
clear
Token clear
Feature activation+1.414
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
money
Token money
Feature activation+0.000
moves
Token moves
Feature activation+0.000
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.522
that
Token that
Feature activation+3.111
are
Token are
Feature activation+3.098
plaus
Token plaus
Feature activation+0.000
ibly
Tokenibly
Feature activation+2.484
unrelated
Token unrelated
Feature activation+1.206
to
Token to
Feature activation+1.238
the
Token the
Feature activation+0.786

INTERVAL 2.379 - 2.855
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.139
One
TokenOne
Feature activation+0.584
possible
Token possible
Feature activation+0.127
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+2.633
that
Token that
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
taxpayer
Token taxpayer
Feature activation+0.000
funding
Token funding
Feature activation+0.000
than
Token than
Feature activation+0.000
24
Token 24
Feature activation+0.000
hours
Token hours
Feature activation+0.000
notice
Token notice
Feature activation+0.000
,
Token,
Feature activation+0.137
but
Token but
Feature activation+2.811
those
Token those
Feature activation+2.307
were
Token were
Feature activation+1.679
details
Token details
Feature activation+0.000
that
Token that
Feature activation+0.000
didn
Token didn
Feature activation+0.000
women
Token women
Feature activation+0.000
citing
Token citing
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
,
Token,
Feature activation+2.567
to
Token to
Feature activation+2.569
30
Token 30
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
reason
Token reason
Feature activation+0.000
we
Token we
Feature activation+0.020
know
Token know
Feature activation+3.149
of
Token of
Feature activation+2.787
her
Token her
Feature activation+0.000
actions
Token actions
Feature activation+0.000
that
Token that
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+1.674
that
Token that
Feature activation+2.961
don
Token don
Feature activation+2.923
't
Token't
Feature activation+2.977
make
Token make
Feature activation+2.580
much
Token much
Feature activation+1.096
sense
Token sense
Feature activation+1.131
).
Token).
Feature activation+0.000
So
Token So
Feature activation+0.000
now
Token now
Feature activation+0.000

INTERVAL 1.903 - 2.379
CONTAINS 0.003%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
with
Token with
Feature activation+0.000
reason
Token reason
Feature activation+0.000
!
Token!
Feature activation+2.059
You
Token You
Feature activation+0.000
are
Token are
Feature activation+0.000
really
Token really
Feature activation+0.000
damn
Token damn
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
dictators
Token dictators
Feature activation+0.000
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
that
Token that
Feature activation+2.089
are
Token are
Feature activation+2.110
unf
Token unf
Feature activation+1.680
athom
Tokenathom
Feature activation+0.000
able
Tokenable
Feature activation+0.414
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+3.178
probably
Token probably
Feature activation+3.954
even
Token even
Feature activation+2.334
more
Token more
Feature activation+2.945
compelling
Token compelling
Feature activation+1.966
:
Token:
Feature activation+0.000
weight
Token weight
Feature activation+0.000
-
Token-
Feature activation+0.000
loss
Tokenloss
Feature activation+0.000
supplements
Token supplements
Feature activation+0.000
The
TokenThe
Feature activation+0.000
reasoning
Token reasoning
Feature activation+0.116
is
Token is
Feature activation+2.646
simple
Token simple
Feature activation+1.569
and
Token and
Feature activation+1.452
straightforward
Token straightforward
Feature activation+2.112
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
established
Token established
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
important
Token important
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+1.949
,
Token,
Feature activation+0.000
Muscle
Token Muscle
Feature activation+0.000
Soldier
Token Soldier
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.427 - 1.903
CONTAINS 0.004%

reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
seems
Token seems
Feature activation+3.069
awfully
Token awfully
Feature activation+1.430
bizarre
Token bizarre
Feature activation+1.033
.
Token.
Feature activation+0.081
Law
Token Law
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
reason
Token reason
Feature activation+0.000
this
Token this
Feature activation+0.000
happened
Token happened
Feature activation+0.000
was
Token was
Feature activation+1.819
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.461
parents
Token parents
Feature activation+0.360
claim
Token claim
Feature activation+1.221
,
Token,
Feature activation+1.806
is
Token is
Feature activation+1.789
not
Token not
Feature activation+2.268
racism
Token racism
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
desire
Token desire
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
reasoning
Token reasoning
Feature activation+0.116
is
Token is
Feature activation+2.646
simple
Token simple
Feature activation+1.569
and
Token and
Feature activation+1.452
straightforward
Token straightforward
Feature activation+2.112
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
was
Token was
Feature activation+1.839
the
Token the
Feature activation+0.000
concern
Token concern
Feature activation+0.000
of
Token of
Feature activation+0.039
members
Token members
Feature activation+0.000
who
Token who
Feature activation+0.000

INTERVAL 0.952 - 1.427
CONTAINS 0.006%

reason
Token reason
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
was
Token was
Feature activation+1.002
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
who
Token who
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+0.000
established
Token established
Feature activation+0.000
genre
Token genre
Feature activation+0.000
.
Token.
Feature activation+0.954
The
Token The
Feature activation+0.277
trans
Token trans
Feature activation+0.000
position
Tokenposition
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
should
Token should
Feature activation+0.000
stay
Token stay
Feature activation+0.000
downtown
Token downtown
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+1.202
of
Token of
Feature activation+0.000
proximity
Token proximity
Feature activation+0.327
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
Face
Token Face
Feature activation+0.000
to
Token to
Feature activation+0.000
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+0.000
W
Token W
Feature activation+0.000
augh
Tokenaugh
Feature activation+1.127
replies
Token replies
Feature activation+0.000
"
Token "
Feature activation+0.136
P
TokenP
Feature activation+0.000
overty
Tokenoverty
Feature activation+0.000
.
Token.
Feature activation+0.000
very
Token very
Feature activation+0.000
strange
Token strange
Feature activation+0.000
ways
Token ways
Feature activation+0.000
but
Token but
Feature activation+0.000
their
Token their
Feature activation+0.000
reasons
Token reasons
Feature activation+1.321
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
Regina
Token Regina
Feature activation+0.000
-
Token-
Feature activation+0.000
trained
Tokentrained
Feature activation+0.000

INTERVAL 0.476 - 0.952
CONTAINS 0.015%

think
Token think
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
term
Token term
Feature activation+0.000
to
Token to
Feature activation+0.778
describe
Token describe
Feature activation+0.000
the
Token the
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
brain
Token brain
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
why
Token why
Feature activation+0.000
those
Token those
Feature activation+0.548
western
Token western
Feature activation+0.000
males
Token males
Feature activation+0.000
losers
Token losers
Feature activation+0.000
keep
Token keep
Feature activation+0.000
boasting
Token boasting
Feature activation+0.000
someone
Token someone
Feature activation+0.047
might
Token might
Feature activation+0.712
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
--
Token --
Feature activation+0.876
the
Token the
Feature activation+0.003
pride
Token pride
Feature activation+0.000
you
Token you
Feature activation+0.000
feel
Token feel
Feature activation+0.000
when
Token when
Feature activation+0.000
that
Token that
Feature activation+4.191
no
Token no
Feature activation+1.967
longer
Token longer
Feature activation+3.723
exist
Token exist
Feature activation+3.177
(
Token (
Feature activation+0.123
and
Tokenand
Feature activation+0.760
a
Token a
Feature activation+1.493
reality
Token reality
Feature activation+0.646
we
Token we
Feature activation+0.000
now
Token now
Feature activation+0.000
live
Token live
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
justification
Token justification
Feature activation+0.000
provided
Token provided
Feature activation+2.254
by
Token by
Feature activation+0.704
Time
Token Time
Feature activation+0.000
explicitly
Token explicitly
Feature activation+1.327
excluded
Token excluded
Feature activation+0.000
disagreement
Token disagreement
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.000 - 0.476
CONTAINS 99.965%

have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.000
progress
Token progress
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
race
Token race
Feature activation+0.000
relations
Token relations
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
Disc
Token Disc
Feature activation+0.000
s
Tokens
Feature activation+0.000
Inn
Token Inn
Feature activation+0.000
ova
Tokenova
Feature activation+0.000
Distance
Token Distance
Feature activation+0.000
Driver
Token Driver
Feature activation+0.000
Champion
Token Champion
Feature activation+0.000
12
Token 12
Feature activation+0.000
$
Token $
Feature activation+0.000
13
Token13
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
uv
Tokenuv
Feature activation+0.000
J
TokenJ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
2
Token2
Feature activation+0.000
Y
TokenY
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Phil
Token Phil
Feature activation+0.000
Ker
Token Ker
Feature activation+0.000
pen
Tokenpen
Feature activation+0.000
(@
Token (@
Feature activation+0.000
.
Token.
Feature activation+0.000
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+0.000
agricultural
Token agricultural
Feature activation+0.000
;
Token;
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
furniture
Token furniture
Feature activation+0.000
their
Token their
Feature activation+0.000
period
Token period
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
busiest
Token busiest
Feature activation+0.000
times
Token times
Feature activation+0.000
in
Token in
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 H7.8: (feature 9558)

TOP ACTIVATIONS
MAX = 2.284

said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Construction
TokenConstruction
Feature activation+0.165
is
Token is
Feature activation+2.284
due
Token due
Feature activation+2.139
to
Token to
Feature activation+2.265
begin
Token begin
Feature activation+2.210
next
Token next
Feature activation+0.558
year
Token year
Feature activation+0.943
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.000
where
Token where
Feature activation+0.000
manufacturing
Token manufacturing
Feature activation+0.000
is
Token is
Feature activation+2.277
legal
Token legal
Feature activation+0.791
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
requires
Token requires
Feature activation+0.000
money
Token money
Feature activation+0.000
seven
Token seven
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
filming
Token filming
Feature activation+0.026
commenced
Token commenced
Feature activation+2.127
on
Token on
Feature activation+0.965
January
Token January
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
1980
Token 1980
Feature activation+0.204
Lizard
Token Lizard
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
production
Tokenproduction
Feature activation+0.011
would
Token would
Feature activation+2.050
be
Token be
Feature activation+2.102
a
Token a
Feature activation+0.848
GO
Token GO
Feature activation+0.000
!
Token!
Feature activation+0.000
Thank
Token Thank
Feature activation+0.000
you
Token you
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
Lizard
Token Lizard
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
production
Tokenproduction
Feature activation+0.011
would
Token would
Feature activation+2.050
be
Token be
Feature activation+2.102
a
Token a
Feature activation+0.848
GO
Token GO
Feature activation+0.000
!
Token!
Feature activation+0.000
Thank
Token Thank
Feature activation+0.000
declined
Token declined
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.323
would
Token would
Feature activation+2.049
actually
Token actually
Feature activation+1.962
begin
Token begin
Feature activation+1.891
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
inated
Tokeninated
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
production
Token production
Feature activation+0.243
is
Token is
Feature activation+1.989
limited
Token limited
Feature activation+0.814
since
Token since
Feature activation+0.057
few
Token few
Feature activation+0.161
if
Token if
Feature activation+0.000
any
Token any
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.323
would
Token would
Feature activation+2.049
actually
Token actually
Feature activation+1.962
begin
Token begin
Feature activation+1.891
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
track
Token track
Feature activation+0.000
work
Token work
Feature activation+0.347
continues
Token continues
Feature activation+1.870
to
Token to
Feature activation+1.951
progress
Token progress
Feature activation+0.789
in
Token in
Feature activation+0.748
this
Token this
Feature activation+0.073
area
Token area
Feature activation+0.357
we
Token we
Feature activation+0.035
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.323
would
Token would
Feature activation+2.049
actually
Token actually
Feature activation+1.962
begin
Token begin
Feature activation+1.891
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
change
Token change
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
track
Token track
Feature activation+0.000
work
Token work
Feature activation+0.347
continues
Token continues
Feature activation+1.870
to
Token to
Feature activation+1.951
progress
Token progress
Feature activation+0.789
in
Token in
Feature activation+0.748
this
Token this
Feature activation+0.073
area
Token area
Feature activation+0.357
did
Token did
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
cleanup
Token cleanup
Feature activation+0.969
easier
Token easier
Feature activation+1.870
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
I
Token I
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
formal
Token formal
Feature activation+0.000
flower
Token flower
Feature activation+0.000
production
Token production
Feature activation+0.644
became
Token became
Feature activation+1.858
established
Token established
Feature activation+1.371
in
Token in
Feature activation+0.394
the
Token the
Feature activation+0.269
Netherlands
Token Netherlands
Feature activation+0.000
with
Token with
Feature activation+0.132
á
Tokená
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
dam
Token dam
Feature activation+0.000
construction
Token construction
Feature activation+0.000
is
Token is
Feature activation+1.837
taking
Token taking
Feature activation+1.665
place
Token place
Feature activation+0.672
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
prosecutors
Token prosecutors
Feature activation+0.000
year
Tokenyear
Feature activation+0.038
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
hip
Token hip
Feature activation+0.000
injury
Token injury
Feature activation+0.000
will
Token will
Feature activation+1.832
be
Token be
Feature activation+1.764
for
Token for
Feature activation+0.619
an
Token an
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
audition
Token audition
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Print
TokenPrint
Feature activation+0.000
ing
Tokening
Feature activation+0.065
human
Token human
Feature activation+0.000
tissue
Token tissue
Feature activation+0.172
is
Token is
Feature activation+1.825
extremely
Token extremely
Feature activation+1.422
difficult
Token difficult
Feature activation+1.618
because
Token because
Feature activation+0.154
of
Token of
Feature activation+0.358
the
Token the
Feature activation+0.127
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
jail
Token jail
Feature activation+0.000
began
Token began
Feature activation+1.824
in
Token in
Feature activation+0.572
2011
Token 2011
Feature activation+0.274
under
Token under
Feature activation+0.240
County
Token County
Feature activation+0.000
Executive
Token Executive
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Water
TokenWater
Feature activation+0.000
management
Token management
Feature activation+0.207
is
Token is
Feature activation+1.822
not
Token not
Feature activation+1.746
only
Token only
Feature activation+1.654
a
Token a
Feature activation+1.142
developing
Token developing
Feature activation+0.372
country
Token country
Feature activation+0.052
ipping
Tokenipping
Feature activation+0.000
to
Token to
Feature activation+1.100
White
Token White
Feature activation+0.000
horse
Tokenhorse
Feature activation+0.156
Motors
Token Motors
Feature activation+0.376
was
Token was
Feature activation+1.820
by
Token by
Feature activation+0.542
rail
Token rail
Feature activation+0.031
from
Token from
Feature activation+0.324
Detroit
Token Detroit
Feature activation+0.000
to
Token to
Feature activation+0.084
ria
Tokenria
Feature activation+0.000
shows
Token shows
Feature activation+0.000
how
Token how
Feature activation+0.000
energy
Token energy
Feature activation+0.000
generation
Token generation
Feature activation+0.519
is
Token is
Feature activation+1.816
tied
Token tied
Feature activation+0.664
tightly
Token tightly
Feature activation+0.000
to
Token to
Feature activation+0.868
the
Token the
Feature activation+0.315
light
Token light
Feature activation+0.000

Top DFA by src position
MAX = 2.603

he
Token he
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Construction
TokenConstruction
Feature activation+2.603
Top resid features:
is
Token is
Feature activation+0.057
Top resid features:
due
Token due
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
begin
Token begin
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
travel
Token travel
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
state
Token state
Feature activation-0.007
Top resid features:
where
Token where
Feature activation-0.026
Top resid features:
manufacturing
Token manufacturing
Feature activation+2.307
Top resid features:
is
Token is
Feature activation+0.491
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
requires
Token requires
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
seven
Token seven
Feature activation+0.015
Top resid features:
months
Token months
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
filming
Token filming
Feature activation+2.299
Top resid features:
commenced
Token commenced
Feature activation+0.115
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
23
Token 23
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Battle
Token Battle
Feature activation-0.005
Top resid features:
Lizard
Token Lizard
Feature activation-0.007
Top resid features:
post
Token post
Feature activation-0.013
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
production
Tokenproduction
Feature activation+2.547
Top resid features:
would
Token would
Feature activation+0.028
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
GO
Token GO
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
Battle
Token Battle
Feature activation-0.005
Top resid features:
Lizard
Token Lizard
Feature activation-0.009
Top resid features:
post
Token post
Feature activation-0.004
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
production
Tokenproduction
Feature activation+2.529
Top resid features:
would
Token would
Feature activation+0.016
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
GO
Token GO
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
producers
Token producers
Feature activation+0.004
Top resid features:
declined
Token declined
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
say
Token say
Feature activation-0.008
Top resid features:
when
Token when
Feature activation+0.012
Top resid features:
production
Token production
Feature activation+2.365
Top resid features:
would
Token would
Feature activation+0.020
Top resid features:
actually
Token actually
Feature activation+0.000
Top resid features:
begin
Token begin
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
poll
Tokenpoll
Feature activation+0.002
Top resid features:
inated
Tokeninated
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
but
Token but
Feature activation+0.085
Top resid features:
fruit
Token fruit
Feature activation+0.024
Top resid features:
production
Token production
Feature activation+2.225
Top resid features:
is
Token is
Feature activation+0.058
Top resid features:
limited
Token limited
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
producers
Token producers
Feature activation+0.003
Top resid features:
declined
Token declined
Feature activation-0.009
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
say
Token say
Feature activation-0.010
Top resid features:
when
Token when
Feature activation-0.000
Top resid features:
production
Token production
Feature activation+2.319
Top resid features:
would
Token would
Feature activation+0.043
Top resid features:
actually
Token actually
Feature activation+0.008
Top resid features:
begin
Token begin
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
As
TokenAs
Feature activation+0.005
Top resid features:
track
Token track
Feature activation+0.037
Top resid features:
work
Token work
Feature activation+2.282
Top resid features:
continues
Token continues
Feature activation+0.057
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
progress
Token progress
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
producers
Token producers
Feature activation+0.003
Top resid features:
declined
Token declined
Feature activation-0.021
Top resid features:
to
Token to
Feature activation-0.016
Top resid features:
say
Token say
Feature activation-0.033
Top resid features:
when
Token when
Feature activation-0.046
Top resid features:
production
Token production
Feature activation+2.203
Top resid features:
would
Token would
Feature activation+0.064
Top resid features:
actually
Token actually
Feature activation+0.007
Top resid features:
begin
Token begin
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
As
TokenAs
Feature activation+0.010
Top resid features:
track
Token track
Feature activation+0.062
Top resid features:
work
Token work
Feature activation+2.151
Top resid features:
continues
Token continues
Feature activation+0.077
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
progress
Token progress
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
also
Token also
Feature activation-0.005
Top resid features:
did
Token did
Feature activation-0.000
Top resid features:
nothing
Token nothing
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
cleanup
Token cleanup
Feature activation+2.318
Top resid features:
easier
Token easier
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
1700
Token 1700
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
formal
Token formal
Feature activation+0.012
Top resid features:
flower
Token flower
Feature activation+0.019
Top resid features:
production
Token production
Feature activation+2.222
Top resid features:
became
Token became
Feature activation+0.035
Top resid features:
established
Token established
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:
Netherlands
Token Netherlands
Feature activation+0.000
Top resid features:
Par
Token Par
Feature activation-0.000
Top resid features:
á
Tokená
Feature activation+0.002
Top resid features:
where
Token where
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
dam
Token dam
Feature activation-0.025
Top resid features:
construction
Token construction
Feature activation+2.215
Top resid features:
is
Token is
Feature activation+0.092
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
perhaps
Token perhaps
Feature activation+0.070
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
rehab
Token rehab
Feature activation+0.266
Top resid features:
work
Token work
Feature activation+1.853
Top resid features:
he
Token he
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
currently
Token currently
Feature activation+0.004
Top resid features:
reported
Token reported
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Print
TokenPrint
Feature activation+0.060
Top resid features:
ing
Tokening
Feature activation+2.004
Top resid features:
human
Token human
Feature activation-0.002
Top resid features:
tissue
Token tissue
Feature activation-0.005
Top resid features:
is
Token is
Feature activation+0.158
Top resid features:
extremely
Token extremely
Feature activation+0.000
Top resid features:
difficult
Token difficult
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.001
Top resid features:
FP
TokenFP
Feature activation-0.001
Top resid features:
."
Token."
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Construction
TokenConstruction
Feature activation+1.895
Top resid features:
of
Token of
Feature activation+0.344
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
$
Token $
Feature activation-0.002
Top resid features:
200
Token200
Feature activation-0.002
Top resid features:
million
Token million
Feature activation-0.002
Top resid features:
water
Token water
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
âĢ
Token âĢ
Feature activation+0.008
Top resid features:
ľ
Tokenľ
Feature activation+0.006
Top resid features:
Water
TokenWater
Feature activation+0.010
Top resid features:
management
Token management
Feature activation+2.208
Top resid features:
is
Token is
Feature activation+0.066
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
developing
Token developing
Feature activation+0.000
Top resid features:
new
Token new
Feature activation-0.005
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
car
Tokencar
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
sh
Tokensh
Feature activation+0.002
Top resid features:
ipping
Tokenipping
Feature activation+2.086
Top resid features:
to
Token to
Feature activation+0.212
Top resid features:
White
Token White
Feature activation-0.005
Top resid features:
horse
Tokenhorse
Feature activation-0.007
Top resid features:
Motors
Token Motors
Feature activation-0.010
Top resid features:
was
Token was
Feature activation+0.017
Top resid features:
mitochond
Token mitochond
Feature activation+0.009
Top resid features:
ria
Tokenria
Feature activation+0.005
Top resid features:
shows
Token shows
Feature activation-0.009
Top resid features:
how
Token how
Feature activation-0.035
Top resid features:
energy
Token energy
Feature activation+0.039
Top resid features:
generation
Token generation
Feature activation+2.160
Top resid features:
is
Token is
Feature activation+0.067
Top resid features:
tied
Token tied
Feature activation+0.000
Top resid features:
tightly
Token tightly
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.01

Head 3: 0.11

Head 4: 0.05

Head 5: 0.05

Head 6: 0.05

Head 7: 0.02

Head 8: 0.55

Head 9: 0.05

Head 10: 0.01

Head 11: 0.01

Positive logits

intensive2.20

undertaken2.15

underway2.13

done2.10

Techniques1.99

method1.98

intensive1.95

occurring1.92

facilitated1.92

processes1.92

exped1.91

Methods1.90

process1.88

routine1.88

involves1.82

expense1.82

performed1.82

techniques1.80

isoft1.79

methods1.78

Negative logits

-1.61

lash-1.60

Antar-1.59

lashed-1.58

bearer-1.56

NAS-1.51

lashes-1.46

declare-1.45

soType-1.45

llah-1.43

punched-1.40

holder-1.39

anamo-1.38

urn-1.38

Garg-1.37

rallying-1.35

citiz-1.35

Zur-1.34

Santa-1.33

Tall-1.33

INTERVAL 2.056 - 2.284
CONTAINS 0.001%

Lizard
Token Lizard
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
production
Tokenproduction
Feature activation+0.011
would
Token would
Feature activation+2.050
be
Token be
Feature activation+2.102
a
Token a
Feature activation+0.848
GO
Token GO
Feature activation+0.000
!
Token!
Feature activation+0.000
Thank
Token Thank
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.000
where
Token where
Feature activation+0.000
manufacturing
Token manufacturing
Feature activation+0.000
is
Token is
Feature activation+2.277
legal
Token legal
Feature activation+0.791
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
requires
Token requires
Feature activation+0.000
money
Token money
Feature activation+0.000
seven
Token seven
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
filming
Token filming
Feature activation+0.026
commenced
Token commenced
Feature activation+2.127
on
Token on
Feature activation+0.965
January
Token January
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
1980
Token 1980
Feature activation+0.204
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Construction
TokenConstruction
Feature activation+0.165
is
Token is
Feature activation+2.284
due
Token due
Feature activation+2.139
to
Token to
Feature activation+2.265
begin
Token begin
Feature activation+2.210
next
Token next
Feature activation+0.558
year
Token year
Feature activation+0.943

INTERVAL 1.827 - 2.056
CONTAINS 0.001%

say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.323
would
Token would
Feature activation+2.049
actually
Token actually
Feature activation+1.962
begin
Token begin
Feature activation+1.891
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
change
Token change
Feature activation+0.000
declined
Token declined
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.323
would
Token would
Feature activation+2.049
actually
Token actually
Feature activation+1.962
begin
Token begin
Feature activation+1.891
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
year
Tokenyear
Feature activation+0.038
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
hip
Token hip
Feature activation+0.000
injury
Token injury
Feature activation+0.000
will
Token will
Feature activation+1.832
be
Token be
Feature activation+1.764
for
Token for
Feature activation+0.619
an
Token an
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
audition
Token audition
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
Lizard
Token Lizard
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
production
Tokenproduction
Feature activation+0.011
would
Token would
Feature activation+2.050
be
Token be
Feature activation+2.102
a
Token a
Feature activation+0.848
GO
Token GO
Feature activation+0.000
!
Token!
Feature activation+0.000
Thank
Token Thank
Feature activation+0.000
did
Token did
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
cleanup
Token cleanup
Feature activation+0.969
easier
Token easier
Feature activation+1.870
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 1.599 - 1.827
CONTAINS 0.002%

that
Token that
Feature activation+0.000
characterized
Token characterized
Feature activation+0.137
shale
Token shale
Feature activation+0.000
gas
Token gas
Feature activation+0.000
fracking
Token fracking
Feature activation+0.000
as
Token as
Feature activation+1.791
an
Token an
Feature activation+1.337
uncontrolled
Token uncontrolled
Feature activation+1.439
science
Token science
Feature activation+0.017
experiment
Token experiment
Feature activation+0.000
and
Token and
Feature activation+0.000
weekends
Token weekends
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
patrolling
Token patrolling
Feature activation+0.396
will
Token will
Feature activation+1.510
be
Token be
Feature activation+1.604
increased
Token increased
Feature activation+0.613
on
Token on
Feature activation+0.236
New
Token New
Feature activation+0.000
Year
Token Year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
he
Token he
Feature activation+1.451
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.059
currently
Token currently
Feature activation+1.365
putting
Token putting
Feature activation+1.721
in
Token in
Feature activation+1.700
on
Token on
Feature activation+1.185
a
Token a
Feature activation+0.122
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
ing
Tokening
Feature activation+0.065
human
Token human
Feature activation+0.000
tissue
Token tissue
Feature activation+0.172
is
Token is
Feature activation+1.825
extremely
Token extremely
Feature activation+1.422
difficult
Token difficult
Feature activation+1.618
because
Token because
Feature activation+0.154
of
Token of
Feature activation+0.358
the
Token the
Feature activation+0.127
oxygen
Token oxygen
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
jail
Token jail
Feature activation+0.000
began
Token began
Feature activation+1.824
in
Token in
Feature activation+0.572
2011
Token 2011
Feature activation+0.274
under
Token under
Feature activation+0.240
County
Token County
Feature activation+0.000
Executive
Token Executive
Feature activation+0.000

INTERVAL 1.371 - 1.599
CONTAINS 0.004%

and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
extend
Token extend
Feature activation+0.000
its
Token its
Feature activation+0.000
development
Token development
Feature activation+0.040
to
Token to
Feature activation+1.435
10
Token 10
Feature activation+0.885
cities
Token cities
Feature activation+0.000
including
Token including
Feature activation+0.000
Var
Token Var
Feature activation+0.000
anas
Tokenanas
Feature activation+0.000
on
Token on
Feature activation+0.000
street
Token street
Feature activation+0.000
corners
Token corners
Feature activation+0.000
or
Token or
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
other
Token other
Feature activation+1.434
people
Token people
Feature activation+0.330
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
homes
Token homes
Feature activation+0.107
Print
TokenPrint
Feature activation+0.000
ing
Tokening
Feature activation+0.065
human
Token human
Feature activation+0.000
tissue
Token tissue
Feature activation+0.172
is
Token is
Feature activation+1.825
extremely
Token extremely
Feature activation+1.422
difficult
Token difficult
Feature activation+1.618
because
Token because
Feature activation+0.154
of
Token of
Feature activation+0.358
the
Token the
Feature activation+0.127
oxygen
Token oxygen
Feature activation+0.000
,
Token,
Feature activation+0.000
formal
Token formal
Feature activation+0.000
flower
Token flower
Feature activation+0.000
production
Token production
Feature activation+0.644
became
Token became
Feature activation+1.858
established
Token established
Feature activation+1.371
in
Token in
Feature activation+0.394
the
Token the
Feature activation+0.269
Netherlands
Token Netherlands
Feature activation+0.000
with
Token with
Feature activation+0.132
the
Token the
Feature activation+0.109
ing
Tokening
Feature activation+0.465
(
Token (
Feature activation+1.023
or
Tokenor
Feature activation+0.921
mold
Token mold
Feature activation+0.000
ering
Tokenering
Feature activation+0.335
)
Token)
Feature activation+1.548
toilets
Token toilets
Feature activation+0.000
,
Token,
Feature activation+0.000
active
Token active
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ers
Tokeners
Feature activation+0.112

INTERVAL 1.142 - 1.371
CONTAINS 0.009%

since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
licensing
Token licensing
Feature activation+0.000
that
Token that
Feature activation+0.940
Spotify
Token Spotify
Feature activation+0.649
has
Token has
Feature activation+1.302
with
Token with
Feature activation+0.000
labels
Token labels
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
rights
Token rights
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ocation
Tokenocation
Feature activation+0.000
,
Token,
Feature activation+0.262
which
Token which
Feature activation+1.148
is
Token is
Feature activation+0.996
the
Token the
Feature activation+1.266
highest
Token highest
Feature activation+0.499
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.148
bat
Token bat
Feature activation+0.013
species
Token species
Feature activation+0.000
their
Token their
Feature activation+0.000
ball
Token ball
Feature activation+0.000
retention
Token retention
Feature activation+0.020
must
Token must
Feature activation+1.306
be
Token be
Feature activation+1.486
far
Token far
Feature activation+1.283
better
Token better
Feature activation+1.310
.
Token.
Feature activation+0.063
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
designing
Token designing
Feature activation+0.000
mobile
Token mobile
Feature activation+0.044
more
Token more
Feature activation+1.277
efficient
Token efficient
Feature activation+0.679
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.030
[
Token[
Feature activation+0.000
10
Token10
Feature activation+0.000
].
Token].
Feature activation+0.000
Liver
Token Liver
Feature activation+0.000
regeneration
Token regeneration
Feature activation+0.067
is
Token is
Feature activation+1.175
also
Token also
Feature activation+1.001
critical
Token critical
Feature activation+0.800
for
Token for
Feature activation+0.298
patients
Token patients
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.914 - 1.142
CONTAINS 0.023%

ers
Tokeners
Feature activation+0.000
that
Token that
Feature activation+0.000
banker
Token banker
Feature activation+0.000
-
Token-
Feature activation+0.144
b
Tokenb
Feature activation+0.000
ashing
Tokenashing
Feature activation+1.068
was
Token was
Feature activation+0.950
un
Token un
Feature activation+0.633
productive
Tokenproductive
Feature activation+0.203
and
Token and
Feature activation+0.318
foolish
Token foolish
Feature activation+0.275
This
TokenThis
Feature activation+0.000
'
Token '
Feature activation+0.000
met
Tokenmet
Feature activation+0.000
agen
Tokenagen
Feature activation+0.000
omics
Tokenomics
Feature activation+0.000
'
Token'
Feature activation+0.942
approach
Token approach
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
approvals
Token approvals
Feature activation+0.000
process
Token process
Feature activation+0.363
is
Token is
Feature activation+1.179
rather
Token rather
Feature activation+1.042
slow
Token slow
Feature activation+0.866
in
Token in
Feature activation+0.551
the
Token the
Feature activation+0.258
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
p
Tokenp
Feature activation+0.000
itch
Tokenitch
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
ing
Tokening
Feature activation+0.056
"
Token"
Feature activation+1.020
in
Token in
Feature activation+1.040
Gal
Token Gal
Feature activation+0.000
le
Tokenle
Feature activation+0.000
,
Token,
Feature activation+0.734
have
Token have
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
can
Token can
Feature activation+0.190
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
Digest
Token Digest
Feature activation+0.000
ion
Tokenion
Feature activation+0.162
starts
Token starts
Feature activation+1.092
in
Token in
Feature activation+0.248
your
Token your
Feature activation+0.432
mouth
Token mouth
Feature activation+0.000
.
Token.
Feature activation+0.000
Your
Token Your
Feature activation+0.000

INTERVAL 0.685 - 0.914
CONTAINS 0.045%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
campaign
Token campaign
Feature activation+0.590
never
Token never
Feature activation+0.689
really
Token really
Feature activation+0.760
recovered
Token recovered
Feature activation+0.113
from
Token from
Feature activation+0.264
the
Token the
Feature activation+0.038
too
Token too
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
talking
Tokentalking
Feature activation+0.000
is
Token is
Feature activation+0.520
not
Token not
Feature activation+0.861
the
Token the
Feature activation+0.968
answer
Token answer
Feature activation+0.404
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
jam
Token jam
Feature activation+0.000
ming
Tokenming
Feature activation+0.028
will
Token will
Feature activation+0.812
only
Token only
Feature activation+0.744
affect
Token affect
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
above
Token above
Feature activation+0.000
50
Token 50
Feature activation+0.000
feet
Token feet
Feature activation+0.000
The
Token The
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
had
Token had
Feature activation+0.103
to
Token to
Feature activation+0.839
be
Token be
Feature activation+0.989
more
Token more
Feature activation+0.688
targeted
Token targeted
Feature activation+0.074
at
Token at
Feature activation+0.000
proteins
Token proteins
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.003
nuances
Token nuances
Feature activation+0.000
of
Token of
Feature activation+0.000
text
Token text
Feature activation+0.000
handling
Token handling
Feature activation+0.000
including
Token including
Feature activation+0.693
all
Token all
Feature activation+0.418
the
Token the
Feature activation+0.317
platform
Token platform
Feature activation+0.000
native
Token native
Feature activation+0.000
keyboard
Token keyboard
Feature activation+0.000

INTERVAL 0.457 - 0.685
CONTAINS 0.103%

.
Token.
Feature activation+0.000
Warfare
Token Warfare
Feature activation+0.000
in
Token in
Feature activation+0.406
Greece
Token Greece
Feature activation+0.201
had
Token had
Feature activation+0.671
always
Token always
Feature activation+0.685
been
Token been
Feature activation+0.662
dictated
Token dictated
Feature activation+0.000
by
Token by
Feature activation+0.054
the
Token the
Feature activation+0.000
terrain
Token terrain
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
or
Token or
Feature activation+0.000
charging
Token charging
Feature activation+0.000
a
Token a
Feature activation+0.000
battery
Token battery
Feature activation+0.465
in
Token in
Feature activation+0.511
a
Token a
Feature activation+0.099
hot
Token hot
Feature activation+0.000
environment
Token environment
Feature activation+0.000
can
Token can
Feature activation+0.000
cause
Token cause
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
journalism
Token journalism
Feature activation+0.000
;
Token;
Feature activation+0.029
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.633
acquies
Token acquies
Feature activation+0.000
cence
Tokencence
Feature activation+0.000
to
Token to
Feature activation+0.000
propaganda
Token propaganda
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Food
TokenFood
Feature activation+0.000
science
Token science
Feature activation+0.000
has
Token has
Feature activation+0.533
created
Token created
Feature activation+0.000
some
Token some
Feature activation+0.000
catast
Token catast
Feature activation+0.000
rop
Tokenrop
Feature activation+0.000
hes
Tokenhes
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
selling
Token selling
Feature activation+0.000
points
Token points
Feature activation+0.460
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.228 - 0.457
CONTAINS 0.251%

,
Token,
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
and
Token and
Feature activation+0.000
articles
Token articles
Feature activation+0.087
are
Token are
Feature activation+0.190
not
Token not
Feature activation+0.239
the
Token the
Feature activation+0.127
same
Token same
Feature activation+0.031
as
Token as
Feature activation+0.057
playing
Token playing
Feature activation+0.000
through
Token through
Feature activation+0.000
edar
Tokenedar
Feature activation+0.000
Grove
Token Grove
Feature activation+0.000
Comp
Token Comp
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
ing
Tokening
Feature activation+0.000
is
Token is
Feature activation+0.281
part
Token part
Feature activation+0.015
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.000
-
Token-
Feature activation+0.000
some
Token some
Feature activation+0.000
type
Token type
Feature activation+0.000
of
Token of
Feature activation+0.000
body
Token body
Feature activation+0.000
covering
Token covering
Feature activation+0.000
sticking
Token sticking
Feature activation+0.234
up
Token up
Feature activation+0.017
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
explanation
Token explanation
Feature activation+0.000
appet
Token appet
Feature activation+0.000
izer
Tokenizer
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
your
Token your
Feature activation+0.000
digestion
Token digestion
Feature activation+0.329
going
Token going
Feature activation+1.074
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
hew
Tokenhew
Feature activation+0.000
neglected
Token neglected
Feature activation+0.000
the
Token the
Feature activation+0.000
development
Token development
Feature activation+0.000
of
Token of
Feature activation+0.000
cavalry
Token cavalry
Feature activation+0.000
in
Token in
Feature activation+0.263
their
Token their
Feature activation+0.111
military
Token military
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.228
CONTAINS 99.561%

was
Token was
Feature activation+0.000
buried
Token buried
Feature activation+0.000
on
Token on
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Iran
TokenIran
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
state
Token state
Feature activation+0.000
radio
Token radio
Feature activation+0.000
to
Token to
Feature activation+0.000
illuminate
Token illuminate
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
thereby
Token thereby
Feature activation+0.000
,
Token,
Feature activation+0.000
illuminate
Token illuminate
Feature activation+0.000
the
Token the
Feature activation+0.000
present
Token present
Feature activation+0.000
reliever
Token reliever
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
injuries
Token injuries
Feature activation+0.000
stemming
Token stemming
Feature activation+0.000
from
Token from
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
format
Token format
Feature activation+0.000
(
Token (
Feature activation+0.000
well
Tokenwell
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
really
Token really
Feature activation+0.000
)
Token)
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
ession
Tokenession
Feature activation+0.000
:
Token:
Feature activation+0.000
Mechan
Token Mechan
Feature activation+0.000
ic
Tokenic
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+0.429
Development
Token Development
Feature activation+0.692
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.429
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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 H7.8: (feature 14163)

TOP ACTIVATIONS
MAX = 3.903

class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.881
has
Token has
Feature activation+3.490
been
Token been
Feature activation+3.903
filed
Token filed
Feature activation+1.333
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
of
Token of
Feature activation+0.000
case
Token case
Feature activation+0.000
stemming
Token stemming
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.069
that
Token that
Feature activation+3.855
alleges
Token alleges
Feature activation+0.000
the
Token the
Feature activation+0.000
men
Token men
Feature activation+0.000
were
Token were
Feature activation+0.000
improperly
Token improperly
Feature activation+0.000
civil
Token civil
Feature activation+0.000
fines
Token fines
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.346
was
Token was
Feature activation+3.671
filed
Token filed
Feature activation+0.750
in
Token in
Feature activation+0.543
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
superior
Token superior
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
one
Token one
Feature activation+0.000
federal
Token federal
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
has
Token has
Feature activation+3.537
been
Token been
Feature activation+3.517
filed
Token filed
Feature activation+1.104
over
Token over
Feature activation+0.000
state
Token state
Feature activation+0.000
House
Token House
Feature activation+0.000
least
Token least
Feature activation+0.000
one
Token one
Feature activation+0.000
federal
Token federal
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
has
Token has
Feature activation+3.537
been
Token been
Feature activation+3.517
filed
Token filed
Feature activation+1.104
over
Token over
Feature activation+0.000
state
Token state
Feature activation+0.000
House
Token House
Feature activation+0.000
District
Token District
Feature activation+0.000
A
TokenA
Feature activation+0.000
class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.881
has
Token has
Feature activation+3.490
been
Token been
Feature activation+3.903
filed
Token filed
Feature activation+1.333
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.125
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
payments
Token payments
Feature activation+0.000
was
Token was
Feature activation+3.422
originally
Token originally
Feature activation+2.013
brought
Token brought
Feature activation+1.233
by
Token by
Feature activation+0.742
House
Token House
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+3.348
filed
Token filed
Feature activation+0.798
in
Token in
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
suit
Token suit
Feature activation+0.565
is
Token is
Feature activation+3.342
yet
Token yet
Feature activation+0.845
to
Token to
Feature activation+1.979
be
Token be
Feature activation+1.945
resolved
Token resolved
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+3.335
the
Token the
Feature activation+2.288
latest
Token latest
Feature activation+2.041
falling
Token falling
Feature activation+1.181
out
Token out
Feature activation+0.313
between
Token between
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.220
,
Token,
Feature activation+3.108
argued
Token argued
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
for
Token for
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+1.211
which
Token which
Feature activation+2.748
was
Token was
Feature activation+2.525
appealed
Token appealed
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
family
Token family
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
last
Token last
Feature activation+0.652
week
Token week
Feature activation+2.624
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
disorderly
Token disorderly
Feature activation+0.000
conduct
Token conduct
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
suit
Token suit
Feature activation+0.309
was
Token was
Feature activation+2.528
settled
Token settled
Feature activation+0.000
,
Token,
Feature activation+0.000
entit
Token entit
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
5
Token 5
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+1.211
which
Token which
Feature activation+2.748
was
Token was
Feature activation+2.525
appealed
Token appealed
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+3.335
the
Token the
Feature activation+2.288
latest
Token latest
Feature activation+2.041
falling
Token falling
Feature activation+1.181
out
Token out
Feature activation+0.313
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
slapped
Token slapped
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+2.253
after
Token after
Feature activation+0.000
using
Token using
Feature activation+0.000
a
Token a
Feature activation+0.000
tank
Token tank
Feature activation+0.000
to
Token to
Feature activation+0.000
Miles
Token Miles
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
on
Token on
Feature activation+1.674
Friday
Token Friday
Feature activation+2.159
on
Token on
Feature activation+1.433
behalf
Token behalf
Feature activation+0.000
of
Token of
Feature activation+0.000
Amanda
Token Amanda
Feature activation+0.000
Ob
Token Ob
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+3.335
the
Token the
Feature activation+2.288
latest
Token latest
Feature activation+2.041
falling
Token falling
Feature activation+1.181
out
Token out
Feature activation+0.313
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.125
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
payments
Token payments
Feature activation+0.000
was
Token was
Feature activation+3.422
originally
Token originally
Feature activation+2.013
brought
Token brought
Feature activation+1.233
by
Token by
Feature activation+0.742
House
Token House
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
against
Token against
Feature activation+0.000

Top DFA by src position
MAX = 5.337

<|endoftext|>
Token<|endoftext|>
Feature activation-0.032
Top resid features:
A
TokenA
Feature activation+0.024
Top resid features:
class
Token class
Feature activation-0.018
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
action
Tokenaction
Feature activation+0.758
Top resid features:
suit
Token suit
Feature activation+4.974
Top resid features:
has
Token has
Feature activation+0.085
Top resid features:
been
Token been
Feature activation-0.029
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.081
Top resid features:
case
Token case
Feature activation+0.039
Top resid features:
stemming
Token stemming
Feature activation-0.043
Top resid features:
from
Token from
Feature activation+0.089
Top resid features:
a
Token a
Feature activation+0.141
Top resid features:
lawsuit
Token lawsuit
Feature activation+5.337
Top resid features:
that
Token that
Feature activation+0.114
Top resid features:
alleges
Token alleges
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
men
Token men
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
plus
Token plus
Feature activation+0.013
Top resid features:
civil
Token civil
Feature activation+0.003
Top resid features:
fines
Token fines
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.045
Top resid features:
lawsuit
Token lawsuit
Feature activation+5.205
Top resid features:
was
Token was
Feature activation+0.040
Top resid features:
filed
Token filed
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:
state
Token state
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.156
Top resid features:
At
Token At
Feature activation+0.001
Top resid features:
least
Token least
Feature activation+0.063
Top resid features:
one
Token one
Feature activation+0.058
Top resid features:
federal
Token federal
Feature activation+0.126
Top resid features:
lawsuit
Token lawsuit
Feature activation+5.050
Top resid features:
has
Token has
Feature activation+0.085
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.096
Top resid features:
At
Token At
Feature activation+0.001
Top resid features:
least
Token least
Feature activation+0.037
Top resid features:
one
Token one
Feature activation+0.026
Top resid features:
federal
Token federal
Feature activation+0.105
Top resid features:
lawsuit
Token lawsuit
Feature activation+5.000
Top resid features:
has
Token has
Feature activation+0.150
Top resid features:
been
Token been
Feature activation+0.028
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.031
Top resid features:
A
TokenA
Feature activation+0.025
Top resid features:
class
Token class
Feature activation-0.009
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
action
Tokenaction
Feature activation+0.956
Top resid features:
suit
Token suit
Feature activation+4.334
Top resid features:
has
Token has
Feature activation+0.010
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
charge
Token charge
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
The
TokenThe
Feature activation+0.064
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.517
Top resid features:
over
Token over
Feature activation+0.310
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
payments
Token payments
Feature activation+0.021
Top resid features:
was
Token was
Feature activation+0.077
Top resid features:
originally
Token originally
Feature activation+0.000
Top resid features:
ies
Tokenies
Feature activation+0.001
Top resid features:
ner
Tokenner
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation+0.110
Top resid features:
lawsuit
Token lawsuit
Feature activation+5.272
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
hair
Token hair
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.137
Top resid features:
The
Token The
Feature activation+0.120
Top resid features:
suit
Token suit
Feature activation+4.518
Top resid features:
is
Token is
Feature activation+0.169
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
resolved
Token resolved
Feature activation+0.000
Top resid features:
stolen
Token stolen
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.068
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.739
Top resid features:
is
Token is
Feature activation+0.247
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
latest
Token latest
Feature activation+0.000
Top resid features:
falling
Token falling
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.177
Top resid features:
2001
Token 2001
Feature activation-0.141
Top resid features:
class
Token class
Feature activation+0.072
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
action
Tokenaction
Feature activation+0.591
Top resid features:
suit
Token suit
Feature activation+4.542
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
argued
Token argued
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:
illegal
Token illegal
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
House
Token House
Feature activation+0.003
Top resid features:
Republicans
Token Republicans
Feature activation+0.052
Top resid features:
won
Token won
Feature activation+0.203
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.051
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
which
Token which
Feature activation+0.023
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
appealed
Token appealed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
The
Token The
Feature activation-0.017
Top resid features:
family
Token family
Feature activation+0.004
Top resid features:
filed
Token filed
Feature activation+0.115
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.722
Top resid features:
last
Token last
Feature activation-0.035
Top resid features:
week
Token week
Feature activation-0.129
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
city
Token city
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.004
Top resid features:
disorderly
Token disorderly
Feature activation-0.006
Top resid features:
conduct
Token conduct
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
That
Token That
Feature activation-0.066
Top resid features:
suit
Token suit
Feature activation+3.631
Top resid features:
was
Token was
Feature activation+0.087
Top resid features:
settled
Token settled
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
entit
Token entit
Feature activation+0.000
Top resid features:
ling
Tokenling
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.070
Top resid features:
House
Token House
Feature activation+0.003
Top resid features:
Republicans
Token Republicans
Feature activation+0.016
Top resid features:
won
Token won
Feature activation+0.161
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
lawsuit
Token lawsuit
Feature activation+3.469
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
which
Token which
Feature activation+0.286
Top resid features:
was
Token was
Feature activation+0.057
Top resid features:
appealed
Token appealed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
stolen
Token stolen
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
The
TokenThe
Feature activation+0.033
Top resid features:
lawsuit
Token lawsuit
Feature activation+3.101
Top resid features:
is
Token is
Feature activation+0.916
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
latest
Token latest
Feature activation+0.000
Top resid features:
falling
Token falling
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
star
Token star
Feature activation-0.006
Top resid features:
was
Token was
Feature activation-0.016
Top resid features:
slapped
Token slapped
Feature activation+0.219
Top resid features:
with
Token with
Feature activation+0.092
Top resid features:
a
Token a
Feature activation+0.117
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.077
Top resid features:
this
Token this
Feature activation-0.017
Top resid features:
week
Token week
Feature activation-0.124
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
using
Token using
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
is
Tokenis
Feature activation+0.002
Top resid features:
&
Token &
Feature activation-0.000
Top resid features:
Miles
Token Miles
Feature activation-0.005
Top resid features:
filed
Token filed
Feature activation+0.185
Top resid features:
a
Token a
Feature activation+0.065
Top resid features:
lawsuit
Token lawsuit
Feature activation+4.202
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
Friday
Token Friday
Feature activation-0.205
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
behalf
Token behalf
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
stolen
Token stolen
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
The
TokenThe
Feature activation+0.048
Top resid features:
lawsuit
Token lawsuit
Feature activation+2.611
Top resid features:
is
Token is
Feature activation+0.834
Top resid features:
the
Token the
Feature activation+0.253
Top resid features:
latest
Token latest
Feature activation+0.026
Top resid features:
falling
Token falling
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
charge
Token charge
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation+0.041
Top resid features:
lawsuit
Token lawsuit
Feature activation+2.990
Top resid features:
over
Token over
Feature activation+0.337
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
payments
Token payments
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.286
Top resid features:
originally
Token originally
Feature activation+0.074
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.01

Head 3: 0.09

Head 4: 0.04

Head 5: 0.05

Head 6: 0.06

Head 7: 0.02

Head 8: 0.54

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

waged2.51

filed2.01

ortium1.93

perpetrated1.93

against1.90

fought1.89

against1.89

Against1.86

emate1.83

raged1.82

fighting1.81

launched1.80

erupted1.79

arnaev1.72

spearheaded1.70

leveled1.65

lasted1.64

lodged1.64

levied1.60

iannopoulos1.57

Negative logits

presets-1.80

Preferences-1.76

Nare-1.73

natureconservancy-1.67

ode-1.61

+/--1.61

discretion-1.60

DCS-1.57

preset-1.56

liking-1.55

Û-1.54

notation-1.53

substit-1.53

modulation-1.53

fingertips-1.53

minist-1.52

Recomm-1.51

transporter-1.50

hier-1.48

cues-1.48

INTERVAL 3.513 - 3.903
CONTAINS 0.001%

class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.881
has
Token has
Feature activation+3.490
been
Token been
Feature activation+3.903
filed
Token filed
Feature activation+1.333
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
of
Token of
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
one
Token one
Feature activation+0.000
federal
Token federal
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
has
Token has
Feature activation+3.537
been
Token been
Feature activation+3.517
filed
Token filed
Feature activation+1.104
over
Token over
Feature activation+0.000
state
Token state
Feature activation+0.000
House
Token House
Feature activation+0.000
least
Token least
Feature activation+0.000
one
Token one
Feature activation+0.000
federal
Token federal
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
has
Token has
Feature activation+3.537
been
Token been
Feature activation+3.517
filed
Token filed
Feature activation+1.104
over
Token over
Feature activation+0.000
state
Token state
Feature activation+0.000
House
Token House
Feature activation+0.000
District
Token District
Feature activation+0.000
civil
Token civil
Feature activation+0.000
fines
Token fines
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.346
was
Token was
Feature activation+3.671
filed
Token filed
Feature activation+0.750
in
Token in
Feature activation+0.543
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
superior
Token superior
Feature activation+0.000
case
Token case
Feature activation+0.000
stemming
Token stemming
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.069
that
Token that
Feature activation+3.855
alleges
Token alleges
Feature activation+0.000
the
Token the
Feature activation+0.000
men
Token men
Feature activation+0.000
were
Token were
Feature activation+0.000
improperly
Token improperly
Feature activation+0.000

INTERVAL 3.123 - 3.513
CONTAINS 0.001%

A
TokenA
Feature activation+0.000
class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.881
has
Token has
Feature activation+3.490
been
Token been
Feature activation+3.903
filed
Token filed
Feature activation+1.333
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+3.348
filed
Token filed
Feature activation+0.798
in
Token in
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
suit
Token suit
Feature activation+0.565
is
Token is
Feature activation+3.342
yet
Token yet
Feature activation+0.845
to
Token to
Feature activation+1.979
be
Token be
Feature activation+1.945
resolved
Token resolved
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+3.335
the
Token the
Feature activation+2.288
latest
Token latest
Feature activation+2.041
falling
Token falling
Feature activation+1.181
out
Token out
Feature activation+0.313
between
Token between
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.125
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
payments
Token payments
Feature activation+0.000
was
Token was
Feature activation+3.422
originally
Token originally
Feature activation+2.013
brought
Token brought
Feature activation+1.233
by
Token by
Feature activation+0.742
House
Token House
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000

INTERVAL 2.732 - 3.123
CONTAINS 0.000%

2001
Token 2001
Feature activation+0.000
class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.220
,
Token,
Feature activation+3.108
argued
Token argued
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
for
Token for
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+1.211
which
Token which
Feature activation+2.748
was
Token was
Feature activation+2.525
appealed
Token appealed
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.342 - 2.732
CONTAINS 0.000%

disorderly
Token disorderly
Feature activation+0.000
conduct
Token conduct
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
suit
Token suit
Feature activation+0.309
was
Token was
Feature activation+2.528
settled
Token settled
Feature activation+0.000
,
Token,
Feature activation+0.000
entit
Token entit
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
5
Token 5
Feature activation+0.000
family
Token family
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
last
Token last
Feature activation+0.652
week
Token week
Feature activation+2.624
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+1.211
which
Token which
Feature activation+2.748
was
Token was
Feature activation+2.525
appealed
Token appealed
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.952 - 2.342
CONTAINS 0.001%

lawsuit
Token lawsuit
Feature activation+0.125
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
payments
Token payments
Feature activation+0.000
was
Token was
Feature activation+3.422
originally
Token originally
Feature activation+2.013
brought
Token brought
Feature activation+1.233
by
Token by
Feature activation+0.742
House
Token House
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
against
Token against
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
suit
Token suit
Feature activation+0.565
is
Token is
Feature activation+3.342
yet
Token yet
Feature activation+0.845
to
Token to
Feature activation+1.979
be
Token be
Feature activation+1.945
resolved
Token resolved
Feature activation+0.000
.
Token.
Feature activation+0.000
Stoke
Token Stoke
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+3.335
the
Token the
Feature activation+2.288
latest
Token latest
Feature activation+2.041
falling
Token falling
Feature activation+1.181
out
Token out
Feature activation+0.313
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
currently
Token currently
Feature activation+1.998
seeks
Token seeks
Feature activation+0.000
decl
Token decl
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
atory
Tokenatory
Feature activation+0.000
relief
Token relief
Feature activation+0.000
Miles
Token Miles
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
on
Token on
Feature activation+1.674
Friday
Token Friday
Feature activation+2.159
on
Token on
Feature activation+1.433
behalf
Token behalf
Feature activation+0.000
of
Token of
Feature activation+0.000
Amanda
Token Amanda
Feature activation+0.000
Ob
Token Ob
Feature activation+0.000

INTERVAL 1.561 - 1.952
CONTAINS 0.001%

The
Token The
Feature activation+0.000
suit
Token suit
Feature activation+0.565
is
Token is
Feature activation+3.342
yet
Token yet
Feature activation+0.845
to
Token to
Feature activation+1.979
be
Token be
Feature activation+1.945
resolved
Token resolved
Feature activation+0.000
.
Token.
Feature activation+0.000
Stoke
Token Stoke
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
filed
Token filed
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.328
May
Token May
Feature activation+0.038
30
Token 30
Feature activation+1.773
against
Token against
Feature activation+0.000
Stewart
Token Stewart
Feature activation+0.000
Johnston
Token Johnston
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
&
Token &
Feature activation+0.000
Miles
Token Miles
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
on
Token on
Feature activation+1.674
Friday
Token Friday
Feature activation+2.159
on
Token on
Feature activation+1.433
behalf
Token behalf
Feature activation+0.000
of
Token of
Feature activation+0.000
Amanda
Token Amanda
Feature activation+0.000
it
Token it
Feature activation+0.000
believes
Token believes
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.344
has
Token has
Feature activation+1.246
no
Token no
Feature activation+1.582
merit
Token merit
Feature activation+0.293
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
sex
Token sex
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
ape
Tokenape
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
is
Token is
Feature activation+1.648
behind
Token behind
Feature activation+0.251
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
©
Token©
Feature activation+0.000

INTERVAL 1.171 - 1.561
CONTAINS 0.002%

o
Tokeno
Feature activation+0.000
filed
Token filed
Feature activation+0.000
the
Token the
Feature activation+0.339
suit
Token suit
Feature activation+0.676
last
Token last
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+1.302
in
Token in
Feature activation+0.817
federal
Token federal
Feature activation+0.000
court
Token court
Feature activation+0.000
in
Token in
Feature activation+0.000
California
Token California
Feature activation+0.129
approved
Token approved
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
litigation
Token litigation
Feature activation+0.000
began
Token began
Feature activation+1.522
âĢĶ
Token âĢĶ
Feature activation+0.300
five
Token five
Feature activation+0.316
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
suit
Token suit
Feature activation+0.881
has
Token has
Feature activation+3.490
been
Token been
Feature activation+3.903
filed
Token filed
Feature activation+1.333
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
of
Token of
Feature activation+0.000
Red
Token Red
Feature activation+0.000
s
Tokens
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
town
Token town
Feature activation+0.000
proceed
Token proceed
Feature activation+1.299
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
that
Token that
Feature activation+0.000
court
Token court
Feature activation+0.000
dismissed
Token dismissed
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
if
Token if
Feature activation+0.000
one
Token one
Feature activation+0.813
gets
Token gets
Feature activation+1.197
filed
Token filed
Feature activation+0.541
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.781 - 1.171
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
pan
Token pan
Feature activation+0.000
handler
Tokenhandler
Feature activation+0.000
lawsuits
Token lawsuits
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+1.166
,
Token,
Feature activation+0.415
a
Token a
Feature activation+0.796
2001
Token 2001
Feature activation+0.000
class
Token class
Feature activation+0.000
-
Token-
Feature activation+0.000
might
Token might
Feature activation+0.000
mean
Token mean
Feature activation+0.000
legal
Token legal
Feature activation+0.000
action
Token action
Feature activation+0.000
is
Token is
Feature activation+1.487
taken
Token taken
Feature activation+1.164
against
Token against
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.000
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
suit
Token suit
Feature activation+0.565
is
Token is
Feature activation+3.342
yet
Token yet
Feature activation+0.845
to
Token to
Feature activation+1.979
be
Token be
Feature activation+1.945
resolved
Token resolved
Feature activation+0.000
.
Token.
Feature activation+0.000
Stoke
Token Stoke
Feature activation+0.000
in
Token in
Feature activation+0.330
various
Token various
Feature activation+0.000
countries
Token countries
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.991
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+3.348
filed
Token filed
Feature activation+0.798
in
Token in
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.390 - 0.781
CONTAINS 0.004%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
In
TokenIn
Feature activation+0.000
recent
Token recent
Feature activation+0.000
court
Token court
Feature activation+0.000
filings
Token filings
Feature activation+0.000
,
Token,
Feature activation+0.550
the
Token the
Feature activation+0.392
Food
Token Food
Feature activation+0.000
and
Token and
Feature activation+0.000
Drug
Token Drug
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
and
Token and
Feature activation+0.000
accusations
Token accusations
Feature activation+0.000
of
Token of
Feature activation+0.000
fake
Token fake
Feature activation+0.000
religion
Token religion
Feature activation+0.000
have
Token have
Feature activation+0.478
long
Token long
Feature activation+0.000
been
Token been
Feature activation+0.397
a
Token a
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
to
Token to
Feature activation+0.000
fines
Token fines
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.346
was
Token was
Feature activation+3.671
filed
Token filed
Feature activation+0.750
in
Token in
Feature activation+0.543
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
superior
Token superior
Feature activation+0.000
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.529
suit
Token suit
Feature activation+0.657
stems
Token stems
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
In
TokenIn
Feature activation+0.000
recent
Token recent
Feature activation+0.000
court
Token court
Feature activation+0.000
filings
Token filings
Feature activation+0.000
,
Token,
Feature activation+0.550
the
Token the
Feature activation+0.392
Food
Token Food
Feature activation+0.000
and
Token and
Feature activation+0.000
Drug
Token Drug
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.000 - 0.390
CONTAINS 99.990%

this
Token this
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
said
Token said
Feature activation+0.000
for
Token for
Feature activation+0.000
sophomore
Token sophomore
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
addiction
Token addiction
Feature activation+0.000
to
Token to
Feature activation+0.000
ben
Token ben
Feature activation+0.000
zos
Tokenzos
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.000
tolerance
Token tolerance
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
salad
Token salad
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
a
Token a
Feature activation+0.000
ca
Token ca
Feature activation+0.000
esar
Tokenesar
Feature activation+0.000
salad
Token salad
Feature activation+0.000
ured
Tokenured
Feature activation+0.000
mayhem
Token mayhem
Feature activation+0.000
"
Token"
Feature activation+0.000
with
Token with
Feature activation+0.000
many
Token many
Feature activation+0.000
delays
Token delays
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
raise
Token raise
Feature activation+0.000
wages
Token wages
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
better
Token better
Feature activation+0.000
.
Token.
Feature activation+0.000
Un
Token Un
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
would
Token would
Feature activation+0.000
campaign
Token campaign
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 H7.8: (feature 23441)

TOP ACTIVATIONS
MAX = 4.224

There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000
asked
Token asked
Feature activation+0.000
These
Token These
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+2.382
my
Token my
Feature activation+3.142
mind
Token mind
Feature activation+0.000
that
Token that
Feature activation+0.000
COP
Token COP
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
is
Token is
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
to
Token to
Feature activation+2.883
us
Token us
Feature activation+2.733
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
to
Token to
Feature activation+2.883
us
Token us
Feature activation+2.733
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+2.382
my
Token my
Feature activation+3.142
mind
Token mind
Feature activation+0.000
that
Token that
Feature activation+0.000
COP
Token COP
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000
asked
Token asked
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
my
Token my
Feature activation+0.000
suspicion
Token suspicion
Feature activation+0.000
as
Token as
Feature activation+2.025
well
Token well
Feature activation+0.954
.
Token.
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Office
TokenOffice
Feature activation+0.000
has
Token has
Feature activation+0.000
'm
Token'm
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
normally
Token normally
Feature activation+0.000
family
Token family
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
story
Token story
Feature activation+0.000
was
Token was
Feature activation+1.943
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
in
Token in
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+1.338
they
Token they
Feature activation+1.746
looked
Token looked
Feature activation+0.200
for
Token for
Feature activation+0.000
signs
Token signs
Feature activation+0.000
of
Token of
Feature activation+0.000
put
Token put
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
normally
Token normally
Feature activation+0.000
be
Token be
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
huge
Token huge
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
in
Token in
Feature activation+1.343
the
Token the
Feature activation+1.387
US
Token US
Feature activation+0.090
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
dead
Token dead
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
in
Token in
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+1.338
they
Token they
Feature activation+1.746
looked
Token looked
Feature activation+0.200
for
Token for
Feature activation+0.000
signs
Token signs
Feature activation+0.000
of
Token of
Feature activation+0.000
fate
Token fate
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
offspring
Token offspring
Feature activation+0.000
can
Token can
Feature activation+0.949
be
Token be
Feature activation+1.334
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
acute
Token acute
Feature activation+0.000
anxiety
Token anxiety
Feature activation+0.000
be
Token be
Feature activation+0.000
taxed
Token taxed
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
is
Token is
Feature activation+1.238
reflected
Token reflected
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
five
Token five
Feature activation+0.000
different
Token different
Feature activation+0.000

Top DFA by src position
MAX = 5.596

fun
Token fun
Feature activation-0.039
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
There
Token There
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.056
Top resid features:
no
Token no
Feature activation+0.039
Top resid features:
doubt
Token doubt
Feature activation+5.596
Top resid features:
in
Token in
Feature activation+0.697
Top resid features:
my
Token my
Feature activation+0.076
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
These
Token These
Feature activation+0.044
Top resid features:
isolated
Token isolated
Feature activation+0.053
Top resid features:
events
Token events
Feature activation+0.103
Top resid features:
put
Token put
Feature activation+0.187
Top resid features:
doubt
Token doubt
Feature activation+5.507
Top resid features:
into
Token into
Feature activation+0.208
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
minds
Token minds
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
These
Token These
Feature activation+0.035
Top resid features:
isolated
Token isolated
Feature activation+0.113
Top resid features:
events
Token events
Feature activation+0.135
Top resid features:
put
Token put
Feature activation+0.074
Top resid features:
doubt
Token doubt
Feature activation+5.074
Top resid features:
into
Token into
Feature activation+0.708
Top resid features:
the
Token the
Feature activation+0.075
Top resid features:
minds
Token minds
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
There
Token There
Feature activation+0.059
Top resid features:
was
Token was
Feature activation+0.102
Top resid features:
no
Token no
Feature activation+0.176
Top resid features:
doubt
Token doubt
Feature activation+5.474
Top resid features:
in
Token in
Feature activation+0.106
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
done
Token done
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.027
Top resid features:
there
Token there
Feature activation+0.003
Top resid features:
's
Token's
Feature activation+0.046
Top resid features:
no
Token no
Feature activation+0.037
Top resid features:
doubt
Token doubt
Feature activation+4.453
Top resid features:
in
Token in
Feature activation+0.650
Top resid features:
my
Token my
Feature activation+0.081
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
COP
Token COP
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.072
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
There
TokenThere
Feature activation+0.111
Top resid features:
is
Token is
Feature activation+0.140
Top resid features:
no
Token no
Feature activation+0.099
Top resid features:
doubt
Token doubt
Feature activation+4.473
Top resid features:
to
Token to
Feature activation+0.059
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.093
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
There
TokenThere
Feature activation+0.131
Top resid features:
is
Token is
Feature activation+0.159
Top resid features:
no
Token no
Feature activation+0.135
Top resid features:
doubt
Token doubt
Feature activation+3.554
Top resid features:
to
Token to
Feature activation+0.815
Top resid features:
us
Token us
Feature activation+0.307
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.060
Top resid features:
These
Token These
Feature activation+0.021
Top resid features:
isolated
Token isolated
Feature activation+0.050
Top resid features:
events
Token events
Feature activation+0.057
Top resid features:
put
Token put
Feature activation+0.025
Top resid features:
doubt
Token doubt
Feature activation+3.785
Top resid features:
into
Token into
Feature activation+0.409
Top resid features:
the
Token the
Feature activation+0.291
Top resid features:
minds
Token minds
Feature activation+0.085
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
done
Token done
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
there
Token there
Feature activation+0.025
Top resid features:
's
Token's
Feature activation+0.069
Top resid features:
no
Token no
Feature activation+0.145
Top resid features:
doubt
Token doubt
Feature activation+4.160
Top resid features:
in
Token in
Feature activation+0.070
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
COP
Token COP
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation-0.041
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
There
Token There
Feature activation+0.094
Top resid features:
was
Token was
Feature activation+0.158
Top resid features:
no
Token no
Feature activation+0.258
Top resid features:
doubt
Token doubt
Feature activation+2.894
Top resid features:
in
Token in
Feature activation+0.410
Top resid features:
my
Token my
Feature activation+0.741
Top resid features:
mind
Token mind
Feature activation+0.132
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
readers
Token readers
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.061
Top resid features:
had
Token had
Feature activation-0.094
Top resid features:
my
Token my
Feature activation+0.289
Top resid features:
suspicion
Token suspicion
Feature activation+3.781
Top resid features:
as
Token as
Feature activation+0.095
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Open
Token Open
Feature activation+0.000
Top resid features:
Office
TokenOffice
Feature activation+0.000
Top resid features:
life
Token life
Feature activation-0.001
Top resid features:
forever
Token forever
Feature activation+0.013
Top resid features:
."
Token."
Feature activation+0.015
Top resid features:
I
Token I
Feature activation-0.032
Top resid features:
'm
Token'm
Feature activation+0.019
Top resid features:
skeptical
Token skeptical
Feature activation+3.303
Top resid features:
,
Token,
Feature activation+0.185
Top resid features:
but
Token but
Feature activation+0.190
Top resid features:
not
Token not
Feature activation+0.521
Top resid features:
as
Token as
Feature activation-0.051
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
adding
Token adding
Feature activation-0.219
Top resid features:
that
Token that
Feature activation-0.059
Top resid features:
his
Token his
Feature activation+0.004
Top resid features:
initial
Token initial
Feature activation+0.122
Top resid features:
skepticism
Token skepticism
Feature activation+3.731
Top resid features:
about
Token about
Feature activation+0.392
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
Bur
Token Bur
Feature activation+0.005
Top resid features:
po
Tokenpo
Feature activation+0.014
Top resid features:
family
Token family
Feature activation-0.018
Top resid features:
person
Token person
Feature activation+0.010
Top resid features:
dead
Token dead
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
When
Token When
Feature activation+0.072
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
doubt
Token doubt
Feature activation+3.821
Top resid features:
,
Token,
Feature activation+0.181
Top resid features:
they
Token they
Feature activation+0.058
Top resid features:
looked
Token looked
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
signs
Token signs
Feature activation+0.000
Top resid features:
life
Token life
Feature activation-0.005
Top resid features:
forever
Token forever
Feature activation+0.012
Top resid features:
."
Token."
Feature activation+0.023
Top resid features:
I
Token I
Feature activation-0.014
Top resid features:
'm
Token'm
Feature activation+0.009
Top resid features:
skeptical
Token skeptical
Feature activation+3.217
Top resid features:
,
Token,
Feature activation+0.286
Top resid features:
but
Token but
Feature activation+0.295
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
life
Token life
Feature activation-0.005
Top resid features:
forever
Token forever
Feature activation+0.010
Top resid features:
."
Token."
Feature activation+0.025
Top resid features:
I
Token I
Feature activation-0.043
Top resid features:
'm
Token'm
Feature activation+0.018
Top resid features:
skeptical
Token skeptical
Feature activation+2.702
Top resid features:
,
Token,
Feature activation+0.599
Top resid features:
but
Token but
Feature activation+0.301
Top resid features:
not
Token not
Feature activation+0.208
Top resid features:
as
Token as
Feature activation-0.101
Top resid features:
much
Token much
Feature activation-0.102
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.322
Top resid features:
is
Token is
Feature activation+0.081
Top resid features:
huge
Token huge
Feature activation-0.069
Top resid features:
uncertainty
Token uncertainty
Feature activation+2.838
Top resid features:
in
Token in
Feature activation+0.778
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.018
Top resid features:
dead
Token dead
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
When
Token When
Feature activation+0.034
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
doubt
Token doubt
Feature activation+3.285
Top resid features:
,
Token,
Feature activation+0.167
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
looked
Token looked
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
signs
Token signs
Feature activation+0.000
Top resid features:
may
Token may
Feature activation-0.005
Top resid features:
have
Token have
Feature activation+0.001
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
exposed
Token exposed
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
uncertainty
Token uncertainty
Feature activation+2.967
Top resid features:
over
Token over
Feature activation+0.528
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
fate
Token fate
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
should
Token should
Feature activation-0.000
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
taxed
Token taxed
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.124
Top resid features:
That
Token That
Feature activation+0.084
Top resid features:
uncertainty
Token uncertainty
Feature activation+2.801
Top resid features:
is
Token is
Feature activation+0.088
Top resid features:
reflected
Token reflected
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:
five
Token five
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.01

Head 3: 0.07

Head 4: 0.06

Head 5: 0.05

Head 6: 0.04

Head 7: 0.02

Head 8: 0.54

Head 9: 0.07

Head 10: 0.02

Head 11: 0.03

Positive logits

anamo1.90

udic1.89

cius1.84

orescence1.80

concede1.72

Ariel1.64

entertained1.60

BILITY1.58

enza1.57

ota1.57

arisen1.56

IENT1.55

arks1.55

igue1.54

arise1.53

bly1.52

ibel1.51

Reserved1.50

orage1.49

ansky1.49

Negative logits

customized-1.95

Heist-1.88

bang-1.77

dos-1.72

tailor-1.64

ufact-1.64

Tycoon-1.62

procession-1.61

rite-1.60

routines-1.57

planned-1.56

custom-1.56

tailored-1.54

benef-1.53

urgy-1.52

fitt-1.51

packages-1.51

Chains-1.50

remod-1.48

promot-1.48

INTERVAL 3.802 - 4.224
CONTAINS 0.000%

These
Token These
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
that
Token that
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000
asked
Token asked
Feature activation+0.000

INTERVAL 3.379 - 3.802
CONTAINS 0.000%

.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000

INTERVAL 2.957 - 3.379
CONTAINS 0.000%

there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+2.382
my
Token my
Feature activation+3.142
mind
Token mind
Feature activation+0.000
that
Token that
Feature activation+0.000
COP
Token COP
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 2.534 - 2.957
CONTAINS 0.000%

events
Token events
Feature activation+0.000
put
Token put
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
into
Token into
Feature activation+3.862
the
Token the
Feature activation+3.860
minds
Token minds
Feature activation+2.593
of
Token of
Feature activation+0.616
the
Token the
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
to
Token to
Feature activation+2.883
us
Token us
Feature activation+2.733
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
to
Token to
Feature activation+2.883
us
Token us
Feature activation+2.733
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.112 - 2.534
CONTAINS 0.000%

,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+2.382
my
Token my
Feature activation+3.142
mind
Token mind
Feature activation+0.000
that
Token that
Feature activation+0.000
COP
Token COP
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
in
Token in
Feature activation+3.695
my
Token my
Feature activation+4.224
mind
Token mind
Feature activation+2.275
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.273
was
Token was
Feature activation+0.000
asked
Token asked
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.690 - 2.112
CONTAINS 0.001%

I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
'm
Token'm
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
normally
Token normally
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
in
Token in
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+1.338
they
Token they
Feature activation+1.746
looked
Token looked
Feature activation+0.200
for
Token for
Feature activation+0.000
signs
Token signs
Feature activation+0.000
of
Token of
Feature activation+0.000
put
Token put
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
my
Token my
Feature activation+0.000
suspicion
Token suspicion
Feature activation+0.000
as
Token as
Feature activation+2.025
well
Token well
Feature activation+0.954
.
Token.
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Office
TokenOffice
Feature activation+0.000
has
Token has
Feature activation+0.000
family
Token family
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
story
Token story
Feature activation+0.000
was
Token was
Feature activation+1.943
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 1.267 - 1.690
CONTAINS 0.001%

fate
Token fate
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
offspring
Token offspring
Feature activation+0.000
can
Token can
Feature activation+0.949
be
Token be
Feature activation+1.334
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
acute
Token acute
Feature activation+0.000
anxiety
Token anxiety
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
,
Token,
Feature activation+0.961
but
Token but
Feature activation+0.250
not
Token not
Feature activation+1.691
as
Token as
Feature activation+1.988
much
Token much
Feature activation+1.564
as
Token as
Feature activation+0.493
I
Token I
Feature activation+0.000
might
Token might
Feature activation+0.000
normally
Token normally
Feature activation+0.000
be
Token be
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
huge
Token huge
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
in
Token in
Feature activation+1.343
the
Token the
Feature activation+1.387
US
Token US
Feature activation+0.090
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
dead
Token dead
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
in
Token in
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
,
Token,
Feature activation+1.338
they
Token they
Feature activation+1.746
looked
Token looked
Feature activation+0.200
for
Token for
Feature activation+0.000
signs
Token signs
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.845 - 1.267
CONTAINS 0.001%

Flan
Token Flan
Feature activation+0.000
nery
Tokennery
Feature activation+0.000
still
Token still
Feature activation+0.000
has
Token has
Feature activation+0.000
questions
Token questions
Feature activation+0.000
to
Token to
Feature activation+0.913
answer
Token answer
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
fate
Token fate
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
offspring
Token offspring
Feature activation+0.000
can
Token can
Feature activation+0.949
be
Token be
Feature activation+1.334
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
acute
Token acute
Feature activation+0.000
posting
Token posting
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
strike
Token strike
Feature activation+0.000
fear
Token fear
Feature activation+0.000
into
Token into
Feature activation+1.048
the
Token the
Feature activation+0.360
hearts
Token hearts
Feature activation+0.000
of
Token of
Feature activation+0.000
diplomats
Token diplomats
Feature activation+0.000
in
Token in
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
my
Token my
Feature activation+0.000
suspicion
Token suspicion
Feature activation+0.000
as
Token as
Feature activation+2.025
well
Token well
Feature activation+0.954
.
Token.
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Office
TokenOffice
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
,
Token,
Feature activation+0.000
Car
Token Car
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
doubts
Token doubts
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+1.090
but
Token but
Feature activation+0.079
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
reason
Token reason
Feature activation+0.000

INTERVAL 0.422 - 0.845
CONTAINS 0.002%

speakers
Token speakers
Feature activation+0.000
to
Token to
Feature activation+0.000
dispar
Token dispar
Feature activation+0.000
age
Tokenage
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
and
Token and
Feature activation+0.758
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
fear
Token fear
Feature activation+0.000
-
Token-
Feature activation+0.056
based
Tokenbased
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
question
Token question
Feature activation+0.000
marks
Token marks
Feature activation+0.631
going
Token going
Feature activation+0.315
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
about
Token about
Feature activation+0.416
that
Token that
Feature activation+0.745
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Christ
TokenChrist
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
community
Token community
Feature activation+0.000
does
Token does
Feature activation+0.000
assess
Token assess
Feature activation+0.000
with
Token with
Feature activation+0.379
varying
Token varying
Feature activation+0.233
degrees
Token degrees
Feature activation+0.664
of
Token of
Feature activation+0.307
confidence
Token confidence
Feature activation+0.062
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
t
Tokent
Feature activation+0.000
really
Token really
Feature activation+0.000
sure
Token sure
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.102
time
Token time
Feature activation+0.625
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000

INTERVAL 0.000 - 0.422
CONTAINS 99.995%

citing
Token citing
Feature activation+0.000
local
Token local
Feature activation+0.000
support
Token support
Feature activation+0.000
and
Token and
Feature activation+0.000
low
Token low
Feature activation+0.000
turnout
Token turnout
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
ges
Tokenges
Feature activation+0.000
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
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000
possible
Token possible
Feature activation+0.000
to
Token to
Feature activation+0.000
stack
Token stack
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
who
Token who
Feature activation+0.000
fought
Token fought
Feature activation+0.000
for
Token for
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
listening
Token listening
Feature activation+0.000
and
Token and
Feature activation+0.000
exploring
Token exploring
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
R
TokenR
Feature activation+0.000
U
TokenU
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
Y
TokenY
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
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
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
football
Token football
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