H9.3 top features

Top feature 0 in H9.3: (feature 14659)

TOP ACTIVATIONS
MAX = 9.018

.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.915
w
Tokenw
Feature activation+9.018
B
TokenB
Feature activation+0.379
Q
TokenQ
Feature activation+6.096
v
Tokenv
Feature activation+6.297
KA
TokenKA
Feature activation+1.122
j
Tokenj
Feature activation+6.220
.
Token.
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
/
Token/
Feature activation+0.000
1
Token1
Feature activation+1.342
X
TokenX
Feature activation+7.558
ig
Tokenig
Feature activation+8.755
24
Token24
Feature activation+5.608
I
TokenI
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.696
v
Tokenv
Feature activation+8.609
9
Token9
Feature activation+7.485
BL
TokenBL
Feature activation+4.856
GF
TokenGF
Feature activation+3.229
Ad
TokenAd
Feature activation+3.200
ki
Tokenki
Feature activation+3.411
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.978
d
Tokend
Feature activation+8.486
E
TokenE
Feature activation+0.624
g
Tokeng
Feature activation+5.392
j
Tokenj
Feature activation+5.756
b
Tokenb
Feature activation+4.529
x
Tokenx
Feature activation+6.684
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.722
p
Tokenp
Feature activation+7.995
8
Token8
Feature activation+8.375
w
Tokenw
Feature activation+7.219
X
TokenX
Feature activation+3.373
WM
TokenWM
Feature activation+1.224
uz
Tokenuz
Feature activation+4.833
Es
TokenEs
Feature activation+0.000
.
Token.
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
/
Token/
Feature activation+0.000
1
Token1
Feature activation+4.069
T
TokenT
Feature activation+5.590
p
Tokenp
Feature activation+8.357
4
Token4
Feature activation+7.144
F
TokenF
Feature activation+5.395
q
Tokenq
Feature activation+5.510
D
TokenD
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.727
sq
Tokensq
Feature activation+8.210
t
Tokent
Feature activation+6.113
Az
TokenAz
Feature activation+4.936
Z
TokenZ
Feature activation+3.950
8
Token8
Feature activation+5.238
h
Tokenh
Feature activation+5.735
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.586
by
Tokenby
Feature activation+2.544
6
Token6
Feature activation+8.154
r
Tokenr
Feature activation+5.999
9
Token9
Feature activation+6.851
dt
Tokendt
Feature activation+4.324
I
TokenI
Feature activation+0.586
Y
TokenY
Feature activation+5.014
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
youtu
Tokenyoutu
Feature activation+0.000
.
Token.
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
/
Token/
Feature activation+8.140
t
Tokent
Feature activation+6.113
DD
TokenDD
Feature activation+2.962
G
TokenG
Feature activation+0.545
K
TokenK
Feature activation+3.223
ST
TokenST
Feature activation+2.218
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+3.624
N
TokenN
Feature activation+1.924
7
Token7
Feature activation+8.096
x
Tokenx
Feature activation+7.199
1
Token1
Feature activation+5.597
u
Tokenu
Feature activation+4.128
VM
TokenVM
Feature activation+2.248
N
TokenN
Feature activation+1.355
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.503
J
TokenJ
Feature activation+4.518
T
TokenT
Feature activation+0.873
3
Token3
Feature activation+8.026
Hi
TokenHi
Feature activation+2.949
B
TokenB
Feature activation+1.045
j
Tokenj
Feature activation+4.984
Y
TokenY
Feature activation+3.428
dj
Tokendj
Feature activation+1.936
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.722
p
Tokenp
Feature activation+7.995
8
Token8
Feature activation+8.375
w
Tokenw
Feature activation+7.219
X
TokenX
Feature activation+3.373
WM
TokenWM
Feature activation+1.224
uz
Tokenuz
Feature activation+4.833
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+4.924
c
Tokenc
Feature activation+6.205
7
Token7
Feature activation+7.901
D
TokenD
Feature activation+1.050
op
Tokenop
Feature activation+3.917
Z
TokenZ
Feature activation+5.216
m
Tokenm
Feature activation+4.750
P
TokenP
Feature activation+2.186
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.396
R
TokenR
Feature activation+1.180
w
Tokenw
Feature activation+7.763
X
TokenX
Feature activation+3.622
R
TokenR
Feature activation+0.867
Ju
TokenJu
Feature activation+2.730
HA
TokenHA
Feature activation+2.315
zy
Tokenzy
Feature activation+1.898
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.871
a
Tokena
Feature activation+3.300
5
Token5
Feature activation+7.754
DN
TokenDN
Feature activation+1.251
GE
TokenGE
Feature activation+3.420
q
Tokenq
Feature activation+6.659
X
TokenX
Feature activation+5.577
n
Tokenn
Feature activation+6.410
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+3.991
2
Token2
Feature activation+3.534
U
TokenU
Feature activation+1.029
x
Tokenx
Feature activation+7.751
FE
TokenFE
Feature activation+3.508
U
TokenU
Feature activation+1.626
f
Tokenf
Feature activation+6.238
Cy
TokenCy
Feature activation+6.494
z
Tokenz
Feature activation+3.740
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.210
watch
Tokenwatch
Feature activation+0.704
?
Token?
Feature activation+0.000
v
Tokenv
Feature activation+0.000
=
Token=
Feature activation+7.735
PG
TokenPG
Feature activation+6.859
un
Tokenun
Feature activation+6.060
Ul
TokenUl
Feature activation+4.003
Ed
TokenEd
Feature activation+1.991
50
Token50
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.501
r
Tokenr
Feature activation+6.595
j
Tokenj
Feature activation+7.729
E
TokenE
Feature activation+0.361
5
Token5
Feature activation+7.060
s
Tokens
Feature activation+3.362
dr
Tokendr
Feature activation+5.121
6
Token6
Feature activation+7.071
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.903
e
Tokene
Feature activation+4.577
7
Token7
Feature activation+7.644
sb
Tokensb
Feature activation+4.206
1
Token1
Feature activation+5.135
oz
Tokenoz
Feature activation+5.263
X
TokenX
Feature activation+4.656
8
Token8
Feature activation+6.760
/
Token/
Feature activation+6.426
isu
Tokenisu
Feature activation+4.019
q
Tokenq
Feature activation+7.455
it
Tokenit
Feature activation+6.264
EC
TokenEC
Feature activation+5.364
6
Token6
Feature activation+7.558
z
Tokenz
Feature activation+4.806
âĢĶ
Token âĢĶ
Feature activation+0.000
AFL
Token AFL
Feature activation+0.000
(@
Token (@
Feature activation+0.000
A
TokenA
Feature activation+0.000

Top DFA by src position
MAX = 9.183

pic
Tokenpic
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.115
Top resid features:
twitter
Tokentwitter
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
com
Tokencom
Feature activation+0.009
Top resid features:
/
Token/
Feature activation+9.183
Top resid features:
w
Tokenw
Feature activation+0.508
Top resid features:
B
TokenB
Feature activation+0.000
Top resid features:
Q
TokenQ
Feature activation+0.000
Top resid features:
v
Tokenv
Feature activation+0.000
Top resid features:
KA
TokenKA
Feature activation+0.000
Top resid features:
://
Token://
Feature activation-0.004
Top resid features:
usat
Tokenusat
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
ly
Tokenly
Feature activation+0.001
Top resid features:
/
Token/
Feature activation+0.037
Top resid features:
1
Token1
Feature activation+7.367
Top resid features:
X
TokenX
Feature activation+1.969
Top resid features:
ig
Tokenig
Feature activation+0.081
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.048
Top resid features:
twitter
Tokentwitter
Feature activation+0.022
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
com
Tokencom
Feature activation+0.046
Top resid features:
/
Token/
Feature activation+8.834
Top resid features:
v
Tokenv
Feature activation+0.287
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
BL
TokenBL
Feature activation+0.000
Top resid features:
GF
TokenGF
Feature activation+0.000
Top resid features:
Ad
TokenAd
Feature activation+0.000
Top resid features:
pic
Tokenpic
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.054
Top resid features:
twitter
Tokentwitter
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
com
Tokencom
Feature activation+0.017
Top resid features:
/
Token/
Feature activation+8.925
Top resid features:
d
Tokend
Feature activation+0.109
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
g
Tokeng
Feature activation+0.000
Top resid features:
j
Tokenj
Feature activation+0.000
Top resid features:
b
Tokenb
Feature activation+0.000
Top resid features:
pic
Tokenpic
Feature activation-0.012
Top resid features:
.
Token.
Feature activation-0.088
Top resid features:
twitter
Tokentwitter
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
com
Tokencom
Feature activation+0.024
Top resid features:
/
Token/
Feature activation+5.867
Top resid features:
p
Tokenp
Feature activation+1.681
Top resid features:
8
Token8
Feature activation+0.811
Top resid features:
w
Tokenw
Feature activation+0.000
Top resid features:
X
TokenX
Feature activation+0.000
Top resid features:
WM
TokenWM
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
bit
Token bit
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
ly
Tokenly
Feature activation+0.021
Top resid features:
/
Token/
Feature activation+0.209
Top resid features:
1
Token1
Feature activation+8.030
Top resid features:
T
TokenT
Feature activation+0.934
Top resid features:
p
Tokenp
Feature activation-0.139
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
F
TokenF
Feature activation+0.000
Top resid features:
q
Tokenq
Feature activation+0.000
Top resid features:
https
Token https
Feature activation-0.006
Top resid features:
://
Token://
Feature activation-0.006
Top resid features:
t
Tokent
Feature activation+0.020
Top resid features:
.
Token.
Feature activation-0.061
Top resid features:
co
Tokenco
Feature activation+0.040
Top resid features:
/
Token/
Feature activation+8.070
Top resid features:
sq
Tokensq
Feature activation+1.166
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
Az
TokenAz
Feature activation+0.000
Top resid features:
Z
TokenZ
Feature activation+0.000
Top resid features:
8
Token8
Feature activation+0.000
Top resid features:
://
Token://
Feature activation-0.005
Top resid features:
t
Tokent
Feature activation+0.022
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
co
Tokenco
Feature activation+0.017
Top resid features:
/
Token/
Feature activation+3.523
Top resid features:
by
Tokenby
Feature activation+4.758
Top resid features:
6
Token6
Feature activation+0.441
Top resid features:
r
Tokenr
Feature activation+0.000
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
dt
Tokendt
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
https
Token https
Feature activation+0.014
Top resid features:
://
Token://
Feature activation-0.010
Top resid features:
youtu
Tokenyoutu
Feature activation+0.020
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
be
Tokenbe
Feature activation+0.047
Top resid features:
/
Token/
Feature activation+8.733
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
DD
TokenDD
Feature activation+0.000
Top resid features:
G
TokenG
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
ST
TokenST
Feature activation+0.000
Top resid features:
http
Token http
Feature activation+0.001
Top resid features:
://
Token://
Feature activation-0.004
Top resid features:
t
Tokent
Feature activation+0.030
Top resid features:
.
Token.
Feature activation-0.053
Top resid features:
co
Tokenco
Feature activation+0.034
Top resid features:
/
Token/
Feature activation+5.176
Top resid features:
N
TokenN
Feature activation+2.703
Top resid features:
7
Token7
Feature activation+0.789
Top resid features:
x
Tokenx
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
u
Tokenu
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
twitter
Tokentwitter
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
com
Tokencom
Feature activation+0.047
Top resid features:
/
Token/
Feature activation+4.502
Top resid features:
J
TokenJ
Feature activation+2.742
Top resid features:
T
TokenT
Feature activation+0.624
Top resid features:
3
Token3
Feature activation+0.725
Top resid features:
Hi
TokenHi
Feature activation+0.000
Top resid features:
B
TokenB
Feature activation+0.000
Top resid features:
pic
Tokenpic
Feature activation-0.015
Top resid features:
.
Token.
Feature activation-0.071
Top resid features:
twitter
Tokentwitter
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation+0.015
Top resid features:
/
Token/
Feature activation+7.704
Top resid features:
p
Tokenp
Feature activation+0.412
Top resid features:
8
Token8
Feature activation+0.000
Top resid features:
w
Tokenw
Feature activation+0.000
Top resid features:
X
TokenX
Feature activation+0.000
Top resid features:
WM
TokenWM
Feature activation+0.000
Top resid features:
https
Token https
Feature activation+0.008
Top resid features:
://
Token://
Feature activation-0.002
Top resid features:
t
Tokent
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.051
Top resid features:
co
Tokenco
Feature activation+0.025
Top resid features:
/
Token/
Feature activation+3.814
Top resid features:
c
Tokenc
Feature activation+3.517
Top resid features:
7
Token7
Feature activation+1.146
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
op
Tokenop
Feature activation+0.000
Top resid features:
Z
TokenZ
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
twitter
Tokentwitter
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
com
Tokencom
Feature activation+0.019
Top resid features:
/
Token/
Feature activation+5.149
Top resid features:
R
TokenR
Feature activation+1.959
Top resid features:
w
Tokenw
Feature activation+0.209
Top resid features:
X
TokenX
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
Ju
TokenJu
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.090
Top resid features:
twitter
Tokentwitter
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.026
Top resid features:
com
Tokencom
Feature activation+0.064
Top resid features:
/
Token/
Feature activation+5.028
Top resid features:
a
Tokena
Feature activation+2.331
Top resid features:
5
Token5
Feature activation+1.021
Top resid features:
DN
TokenDN
Feature activation+0.000
Top resid features:
GE
TokenGE
Feature activation+0.000
Top resid features:
q
Tokenq
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.046
Top resid features:
twitter
Tokentwitter
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
com
Tokencom
Feature activation+0.026
Top resid features:
/
Token/
Feature activation+3.823
Top resid features:
2
Token2
Feature activation+2.988
Top resid features:
U
TokenU
Feature activation+1.022
Top resid features:
x
Tokenx
Feature activation+0.458
Top resid features:
FE
TokenFE
Feature activation+0.000
Top resid features:
U
TokenU
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation-0.002
Top resid features:
/
Token/
Feature activation-0.012
Top resid features:
watch
Tokenwatch
Feature activation-0.014
Top resid features:
?
Token?
Feature activation+0.031
Top resid features:
v
Tokenv
Feature activation+0.047
Top resid features:
=
Token=
Feature activation+8.277
Top resid features:
PG
TokenPG
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation+0.000
Top resid features:
Ul
TokenUl
Feature activation+0.000
Top resid features:
Ed
TokenEd
Feature activation+0.000
Top resid features:
50
Token50
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.053
Top resid features:
twitter
Tokentwitter
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
com
Tokencom
Feature activation+0.060
Top resid features:
/
Token/
Feature activation+7.096
Top resid features:
r
Tokenr
Feature activation+0.881
Top resid features:
j
Tokenj
Feature activation+0.299
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
pic
Token pic
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.049
Top resid features:
twitter
Tokentwitter
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
com
Tokencom
Feature activation+0.065
Top resid features:
/
Token/
Feature activation+4.990
Top resid features:
e
Tokene
Feature activation+2.102
Top resid features:
7
Token7
Feature activation+1.095
Top resid features:
sb
Tokensb
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
oz
Tokenoz
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation+0.006
Top resid features:
/
Token/
Feature activation+1.716
Top resid features:
isu
Tokenisu
Feature activation+1.456
Top resid features:
q
Tokenq
Feature activation+0.645
Top resid features:
it
Tokenit
Feature activation+1.493
Top resid features:
EC
TokenEC
Feature activation+2.579
Top resid features:
6
Token6
Feature activation+0.442
Top resid features:
z
Tokenz
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
AFL
Token AFL
Feature activation+0.000
Top resid features:
(@
Token (@
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.01

Head 2: 0.03

Head 3: 0.64

Head 4: 0.04

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.03

Head 9: 0.02

Head 10: 0.04

Head 11: 0.03

Positive logits

Cs3.51

YC3.29

wx3.26

EH3.24

YN3.23

RG3.23

DN3.20

rf3.13

YP3.08

DEF3.07

Ns3.02

RP3.01

CB3.00

KT2.99

WF2.98

Cu2.98

cv2.98

KN2.96

UX2.95

FH2.92

Negative logits

textbooks-2.32

biography-2.31

documentary-2.25

professionally-2.09

exhibition-2.09

depiction-2.09

book-2.09

portrait-2.07

broch-2.06

caring-2.06

travel-2.06

detailing-2.06

dressing-2.06

outdoors-2.05

presentation-2.05

travelling-2.04

curriculum-2.04

packaging-2.04

portrayal-2.02

educational-2.02

INTERVAL 8.116 - 9.018
CONTAINS 0.001%

twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.722
p
Tokenp
Feature activation+7.995
8
Token8
Feature activation+8.375
w
Tokenw
Feature activation+7.219
X
TokenX
Feature activation+3.373
WM
TokenWM
Feature activation+1.224
uz
Tokenuz
Feature activation+4.833
Es
TokenEs
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.727
sq
Tokensq
Feature activation+8.210
t
Tokent
Feature activation+6.113
Az
TokenAz
Feature activation+4.936
Z
TokenZ
Feature activation+3.950
8
Token8
Feature activation+5.238
h
Tokenh
Feature activation+5.735
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.978
d
Tokend
Feature activation+8.486
E
TokenE
Feature activation+0.624
g
Tokeng
Feature activation+5.392
j
Tokenj
Feature activation+5.756
b
Tokenb
Feature activation+4.529
x
Tokenx
Feature activation+6.684
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.586
by
Tokenby
Feature activation+2.544
6
Token6
Feature activation+8.154
r
Tokenr
Feature activation+5.999
9
Token9
Feature activation+6.851
dt
Tokendt
Feature activation+4.324
I
TokenI
Feature activation+0.586
Y
TokenY
Feature activation+5.014
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.915
w
Tokenw
Feature activation+9.018
B
TokenB
Feature activation+0.379
Q
TokenQ
Feature activation+6.096
v
Tokenv
Feature activation+6.297
KA
TokenKA
Feature activation+1.122
j
Tokenj
Feature activation+6.220

INTERVAL 7.214 - 8.116
CONTAINS 0.003%

usat
Tokenusat
Feature activation+0.000
.
Token.
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
/
Token/
Feature activation+0.000
2
Token2
Feature activation+0.085
k
Tokenk
Feature activation+7.239
ki
Tokenki
Feature activation+5.508
K
TokenK
Feature activation+5.916
s
Tokens
Feature activation+4.603
x
Tokenx
Feature activation+1.500
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
/
Token/
Feature activation+0.000
1
Token1
Feature activation+1.235
g
Tokeng
Feature activation+6.379
sc
Tokensc
Feature activation+7.442
go
Tokengo
Feature activation+6.597
E
TokenE
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
On
TokenOn
Feature activation+0.000
May
Token May
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.722
p
Tokenp
Feature activation+7.995
8
Token8
Feature activation+8.375
w
Tokenw
Feature activation+7.219
X
TokenX
Feature activation+3.373
WM
TokenWM
Feature activation+1.224
uz
Tokenuz
Feature activation+4.833
Es
TokenEs
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.855
8
Token8
Feature activation+7.371
Cy
TokenCy
Feature activation+3.679
7
Token7
Feature activation+5.715
Y
TokenY
Feature activation+1.905
Pl
TokenPl
Feature activation+5.117
EC
TokenEC
Feature activation+4.577
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.210
watch
Tokenwatch
Feature activation+0.704
?
Token?
Feature activation+0.000
v
Tokenv
Feature activation+0.000
=
Token=
Feature activation+7.735
PG
TokenPG
Feature activation+6.859
un
Tokenun
Feature activation+6.060
Ul
TokenUl
Feature activation+4.003
Ed
TokenEd
Feature activation+1.991
50
Token50
Feature activation+0.000

INTERVAL 6.312 - 7.214
CONTAINS 0.004%

t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.199
W
TokenW
Feature activation+3.238
9
Token9
Feature activation+6.813
L
TokenL
Feature activation+0.590
2
Token2
Feature activation+4.923
b
Tokenb
Feature activation+3.138
2
Token2
Feature activation+3.374
Z
TokenZ
Feature activation+3.439
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.305
SM
TokenSM
Feature activation+5.167
n
Tokenn
Feature activation+5.414
9
Token9
Feature activation+6.670
vl
Tokenvl
Feature activation+6.819
K
TokenK
Feature activation+3.156
cd
Tokencd
Feature activation+4.133
T
TokenT
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
j
Tokenj
Feature activation+7.729
E
TokenE
Feature activation+0.361
5
Token5
Feature activation+7.060
s
Tokens
Feature activation+3.362
dr
Tokendr
Feature activation+5.121
6
Token6
Feature activation+7.071
y
Tokeny
Feature activation+6.013
D
TokenD
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
(@
Token (@
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.127
EN
TokenEN
Feature activation+3.277
g
Tokeng
Feature activation+6.378
1
Token1
Feature activation+5.966
r
Tokenr
Feature activation+5.652
ry
Tokenry
Feature activation+5.648
TF
TokenTF
Feature activation+5.230
U
TokenU
Feature activation+0.000
96
Token96
Feature activation+5.334
X
TokenX
Feature activation+5.019
O
TokenO
Feature activation+0.529
I
TokenI
Feature activation+0.513
w
Tokenw
Feature activation+6.258
v
Tokenv
Feature activation+6.845
8
Token8
Feature activation+6.902
I
TokenI
Feature activation+0.429
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000

INTERVAL 5.411 - 6.312
CONTAINS 0.009%

/
Token/
Feature activation+6.215
k
Tokenk
Feature activation+6.285
Es
TokenEs
Feature activation+5.121
HE
TokenHE
Feature activation+4.650
f
Tokenf
Feature activation+4.997
pu
Tokenpu
Feature activation+5.696
H
TokenH
Feature activation+4.421
p
Tokenp
Feature activation+1.891
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+5.113
Cl
TokenCl
Feature activation+7.340
n
Tokenn
Feature activation+4.601
O
TokenO
Feature activation+0.386
w
Tokenw
Feature activation+6.014
Fs
TokenFs
Feature activation+2.780
X
TokenX
Feature activation+5.278
02
Token02
Feature activation+0.344
âĢĶ
Token âĢĶ
Feature activation+0.000
ke
Token ke
Feature activation+0.000
J
TokenJ
Feature activation+4.452
N
TokenN
Feature activation+1.085
kl
Tokenkl
Feature activation+5.995
5
Token5
Feature activation+6.602
k
Tokenk
Feature activation+6.381
8
Token8
Feature activation+5.520
Il
TokenIl
Feature activation+3.649
K
TokenK
Feature activation+0.588
âĢĶ
Token âĢĶ
Feature activation+0.000
Good
Token Good
Feature activation+0.000
Morning
Token Morning
Feature activation+0.000
/
Token/
Feature activation+5.077
Ds
TokenDs
Feature activation+4.202
95
Token95
Feature activation+6.115
oS
TokenoS
Feature activation+2.791
go
Tokengo
Feature activation+5.457
8
Token8
Feature activation+5.916
f
Tokenf
Feature activation+1.696
âĢĶ
Token âĢĶ
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
J
Token J
Feature activation+0.000
.
Token.
Feature activation+0.000
/
Token/
Feature activation+2.751
I
TokenI
Feature activation+0.204
e
Tokene
Feature activation+3.900
um
Tokenum
Feature activation+4.819
T
TokenT
Feature activation+0.587
as
Tokenas
Feature activation+6.110
R
TokenR
Feature activation+3.505
NN
TokenNN
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Edward
Token Edward
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000

INTERVAL 4.509 - 5.411
CONTAINS 0.012%

t
Tokent
Feature activation+6.113
DD
TokenDD
Feature activation+2.962
G
TokenG
Feature activation+0.545
K
TokenK
Feature activation+3.223
ST
TokenST
Feature activation+2.218
z
Tokenz
Feature activation+5.134
B
TokenB
Feature activation+0.155
x
Tokenx
Feature activation+1.766
k
Tokenk
Feature activation+0.000
check
Token check
Feature activation+0.000
it
Token it
Feature activation+0.000
EN
TokenEN
Feature activation+3.277
g
Tokeng
Feature activation+6.378
1
Token1
Feature activation+5.966
r
Tokenr
Feature activation+5.652
ry
Tokenry
Feature activation+5.648
TF
TokenTF
Feature activation+5.230
U
TokenU
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Danielle
Token Danielle
Feature activation+0.000
Av
Token Av
Feature activation+0.000
itable
Tokenitable
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+5.727
sq
Tokensq
Feature activation+8.210
t
Tokent
Feature activation+6.113
Az
TokenAz
Feature activation+4.936
Z
TokenZ
Feature activation+3.950
8
Token8
Feature activation+5.238
h
Tokenh
Feature activation+5.735
J
TokenJ
Feature activation+3.618
Z
TokenZ
Feature activation+0.066
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+1.192
P
TokenP
Feature activation+3.454
d
Tokend
Feature activation+4.676
g
Tokeng
Feature activation+4.400
3
Token3
Feature activation+5.265
Me
TokenMe
Feature activation+5.350
hw
Tokenhw
Feature activation+4.302
S
TokenS
Feature activation+1.482
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+6.426
isu
Tokenisu
Feature activation+4.019
q
Tokenq
Feature activation+7.455
it
Tokenit
Feature activation+6.264
EC
TokenEC
Feature activation+5.364
6
Token6
Feature activation+7.558
z
Tokenz
Feature activation+4.806
âĢĶ
Token âĢĶ
Feature activation+0.000
AFL
Token AFL
Feature activation+0.000
(@
Token (@
Feature activation+0.000

INTERVAL 3.607 - 4.509
CONTAINS 0.009%

.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.970
l
Tokenl
Feature activation+3.291
BR
TokenBR
Feature activation+3.251
Q
TokenQ
Feature activation+4.084
f
Tokenf
Feature activation+3.983
v
Tokenv
Feature activation+5.358
7
Token7
Feature activation+5.947
rr
Tokenrr
Feature activation+5.151
5
Token5
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+3.834
L
TokenL
Feature activation+1.543
5
Token5
Feature activation+7.318
b
Tokenb
Feature activation+4.038
Up
TokenUp
Feature activation+3.882
FO
TokenFO
Feature activation+0.826
6
Token6
Feature activation+6.258
O
TokenO
Feature activation+1.350
4
Token4
Feature activation+0.505
pic
Token pic
Feature activation+0.000
Y
TokenY
Feature activation+3.719
On
TokenOn
Feature activation+4.621
7
Token7
Feature activation+6.197
y
Tokeny
Feature activation+3.916
O
TokenO
Feature activation+0.196
m
Tokenm
Feature activation+4.356
B
TokenB
Feature activation+1.505
J
TokenJ
Feature activation+3.666
H
TokenH
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Chase
Token Chase
Feature activation+0.000
/
Token/
Feature activation+5.586
by
Tokenby
Feature activation+2.544
6
Token6
Feature activation+8.154
r
Tokenr
Feature activation+5.999
9
Token9
Feature activation+6.851
dt
Tokendt
Feature activation+4.324
I
TokenI
Feature activation+0.586
Y
TokenY
Feature activation+5.014
9
Token9
Feature activation+0.670
âĢĶ
Token âĢĶ
Feature activation+0.000
GL
Token GL
Feature activation+0.000
VL
TokenVL
Feature activation+0.725
8
Token8
Feature activation+2.623
d
Tokend
Feature activation+2.109
0
Token0
Feature activation+3.078
S
TokenS
Feature activation+0.934
6
Token6
Feature activation+3.909
k
Tokenk
Feature activation+2.955
C
TokenC
Feature activation+0.510
f
Tokenf
Feature activation+0.489
I
TokenI
Feature activation+0.000
/
Token/
Feature activation+0.000

INTERVAL 2.705 - 3.607
CONTAINS 0.007%

https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+2.751
I
TokenI
Feature activation+0.204
e
Tokene
Feature activation+3.900
um
Tokenum
Feature activation+4.819
T
TokenT
Feature activation+0.587
as
Tokenas
Feature activation+6.110
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.871
a
Tokena
Feature activation+3.300
5
Token5
Feature activation+7.754
DN
TokenDN
Feature activation+1.251
GE
TokenGE
Feature activation+3.420
q
Tokenq
Feature activation+6.659
X
TokenX
Feature activation+5.577
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+3.991
2
Token2
Feature activation+3.534
U
TokenU
Feature activation+1.029
x
Tokenx
Feature activation+7.751
FE
TokenFE
Feature activation+3.508
U
TokenU
Feature activation+1.626
f
Tokenf
Feature activation+6.238
Cy
TokenCy
Feature activation+6.494
z
Tokenz
Feature activation+3.740
âĢĶ
Token âĢĶ
Feature activation+0.000
T
TokenT
Feature activation+0.873
3
Token3
Feature activation+8.026
Hi
TokenHi
Feature activation+2.949
B
TokenB
Feature activation+1.045
j
Tokenj
Feature activation+4.984
Y
TokenY
Feature activation+3.428
dj
Tokendj
Feature activation+1.936
âĢĶ
Token âĢĶ
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
(@
Token (@
Feature activation+0.000
/-
Token/-
Feature activation+0.087
o
Tokeno
Feature activation+0.444
q
Tokenq
Feature activation+2.773
T
TokenT
Feature activation+2.154
Z
TokenZ
Feature activation+3.980
q
Tokenq
Feature activation+3.476
6
Token6
Feature activation+3.036
f
Tokenf
Feature activation+2.660
4
Token4
Feature activation+2.534
q
Tokenq
Feature activation+0.979
ew
Tokenew
Feature activation+0.000

INTERVAL 1.804 - 2.705
CONTAINS 0.007%

com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+4.855
8
Token8
Feature activation+7.371
Cy
TokenCy
Feature activation+3.679
7
Token7
Feature activation+5.715
Y
TokenY
Feature activation+1.905
Pl
TokenPl
Feature activation+5.117
EC
TokenEC
Feature activation+4.577
X
TokenX
Feature activation+1.189
âĢĶ
Token âĢĶ
Feature activation+0.000
Elon
Token Elon
Feature activation+0.000
Tu
TokenTu
Feature activation+0.000
EF
TokenEF
Feature activation+0.000
+
Token+
Feature activation+0.254
s
Tokens
Feature activation+0.298
2
Token2
Feature activation+1.232
ae
Tokenae
Feature activation+2.156
+
Token+
Feature activation+1.967
Pe
TokenPe
Feature activation+1.539
H
TokenH
Feature activation+1.455
j
Tokenj
Feature activation+1.286
h
Tokenh
Feature activation+1.507
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
/
Token/
Feature activation+3.391
Pa
TokenPa
Feature activation+1.847
Lv
TokenLv
Feature activation+4.460
JD
TokenJD
Feature activation+1.603
v
Tokenv
Feature activation+5.436
D
TokenD
Feature activation+1.151
bl
Tokenbl
Feature activation+0.000
v
Tokenv
Feature activation+0.000
=
Token=
Feature activation+7.735
PG
TokenPG
Feature activation+6.859
un
Tokenun
Feature activation+6.060
Ul
TokenUl
Feature activation+4.003
Ed
TokenEd
Feature activation+1.991
50
Token50
Feature activation+0.000
A
TokenA
Feature activation+0.000
),
Token),
Feature activation+0.000
will
Token will
Feature activation+0.000
face
Token face
Feature activation+0.000
#
Token#
Feature activation+0.000
st
Tokenst
Feature activation+0.000
hash
Tokenhash
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+5.003
fi
Tokenfi
Feature activation+2.360
E
TokenE
Feature activation+1.278
1
Token1
Feature activation+4.129
b
Tokenb
Feature activation+4.246
TR
TokenTR
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.902 - 1.804
CONTAINS 0.016%

i
Tokeni
Feature activation+0.947
V
TokenV
Feature activation+0.443
SH
TokenSH
Feature activation+0.919
0
Token0
Feature activation+0.284
j
Tokenj
Feature activation+1.504
n
Tokenn
Feature activation+1.289
V
TokenV
Feature activation+0.230
AS
TokenAS
Feature activation+0.799
Q
TokenQ
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
0
Token0
Feature activation+0.000
TC
TokenTC
Feature activation+0.666
k
Tokenk
Feature activation+0.000
d
Tokend
Feature activation+1.104
v
Tokenv
Feature activation+1.359
b
Tokenb
Feature activation+1.228
2
Token2
Feature activation+1.348
ds
Tokends
Feature activation+1.030
Z
TokenZ
Feature activation+1.075
SB
TokenSB
Feature activation+0.000
J
TokenJ
Feature activation+0.652
bm
Tokenbm
Feature activation+0.000
e
Tokene
Feature activation+3.708
ac
Tokenac
Feature activation+2.982
61
Token61
Feature activation+1.210
c
Tokenc
Feature activation+1.928
0
Token0
Feature activation+1.407
ef
Tokenef
Feature activation+1.382
74
Token74
Feature activation+1.597
d
Tokend
Feature activation+0.232
_
Token_
Feature activation+0.000
story
Tokenstory
Feature activation+0.000
.
Token.
Feature activation+0.000
jpg
Tokenjpg
Feature activation+0.000
?
Token?
Feature activation+0.000
pub
Tokenpub
Feature activation+0.167
Id
TokenId
Feature activation+0.000
=
Token=
Feature activation+0.525
11
Token11
Feature activation+1.363
559
Token559
Feature activation+0.532
68
Token68
Feature activation+0.437
404
Token404
Feature activation+0.000
"
Token"
Feature activation+0.000
true
Token true
Feature activation+0.000
k
Tokenk
Feature activation+0.000
d
Tokend
Feature activation+1.104
v
Tokenv
Feature activation+1.359
b
Tokenb
Feature activation+1.228
2
Token2
Feature activation+1.348
ds
Tokends
Feature activation+1.030
Z
TokenZ
Feature activation+1.075
SB
TokenSB
Feature activation+0.000
J
TokenJ
Feature activation+0.652
bm
Tokenbm
Feature activation+0.000
M
TokenM
Feature activation+0.000

INTERVAL 0.000 - 0.902
CONTAINS 99.932%

,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
looked
Token looked
Feature activation+0.000
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
ref
Tokenref
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
,
Token,
Feature activation+0.000
Mud
Token Mud
Feature activation+0.000
ich
Tokenich
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
,
Token,
Feature activation+0.000
Vel
Token Vel
Feature activation+0.000
acher
Tokenacher
Feature activation+0.000
y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.000
Mad
Token Mad
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
"
Token "
Feature activation+0.000
Red
TokenRed
Feature activation+0.000
Right
Token Right
Feature activation+0.000
Hand
Token Hand
Feature activation+0.000
".
Token".
Feature activation+0.000
"
Token "
Feature activation+0.000
Red
TokenRed
Feature activation+0.000
Right
Token Right
Feature activation+0.000
Hand
Token Hand
Feature activation+0.000
"
Token"
Feature activation+0.000
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.000
growth
Token growth
Feature activation+0.000
and
Token and
Feature activation+0.000
bad
Token bad
Feature activation+0.000
for
Token for
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
the
Token the
Feature activation+0.000
title
Token title
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
walked
Token walked
Feature activation+0.000
in
Token in
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
Punk
Token Punk
Feature activation+0.000
kid
Token kid
Feature activation+0.000
and
Token and
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H9.3: (feature 13008)

TOP ACTIVATIONS
MAX = 2.306

of
Token of
Feature activation+0.539
self
Token self
Feature activation+1.545
-
Token-
Feature activation+1.317
inf
Tokeninf
Feature activation+1.116
licted
Tokenlicted
Feature activation+1.786
body
Token body
Feature activation+2.306
blows
Token blows
Feature activation+0.685
like
Token like
Feature activation+0.021
none
Token none
Feature activation+0.000
other
Token other
Feature activation+0.000
seen
Token seen
Feature activation+0.000
days
Token days
Feature activation+0.000
after
Token after
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
two
Token two
Feature activation+0.000
solo
Token solo
Feature activation+0.480
home
Token home
Feature activation+2.053
runs
Token runs
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.055
few
Token few
Feature activation+0.377
turn
Token turn
Feature activation+1.502
-
Token-
Feature activation+1.833
of
Tokenof
Feature activation+0.853
-
Token-
Feature activation+0.815
events
Tokenevents
Feature activation+1.157
that
Token that
Feature activation+0.165
I
Token I
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.539
self
Token self
Feature activation+1.545
-
Token-
Feature activation+1.317
inf
Tokeninf
Feature activation+1.116
licted
Tokenlicted
Feature activation+1.786
body
Token body
Feature activation+2.306
blows
Token blows
Feature activation+0.685
like
Token like
Feature activation+0.021
none
Token none
Feature activation+0.000
other
Token other
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.472
international
Token international
Feature activation+1.784
operations
Token operations
Feature activation+0.321
to
Token to
Feature activation+0.000
date
Token date
Feature activation+0.000
against
Token against
Feature activation+0.000
al
Token al
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.134
recent
Token recent
Feature activation+0.822
NSA
Token NSA
Feature activation+1.709
stories
Token stories
Feature activation+0.171
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
O
TokenO
Feature activation+0.000
and
Token and
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
these
Token these
Feature activation+0.177
m
Token m
Feature activation+1.057
add
Tokenadd
Feature activation+0.420
ening
Tokenening
Feature activation+1.702
attacks
Token attacks
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
latest
Token latest
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.338
foreign
Token foreign
Feature activation+1.695
trips
Token trips
Feature activation+0.317
to
Token to
Feature activation+0.529
cement
Token cement
Feature activation+0.000
relations
Token relations
Feature activation+0.000
with
Token with
Feature activation+0.000
three
Token three
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.000
recent
Token recent
Feature activation+0.400
home
Token home
Feature activation+1.636
inv
Token inv
Feature activation+0.835
asions
Tokenasions
Feature activation+0.000
on
Token on
Feature activation+0.254
the
Token the
Feature activation+0.035
Northwest
Token Northwest
Feature activation+0.000
spurred
Token spurred
Feature activation+0.000
a
Token a
Feature activation+0.000
collective
Token collective
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.513
nervous
Token nervous
Feature activation+1.631
laughter
Token laughter
Feature activation+0.322
from
Token from
Feature activation+0.281
the
Token the
Feature activation+0.000
studio
Token studio
Feature activation+0.000
audience
Token audience
Feature activation+0.000
latest
Token latest
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
string
Token string
Feature activation+0.000
of
Token of
Feature activation+0.579
drug
Token drug
Feature activation+1.627
-
Token-
Feature activation+1.431
related
Tokenrelated
Feature activation+1.559
exploits
Token exploits
Feature activation+0.561
at
Token at
Feature activation+0.337
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.334
Avengers
Token Avengers
Feature activation+0.935
:
Token:
Feature activation+0.217
Infinity
Token Infinity
Feature activation+0.000
War
Token War
Feature activation+1.594
films
Token films
Feature activation+0.202
once
Token once
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Check
Token Check
Feature activation+0.000
ests
Tokenests
Feature activation+0.456
,
Token,
Feature activation+0.420
and
Token and
Feature activation+0.434
other
Token other
Feature activation+0.568
huge
Token huge
Feature activation+1.296
beer
Token beer
Feature activation+1.591
events
Token events
Feature activation+0.017
throughout
Token throughout
Feature activation+0.098
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
that
Token that
Feature activation+0.000
similarly
Token similarly
Feature activation+0.093
budget
Token budget
Feature activation+0.405
-
Token-
Feature activation+0.395
b
Tokenb
Feature activation+0.000
usting
Tokenusting
Feature activation+0.846
tax
Token tax
Feature activation+1.584
cuts
Token cuts
Feature activation+0.000
with
Token with
Feature activation+0.000
big
Token big
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
string
Token string
Feature activation+0.000
of
Token of
Feature activation+0.579
drug
Token drug
Feature activation+1.627
-
Token-
Feature activation+1.431
related
Tokenrelated
Feature activation+1.559
exploits
Token exploits
Feature activation+0.561
at
Token at
Feature activation+0.337
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.000
district
Token district
Feature activation+0.000
House
Token House
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
a
Token a
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.539
self
Token self
Feature activation+1.545
-
Token-
Feature activation+1.317
inf
Tokeninf
Feature activation+1.116
licted
Tokenlicted
Feature activation+1.786
body
Token body
Feature activation+2.306
blows
Token blows
Feature activation+0.685
I
Token I
Feature activation+0.000
use
Token use
Feature activation+0.000
for
Token for
Feature activation+0.000
random
Token random
Feature activation+0.363
Optim
Token Optim
Feature activation+0.663
ist
Tokenist
Feature activation+1.523
comics
Token comics
Feature activation+0.564
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
In
TokenIn
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.055
few
Token few
Feature activation+0.377
turn
Token turn
Feature activation+1.502
-
Token-
Feature activation+1.833
of
Tokenof
Feature activation+0.853
-
Token-
Feature activation+0.815
events
Tokenevents
Feature activation+1.157
that
Token that
Feature activation+0.165
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.177
Metro
Token Metro
Feature activation+0.976
lin
Tokenlin
Feature activation+0.098
x
Tokenx
Feature activation+1.495
projects
Token projects
Feature activation+0.155
per
Token per
Feature activation+0.000
se
Token se
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.068
ry
Tokenry
Feature activation+0.000
schedule
Token schedule
Feature activation+0.000
of
Token of
Feature activation+0.000
Congressional
Token Congressional
Feature activation+0.968
town
Token town
Feature activation+0.752
hall
Token hall
Feature activation+1.488
meetings
Token meetings
Feature activation+0.041
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
another
Token another
Feature activation+0.000

Top DFA by src position
MAX = 2.063

series
Token series
Feature activation+0.093
Top resid features:
of
Token of
Feature activation+0.603
Top resid features:
self
Token self
Feature activation+0.046
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
inf
Tokeninf
Feature activation-0.002
Top resid features:
licted
Tokenlicted
Feature activation+1.863
Top resid features:
body
Token body
Feature activation+0.118
Top resid features:
blows
Token blows
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
none
Token none
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.017
Top resid features:
days
Token days
Feature activation-0.001
Top resid features:
after
Token after
Feature activation-0.001
Top resid features:
allowing
Token allowing
Feature activation-0.040
Top resid features:
two
Token two
Feature activation+0.632
Top resid features:
solo
Token solo
Feature activation+1.790
Top resid features:
home
Token home
Feature activation+0.116
Top resid features:
runs
Token runs
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:
3
Token 3
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
In
TokenIn
Feature activation+0.004
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.054
Top resid features:
the
Token the
Feature activation+0.404
Top resid features:
few
Token few
Feature activation+1.350
Top resid features:
turn
Token turn
Feature activation+0.449
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
of
Tokenof
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
events
Tokenevents
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+0.003
Top resid features:
House
Token House
Feature activation-0.004
Top resid features:
experienced
Token experienced
Feature activation+0.044
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
series
Token series
Feature activation+0.297
Top resid features:
of
Token of
Feature activation+1.490
Top resid features:
self
Token self
Feature activation+0.088
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
inf
Tokeninf
Feature activation-0.000
Top resid features:
licted
Tokenlicted
Feature activation+0.262
Top resid features:
body
Token body
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
part
Token part
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
one
Token one
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
biggest
Token biggest
Feature activation+2.063
Top resid features:
international
Token international
Feature activation+0.070
Top resid features:
operations
Token operations
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
date
Token date
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
ras
Tokenras
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
number
Token number
Feature activation+0.127
Top resid features:
of
Token of
Feature activation+0.314
Top resid features:
recent
Token recent
Feature activation+1.625
Top resid features:
NSA
Token NSA
Feature activation+0.110
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
how
Token how
Feature activation-0.001
Top resid features:
painful
Token painful
Feature activation+0.030
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
frustrating
Token frustrating
Feature activation+0.007
Top resid features:
these
Token these
Feature activation+1.957
Top resid features:
m
Token m
Feature activation-0.008
Top resid features:
add
Tokenadd
Feature activation+0.002
Top resid features:
ening
Tokenening
Feature activation+0.138
Top resid features:
attacks
Token attacks
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
latest
Token latest
Feature activation+0.034
Top resid features:
in
Token in
Feature activation+0.083
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
series
Token series
Feature activation+0.127
Top resid features:
of
Token of
Feature activation+1.924
Top resid features:
foreign
Token foreign
Feature activation+0.025
Top resid features:
trips
Token trips
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
cement
Token cement
Feature activation+0.000
Top resid features:
relations
Token relations
Feature activation+0.000
Top resid features:
believed
Token believed
Feature activation-0.005
Top resid features:
three
Token three
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.101
Top resid features:
four
Token four
Feature activation+0.093
Top resid features:
recent
Token recent
Feature activation+1.851
Top resid features:
home
Token home
Feature activation+0.036
Top resid features:
inv
Token inv
Feature activation+0.000
Top resid features:
asions
Tokenasions
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.021
Top resid features:
spurred
Token spurred
Feature activation+0.022
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
collective
Token collective
Feature activation+0.042
Top resid features:
series
Token series
Feature activation+0.181
Top resid features:
of
Token of
Feature activation+1.706
Top resid features:
nervous
Token nervous
Feature activation+0.059
Top resid features:
laughter
Token laughter
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:
studio
Token studio
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
latest
Token latest
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.113
Top resid features:
a
Token a
Feature activation+0.044
Top resid features:
string
Token string
Feature activation+0.259
Top resid features:
of
Token of
Feature activation+1.579
Top resid features:
drug
Token drug
Feature activation+0.031
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
related
Tokenrelated
Feature activation+0.000
Top resid features:
exploits
Token exploits
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
crossover
Token crossover
Feature activation+0.014
Top resid features:
happening
Token happening
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.062
Top resid features:
two
Token two
Feature activation+0.507
Top resid features:
upcoming
Token upcoming
Feature activation+1.421
Top resid features:
Avengers
Token Avengers
Feature activation+0.135
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
Infinity
Token Infinity
Feature activation+0.002
Top resid features:
War
Token War
Feature activation+0.059
Top resid features:
films
Token films
Feature activation+0.000
Top resid features:
ober
Tokenober
Feature activation+0.030
Top resid features:
f
Tokenf
Feature activation+0.002
Top resid features:
ests
Tokenests
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
and
Token and
Feature activation+0.122
Top resid features:
other
Token other
Feature activation+0.875
Top resid features:
huge
Token huge
Feature activation+0.864
Top resid features:
beer
Token beer
Feature activation+0.018
Top resid features:
events
Token events
Feature activation+0.000
Top resid features:
throughout
Token throughout
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
proposed
Token proposed
Feature activation+0.300
Top resid features:
similarly
Token similarly
Feature activation+0.039
Top resid features:
budget
Token budget
Feature activation+0.050
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
b
Tokenb
Feature activation+0.000
Top resid features:
usting
Tokenusting
Feature activation+1.658
Top resid features:
tax
Token tax
Feature activation+0.005
Top resid features:
cuts
Token cuts
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:
benefits
Token benefits
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
latest
Token latest
Feature activation+0.058
Top resid features:
in
Token in
Feature activation+0.063
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
string
Token string
Feature activation+0.233
Top resid features:
of
Token of
Feature activation+1.193
Top resid features:
drug
Token drug
Feature activation+0.141
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
related
Tokenrelated
Feature activation+0.363
Top resid features:
exploits
Token exploits
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+0.000
Top resid features:
House
Token House
Feature activation-0.016
Top resid features:
experienced
Token experienced
Feature activation+0.090
Top resid features:
a
Token a
Feature activation+0.046
Top resid features:
series
Token series
Feature activation+0.301
Top resid features:
of
Token of
Feature activation+1.520
Top resid features:
self
Token self
Feature activation+0.036
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
inf
Tokeninf
Feature activation+0.000
Top resid features:
licted
Tokenlicted
Feature activation+0.000
Top resid features:
body
Token body
Feature activation+0.000
Top resid features:
newspaper
Token newspaper
Feature activation-0.021
Top resid features:
template
Token template
Feature activation-0.003
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
use
Token use
Feature activation-0.005
Top resid features:
for
Token for
Feature activation+0.153
Top resid features:
random
Token random
Feature activation+1.864
Top resid features:
Optim
Token Optim
Feature activation+0.002
Top resid features:
ist
Tokenist
Feature activation+0.035
Top resid features:
comics
Token comics
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
In
TokenIn
Feature activation+0.003
Top resid features:
one
Token one
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.130
Top resid features:
the
Token the
Feature activation+0.853
Top resid features:
few
Token few
Feature activation+0.895
Top resid features:
turn
Token turn
Feature activation+0.015
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
of
Tokenof
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
events
Tokenevents
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.030
Top resid features:
corridor
Token corridor
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
These
Token These
Feature activation+0.045
Top resid features:
are
Token are
Feature activation+0.188
Top resid features:
not
Token not
Feature activation+1.800
Top resid features:
Metro
Token Metro
Feature activation+0.019
Top resid features:
lin
Tokenlin
Feature activation+0.004
Top resid features:
x
Tokenx
Feature activation+0.020
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
p
Token p
Feature activation+0.000
Top resid features:
alt
Tokenalt
Feature activation+0.001
Top resid features:
ry
Tokenry
Feature activation+0.002
Top resid features:
schedule
Token schedule
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+1.189
Top resid features:
Congressional
Token Congressional
Feature activation+0.495
Top resid features:
town
Token town
Feature activation+0.123
Top resid features:
hall
Token hall
Feature activation+0.126
Top resid features:
meetings
Token meetings
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.04

Head 3: 0.60

Head 4: 0.03

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.03

Head 10: 0.08

Head 11: 0.02

Positive logits

incidents3.65

episodes3.61

trips3.57

surprises3.55

scenarios3.53

announcements3.46

failures3.45

bouts3.44

engagements3.44

reminders3.43

dramas3.41

disasters3.41

izations3.39

stories3.37

outings3.36

attacks3.35

sessions3.33

tragedies3.31

downs3.31

setbacks3.28

Negative logits

regulator-2.57

protector-2.35

wark-2.28

curator-2.17

inventor-2.17

insurer-2.15

conservancy-2.08

brewer-2.07

advocate-2.07

architect-2.07

economist-2.06

fecture-2.06

onductor-2.05

maker-2.05

distributor-2.03

engineer-2.02

uana-2.01

utenant-2.01

aler-2.01

lender-2.01

INTERVAL 2.076 - 2.306
CONTAINS 0.000%

of
Token of
Feature activation+0.539
self
Token self
Feature activation+1.545
-
Token-
Feature activation+1.317
inf
Tokeninf
Feature activation+1.116
licted
Tokenlicted
Feature activation+1.786
body
Token body
Feature activation+2.306
blows
Token blows
Feature activation+0.685
like
Token like
Feature activation+0.021
none
Token none
Feature activation+0.000
other
Token other
Feature activation+0.000
seen
Token seen
Feature activation+0.000

INTERVAL 1.845 - 2.076
CONTAINS 0.000%

days
Token days
Feature activation+0.000
after
Token after
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
two
Token two
Feature activation+0.000
solo
Token solo
Feature activation+0.480
home
Token home
Feature activation+2.053
runs
Token runs
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.614 - 1.845
CONTAINS 0.001%

latest
Token latest
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.338
foreign
Token foreign
Feature activation+1.695
trips
Token trips
Feature activation+0.317
to
Token to
Feature activation+0.529
cement
Token cement
Feature activation+0.000
relations
Token relations
Feature activation+0.000
with
Token with
Feature activation+0.000
three
Token three
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.000
recent
Token recent
Feature activation+0.400
home
Token home
Feature activation+1.636
inv
Token inv
Feature activation+0.835
asions
Tokenasions
Feature activation+0.000
on
Token on
Feature activation+0.254
the
Token the
Feature activation+0.035
Northwest
Token Northwest
Feature activation+0.000
latest
Token latest
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
string
Token string
Feature activation+0.000
of
Token of
Feature activation+0.579
drug
Token drug
Feature activation+1.627
-
Token-
Feature activation+1.431
related
Tokenrelated
Feature activation+1.559
exploits
Token exploits
Feature activation+0.561
at
Token at
Feature activation+0.337
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
these
Token these
Feature activation+0.177
m
Token m
Feature activation+1.057
add
Tokenadd
Feature activation+0.420
ening
Tokenening
Feature activation+1.702
attacks
Token attacks
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
spurred
Token spurred
Feature activation+0.000
a
Token a
Feature activation+0.000
collective
Token collective
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.513
nervous
Token nervous
Feature activation+1.631
laughter
Token laughter
Feature activation+0.322
from
Token from
Feature activation+0.281
the
Token the
Feature activation+0.000
studio
Token studio
Feature activation+0.000
audience
Token audience
Feature activation+0.000

INTERVAL 1.384 - 1.614
CONTAINS 0.004%

âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
intensely
Token intensely
Feature activation+0.000
satisfying
Token satisfying
Feature activation+0.357
âĢĶ
TokenâĢĶ
Feature activation+0.944
under
Tokenunder
Feature activation+1.445
t
Tokent
Feature activation+0.464
akings
Tokenakings
Feature activation+0.646
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
I
Token I
Feature activation+0.000
use
Token use
Feature activation+0.000
for
Token for
Feature activation+0.000
random
Token random
Feature activation+0.363
Optim
Token Optim
Feature activation+0.663
ist
Tokenist
Feature activation+1.523
comics
Token comics
Feature activation+0.564
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
often
Token often
Feature activation+0.211
these
Token these
Feature activation+0.747
awkward
Token awkward
Feature activation+1.431
moments
Token moments
Feature activation+0.479
when
Token when
Feature activation+0.343
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.011
to
Token to
Feature activation+0.186
similarly
Token similarly
Feature activation+0.093
budget
Token budget
Feature activation+0.405
-
Token-
Feature activation+0.395
b
Tokenb
Feature activation+0.000
usting
Tokenusting
Feature activation+0.846
tax
Token tax
Feature activation+1.584
cuts
Token cuts
Feature activation+0.000
with
Token with
Feature activation+0.000
big
Token big
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
string
Token string
Feature activation+0.000
of
Token of
Feature activation+0.579
drug
Token drug
Feature activation+1.627
-
Token-
Feature activation+1.431
related
Tokenrelated
Feature activation+1.559
exploits
Token exploits
Feature activation+0.561
at
Token at
Feature activation+0.337
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.000
district
Token district
Feature activation+0.000

INTERVAL 1.153 - 1.384
CONTAINS 0.008%

still
Token still
Feature activation+0.000
encountered
Token encountered
Feature activation+0.000
relatively
Token relatively
Feature activation+0.079
few
Token few
Feature activation+0.145
âĢ
Token âĢ
Feature activation+0.650
ľ
Tokenľ
Feature activation+1.154
sh
Tokensh
Feature activation+1.022
o
Tokeno
Feature activation+0.724
vel
Tokenvel
Feature activation+0.648
-
Token-
Feature activation+0.380
ready
Tokenready
Feature activation+0.785
âĢĶ
TokenâĢĶ
Feature activation+0.000
there
Tokenthere
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
world
Token world
Feature activation+0.681
-
Token-
Feature activation+1.196
famous
Tokenfamous
Feature activation+0.627
contributors
Token contributors
Feature activation+0.244
(
Token (
Feature activation+0.000
Alexander
TokenAlexander
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
the
Token the
Feature activation+0.000
coolest
Token coolest
Feature activation+0.000
and
Token and
Feature activation+0.619
most
Token most
Feature activation+0.089
immediately
Token immediately
Feature activation+0.000
worthwhile
Token worthwhile
Feature activation+1.211
applications
Token applications
Feature activation+0.053
of
Token of
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
ledger
Token ledger
Feature activation+0.000
and
Token and
Feature activation+0.000
:
Token:
Feature activation+0.000
7
Token 7
Feature activation+0.000
Weird
Token Weird
Feature activation+0.267
Head
Token Head
Feature activation+0.827
ache
Tokenache
Feature activation+0.827
Tr
Token Tr
Feature activation+1.168
ig
Tokenig
Feature activation+0.899
gers
Tokengers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
4
Token4
Feature activation+0.000
ch
Token ch
Feature activation+0.132
ock
Tokenock
Feature activation+0.000
-
Token-
Feature activation+0.006
full
Tokenfull
Feature activation+0.000
of
Token of
Feature activation+0.310
bad
Token bad
Feature activation+1.210
press
Token press
Feature activation+0.133
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
Police
Token Police
Feature activation+0.000

INTERVAL 0.923 - 1.153
CONTAINS 0.024%

during
Token during
Feature activation+0.004
sex
Token sex
Feature activation+0.000
and
Token and
Feature activation+0.164
whispering
Token whispering
Feature activation+0.000
sweet
Token sweet
Feature activation+0.165
not
Token not
Feature activation+0.966
h
Tokenh
Feature activation+0.533
ings
Tokenings
Feature activation+0.000
to
Token to
Feature activation+0.000
BDS
Token BDS
Feature activation+0.000
M
TokenM
Feature activation+0.000
back
Token back
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.685
loan
Token loan
Feature activation+1.005
spells
Token spells
Feature activation+0.103
and
Token and
Feature activation+0.132
have
Token have
Feature activation+0.000
him
Token him
Feature activation+0.000
as
Token as
Feature activation+0.000
-
Token-
Feature activation+0.000
Ky
TokenKy
Feature activation+0.000
.),
Token.),
Feature activation+0.000
the
Token the
Feature activation+0.488
Surveillance
Token Surveillance
Feature activation+0.299
State
Token State
Feature activation+1.061
Repe
Token Repe
Feature activation+0.112
al
Tokenal
Feature activation+0.872
Act
Token Act
Feature activation+0.521
would
Token would
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.539
self
Token self
Feature activation+1.545
-
Token-
Feature activation+1.317
inf
Tokeninf
Feature activation+1.116
licted
Tokenlicted
Feature activation+1.786
body
Token body
Feature activation+2.306
blows
Token blows
Feature activation+0.685
like
Token like
Feature activation+0.021
none
Token none
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
huge
Token huge
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+1.054
-
Token-
Feature activation+0.933
star
Tokenstar
Feature activation+0.925
reviews
Token reviews
Feature activation+0.000
that
Token that
Feature activation+0.000
say
Token say
Feature activation+0.000

INTERVAL 0.692 - 0.923
CONTAINS 0.052%

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
around
Token around
Feature activation+0.000
forty
Token forty
Feature activation+0.000
moderate
Token moderate
Feature activation+0.102
discontin
Token discontin
Feature activation+0.790
u
Tokenu
Feature activation+0.436
ities
Tokenities
Feature activation+0.071
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
ribed
Tokenribed
Feature activation+0.473
sol
Token sol
Feature activation+0.455
os
Tokenos
Feature activation+0.000
of
Token of
Feature activation+0.557
their
Token their
Feature activation+0.640
favorite
Token favorite
Feature activation+0.749
players
Token players
Feature activation+0.139
or
Token or
Feature activation+0.375
The
Token The
Feature activation+0.288
Real
Token Real
Feature activation+0.000
Book
Token Book
Feature activation+0.000
of
Token of
Feature activation+0.234
her
Token her
Feature activation+0.775
sister
Token sister
Feature activation+0.852
's
Token's
Feature activation+0.787
missing
Token missing
Feature activation+0.961
person
Token person
Feature activation+0.821
report
Token report
Feature activation+0.439
:
Token:
Feature activation+0.271
119
Token 119
Feature activation+0.000
1
Token1
Feature activation+0.047
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.000
no
Token no
Feature activation+0.000
k
Token k
Feature activation+0.695
enn
Tokenenn
Feature activation+0.810
el
Tokenel
Feature activation+0.745
staff
Token staff
Feature activation+0.253
present
Token present
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
Token All
Feature activation+0.000
changes
Token changes
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+1.067
most
Token most
Feature activation+0.784
long
Token long
Feature activation+0.923
ed
Tokened
Feature activation+0.707
for
Token for
Feature activation+0.977
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 0.461 - 0.692
CONTAINS 0.129%

record
Token record
Feature activation+0.000
for
Token for
Feature activation+0.000
most
Token most
Feature activation+0.000
consecutive
Token consecutive
Feature activation+0.244
games
Token games
Feature activation+0.123
played
Token played
Feature activation+0.521
with
Token with
Feature activation+0.000
9
Token 9
Feature activation+0.000
64
Token64
Feature activation+0.000
.
Token.
Feature activation+0.000
In
TokenIn
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
so
Token so
Feature activation+0.040
many
Token many
Feature activation+0.048
âĢ
Token âĢ
Feature activation+0.281
ľ
Tokenľ
Feature activation+0.675
ir
Tokenir
Feature activation+0.588
ons
Tokenons
Feature activation+0.609
in
Token in
Feature activation+0.067
the
Token the
Feature activation+0.000
fire
Token fire
Feature activation+0.104
sane
Token sane
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
organize
Token organize
Feature activation+0.000
client
Token client
Feature activation+0.121
-
Token-
Feature activation+0.246
side
Tokenside
Feature activation+0.481
code
Token code
Feature activation+0.140
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Are
TokenAre
Feature activation+0.000
any
Token any
Feature activation+0.272
of
Token of
Feature activation+0.503
these
Token these
Feature activation+0.257
a
Token a
Feature activation+0.312
part
Token part
Feature activation+0.039
of
Token of
Feature activation+0.287
your
Token your
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
trio
Token trio
Feature activation+0.000
of
Token of
Feature activation+0.000
great
Token great
Feature activation+0.398
Starg
Token Starg
Feature activation+0.659
irl
Tokenirl
Feature activation+1.215
-
Token-
Feature activation+0.943
centric
Tokencentric
Feature activation+1.133
stories
Token stories
Feature activation+0.338
,
Token,
Feature activation+0.099

INTERVAL 0.231 - 0.461
CONTAINS 0.338%

you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
toss
Token toss
Feature activation+0.000
in
Token in
Feature activation+0.000
dis
Token dis
Feature activation+0.062
j
Tokenj
Feature activation+0.357
ointed
Tokenointed
Feature activation+0.101
thoughts
Token thoughts
Feature activation+0.000
at
Token at
Feature activation+0.000
random
Token random
Feature activation+0.000
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
were
Token were
Feature activation+0.000
early
Token early
Feature activation+0.284
scares
Token scares
Feature activation+0.130
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.225
the
Token the
Feature activation+0.024
goalkeeper
Token goalkeeper
Feature activation+0.000
-
Token-
Feature activation+0.380
ready
Tokenready
Feature activation+0.785
âĢ
TokenâĢ
Feature activation+0.298
Ŀ
TokenĿ
Feature activation+0.914
giving
Token giving
Feature activation+0.764
opportunities
Token opportunities
Feature activation+0.405
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
encountered
Token encountered
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
after
Token after
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
passes
Token passes
Feature activation+0.000
and
Token and
Feature activation+0.369
re
Token re
Feature activation+0.536
-
Token-
Feature activation+0.460
pass
Tokenpass
Feature activation+0.384
es
Tokenes
Feature activation+0.043
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
includes
Token includes
Feature activation+0.000
some
Token some
Feature activation+0.000
major
Token major
Feature activation+0.000
new
Token new
Feature activation+0.236
features
Token features
Feature activation+0.000
for
Token for
Feature activation+0.000
interface
Token interface
Feature activation+0.000
designers
Token designers
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.000 - 0.231
CONTAINS 99.444%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
life
Token life
Feature activation+0.000
at
Token at
Feature activation+0.000
any
Token any
Feature activation+0.000
cost
Token cost
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
15
Token 15
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
may
Token may
Feature activation+0.000
vote
Token vote
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Green
Token Green
Feature activation+0.000
B
Token B
Feature activation+0.000
eret
Tokeneret
Feature activation+0.000
from
Token from
Feature activation+0.000
A
Token A
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
Park
Token Park
Feature activation+0.000
deserves
Token deserves
Feature activation+0.000
a
Token a
Feature activation+0.000
Medal
Token Medal
Feature activation+0.000
States
Token States
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
thus
Token thus
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
ineligible
Token ineligible
Feature activation+0.000
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
work
Tokenwork
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
law
Token law
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
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 H9.3: (feature 6405)

TOP ACTIVATIONS
MAX = 3.111

more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+1.044
average
Token average
Feature activation+0.224
internet
Token internet
Feature activation+3.111
user
Token user
Feature activation+0.281
to
Token to
Feature activation+0.248
watch
Token watch
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
programs
Token programs
Feature activation+0.000
-
Token-
Feature activation+0.514
plus
Tokenplus
Feature activation+0.617
strong
Token strong
Feature activation+0.642
crowd
Token crowd
Feature activation+0.201
of
Token of
Feature activation+0.412
Toronto
Token Toronto
Feature activation+3.087
fans
Token fans
Feature activation+0.421
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.176
vast
Token vast
Feature activation+0.000
majority
Token majority
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.185
Ċ
TokenĊ
Feature activation+0.079
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
52
Token52
Feature activation+2.844
people
Token people
Feature activation+0.741
outside
Token outside
Feature activation+0.898
of
Token of
Feature activation+0.263
Google
Token Google
Feature activation+0.211
.
Token.
Feature activation+0.000
disappointing
Token disappointing
Feature activation+0.000
to
Token to
Feature activation+0.406
many
Token many
Feature activation+0.870
Linux
Token Linux
Feature activation+1.691
and
Token and
Feature activation+1.299
Mac
Token Mac
Feature activation+2.797
OS
Token OS
Feature activation+1.884
X
Token X
Feature activation+2.844
users
Token users
Feature activation+0.430
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.006
of
Token of
Feature activation+0.785
Likely
Token Likely
Feature activation+0.415
U
Token U
Feature activation+1.619
.
Token.
Feature activation+1.382
S
TokenS
Feature activation+2.276
.
Token.
Feature activation+2.746
Voters
Token Voters
Feature activation+0.345
believe
Token believe
Feature activation+0.049
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
of
Token of
Feature activation+0.000
Prec
Token Prec
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.821
fulfillment
Token fulfillment
Feature activation+2.731
team
Token team
Feature activation+1.059
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
several
Token several
Feature activation+0.000
squirrel
Token squirrel
Feature activation+0.000
the
Token the
Feature activation+0.443
illegal
Token illegal
Feature activation+0.083
sl
Token sl
Feature activation+0.000
ums
Tokenums
Feature activation+0.052
asking
Token asking
Feature activation+0.099
the
Token the
Feature activation+2.713
dwell
Token dwell
Feature activation+0.818
ers
Tokeners
Feature activation+1.203
to
Token to
Feature activation+0.480
vac
Token vac
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.098
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+1.538
cheerful
Token cheerful
Feature activation+2.673
parents
Token parents
Feature activation+1.253
and
Token and
Feature activation+1.131
children
Token children
Feature activation+1.146
who
Token who
Feature activation+0.195
turned
Token turned
Feature activation+0.000
sell
Token sell
Feature activation+1.966
out
Tokenout
Feature activation+0.318
crowd
Token crowd
Feature activation+0.945
of
Token of
Feature activation+0.931
11
Token 11
Feature activation+1.045
,
Token,
Feature activation+2.651
5
Token5
Feature activation+1.415
69
Token69
Feature activation+0.770
fans
Token fans
Feature activation+0.322
at
Token at
Feature activation+0.114
Papa
Token Papa
Feature activation+0.000
,
Token,
Feature activation+1.344
700
Token700
Feature activation+0.914
U
Token U
Feature activation+1.240
.
Token.
Feature activation+1.293
S
TokenS
Feature activation+2.312
.
Token.
Feature activation+2.649
elementary
Token elementary
Feature activation+1.615
schools
Token schools
Feature activation+0.312
featuring
Token featuring
Feature activation+0.000
footage
Token footage
Feature activation+0.000
of
Token of
Feature activation+0.000
comments
Token comments
Feature activation+0.000
caused
Token caused
Feature activation+0.000
a
Token a
Feature activation+0.000
backlash
Token backlash
Feature activation+0.000
among
Token among
Feature activation+0.162
football
Token football
Feature activation+2.564
players
Token players
Feature activation+0.228
and
Token and
Feature activation+0.692
team
Token team
Feature activation+1.066
owners
Token owners
Feature activation+0.116
alike
Token alike
Feature activation+0.000
-
Token-
Feature activation+0.000
average
Tokenaverage
Feature activation+0.000
popularity
Token popularity
Feature activation+0.000
among
Token among
Feature activation+0.000
cord
Token cord
Feature activation+0.495
-
Token-
Feature activation+2.549
cut
Tokencut
Feature activation+1.316
ters
Tokenters
Feature activation+0.000
are
Token are
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
programs
Token programs
Feature activation+0.000
to
Token to
Feature activation+0.024
satisfy
Token satisfy
Feature activation+0.283
not
Token not
Feature activation+0.160
only
Token only
Feature activation+1.284
the
Token the
Feature activation+2.149
story
Token story
Feature activation+2.545
buffs
Token buffs
Feature activation+0.898
,
Token,
Feature activation+0.274
but
Token but
Feature activation+0.795
also
Token also
Feature activation+1.127
the
Token the
Feature activation+1.880
unres
Token unres
Feature activation+0.000
erved
Tokenerved
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
apologise
Token apologise
Feature activation+0.000
to
Token to
Feature activation+0.214
Nin
Token Nin
Feature activation+2.541
ems
Tokenems
Feature activation+2.256
n
Tokenn
Feature activation+1.447
's
Token's
Feature activation+1.825
staff
Token staff
Feature activation+0.749
for
Token for
Feature activation+0.153
rest
Token rest
Feature activation+0.057
of
Token of
Feature activation+1.521
the
Token the
Feature activation+2.047
i
Token i
Feature activation+1.174
Ac
TokenAc
Feature activation+0.385
quire
Tokenquire
Feature activation+2.516
team
Token team
Feature activation+0.000
as
Token as
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
-
Token-
Feature activation+2.263
modern
Tokenmodern
Feature activation+2.359
/
Token/
Feature activation+1.418
super
Tokensuper
Feature activation+0.343
-
Token-
Feature activation+0.526
bike
Tokenbike
Feature activation+2.426
crowd
Token crowd
Feature activation+0.090
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.089
as
Token as
Feature activation+0.623
the
Token the
Feature activation+1.718
state
Token state
Feature activation+1.995
âĢ
TokenâĢ
Feature activation+0.364
Ļ
TokenĻ
Feature activation+1.221
s
Tokens
Feature activation+2.144
blue
Token blue
Feature activation+0.888
-
Token-
Feature activation+2.368
collar
Tokencollar
Feature activation+2.197
workers
Token workers
Feature activation+1.226
in
Token in
Feature activation+0.399
places
Token places
Feature activation+0.000
such
Token such
Feature activation+0.046
with
Token with
Feature activation+0.000
both
Token both
Feature activation+0.901
the
Token the
Feature activation+1.592
ultra
Token ultra
Feature activation+2.180
-
Token-
Feature activation+2.263
modern
Tokenmodern
Feature activation+2.359
/
Token/
Feature activation+1.418
super
Tokensuper
Feature activation+0.343
-
Token-
Feature activation+0.526
bike
Tokenbike
Feature activation+2.426
crowd
Token crowd
Feature activation+0.090
the
Token the
Feature activation+0.000
safety
Token safety
Feature activation+0.000
and
Token and
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
of
Token of
Feature activation+0.002
construction
Token construction
Feature activation+2.334
workers
Token workers
Feature activation+0.582
on
Token on
Feature activation+0.000
Qatar
Token Qatar
Feature activation+0.000
's
Token's
Feature activation+0.000
world
Token world
Feature activation+0.000
the
Token the
Feature activation+0.000
lives
Token lives
Feature activation+0.000
of
Token of
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+1.087
its
Token its
Feature activation+2.327
poorest
Token poorest
Feature activation+1.220
citizens
Token citizens
Feature activation+0.009
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
than
Token than
Feature activation+0.000

Top DFA by src position
MAX = 3.615

are
Token are
Feature activation+0.004
Top resid features:
more
Token more
Feature activation-0.003
Top resid features:
likely
Token likely
Feature activation+0.002
Top resid features:
than
Token than
Feature activation+0.342
Top resid features:
the
Token the
Feature activation+0.266
Top resid features:
average
Token average
Feature activation+2.970
Top resid features:
internet
Token internet
Feature activation+0.103
Top resid features:
user
Token user
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
watch
Token watch
Feature activation+0.000
Top resid features:
ABC
Token ABC
Feature activation+0.000
Top resid features:
400
Token400
Feature activation+0.006
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
plus
Tokenplus
Feature activation+0.004
Top resid features:
strong
Token strong
Feature activation+0.022
Top resid features:
crowd
Token crowd
Feature activation-0.025
Top resid features:
of
Token of
Feature activation+3.615
Top resid features:
Toronto
Token Toronto
Feature activation+0.017
Top resid features:
fans
Token fans
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:
vast
Token vast
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
ve
Tokenve
Feature activation-0.007
Top resid features:
started
Token started
Feature activation-0.030
Top resid features:
selling
Token selling
Feature activation-0.004
Top resid features:
devices
Token devices
Feature activation-0.007
Top resid features:
to
Token to
Feature activation+3.459
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
1
Token1
Feature activation+0.001
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
52
Token52
Feature activation+0.019
Top resid features:
might
Token might
Feature activation+0.003
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
disappointing
Token disappointing
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.247
Top resid features:
many
Token many
Feature activation+0.655
Top resid features:
Linux
Token Linux
Feature activation+2.295
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
Mac
Token Mac
Feature activation+0.090
Top resid features:
OS
Token OS
Feature activation+0.000
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
users
Token users
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.026
Top resid features:
just
Token just
Feature activation+0.003
Top resid features:
29
Token 29
Feature activation+0.006
Top resid features:
%
Token%
Feature activation-0.034
Top resid features:
of
Token of
Feature activation+0.158
Top resid features:
Likely
Token Likely
Feature activation+2.821
Top resid features:
U
Token U
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
S
TokenS
Feature activation+0.275
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
Voters
Token Voters
Feature activation+0.000
Top resid features:
experience
Token experience
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Prec
Token Prec
Feature activation-0.002
Top resid features:
ise
Tokenise
Feature activation-0.000
Top resid features:
with
Token with
Feature activation+1.352
Top resid features:
the
Token the
Feature activation+1.890
Top resid features:
fulfillment
Token fulfillment
Feature activation+0.034
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
due
Token due
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
several
Token several
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
illegal
Token illegal
Feature activation-0.004
Top resid features:
sl
Token sl
Feature activation-0.007
Top resid features:
ums
Tokenums
Feature activation-0.000
Top resid features:
asking
Token asking
Feature activation+3.170
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
dwell
Token dwell
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
vac
Token vac
Feature activation+0.000
Top resid features:
ceremony
Token ceremony
Feature activation+0.006
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
front
Token front
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.398
Top resid features:
hundreds
Token hundreds
Feature activation+0.608
Top resid features:
of
Token of
Feature activation+1.930
Top resid features:
cheerful
Token cheerful
Feature activation+0.231
Top resid features:
parents
Token parents
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
sell
Token sell
Feature activation+0.091
Top resid features:
out
Tokenout
Feature activation+0.089
Top resid features:
crowd
Token crowd
Feature activation+0.081
Top resid features:
of
Token of
Feature activation+0.737
Top resid features:
11
Token 11
Feature activation+2.141
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
69
Token69
Feature activation+0.000
Top resid features:
fans
Token fans
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
apes
Tokenapes
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.793
Top resid features:
over
Token over
Feature activation+0.028
Top resid features:
3
Token 3
Feature activation+0.090
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
700
Token700
Feature activation+2.152
Top resid features:
U
Token U
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
S
TokenS
Feature activation+0.119
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
elementary
Token elementary
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.004
Top resid features:
comments
Token comments
Feature activation+0.002
Top resid features:
caused
Token caused
Feature activation+0.030
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
backlash
Token backlash
Feature activation+0.010
Top resid features:
among
Token among
Feature activation+3.011
Top resid features:
football
Token football
Feature activation+0.032
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
than
Tokenthan
Feature activation+0.015
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
average
Tokenaverage
Feature activation+0.004
Top resid features:
popularity
Token popularity
Feature activation+0.005
Top resid features:
among
Token among
Feature activation+1.711
Top resid features:
cord
Token cord
Feature activation+1.413
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
cut
Tokencut
Feature activation+0.000
Top resid features:
ters
Tokenters
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
experience
Token experience
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
satisfy
Token satisfy
Feature activation+0.163
Top resid features:
not
Token not
Feature activation+0.071
Top resid features:
only
Token only
Feature activation+1.660
Top resid features:
the
Token the
Feature activation+1.124
Top resid features:
story
Token story
Feature activation+0.005
Top resid features:
buffs
Token buffs
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:
we
Token we
Feature activation-0.003
Top resid features:
unres
Token unres
Feature activation+0.004
Top resid features:
erved
Tokenerved
Feature activation+0.009
Top resid features:
ly
Tokenly
Feature activation-0.001
Top resid features:
apologise
Token apologise
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+2.744
Top resid features:
Nin
Token Nin
Feature activation+0.040
Top resid features:
ems
Tokenems
Feature activation+0.000
Top resid features:
n
Tokenn
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
experience
Token experience
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.294
Top resid features:
rest
Token rest
Feature activation+0.383
Top resid features:
of
Token of
Feature activation+0.528
Top resid features:
the
Token the
Feature activation+1.778
Top resid features:
i
Token i
Feature activation+0.020
Top resid features:
Ac
TokenAc
Feature activation+0.017
Top resid features:
quire
Tokenquire
Feature activation+0.022
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
being
Token being
Feature activation-0.001
Top resid features:
popular
Token popular
Feature activation+0.005
Top resid features:
with
Token with
Feature activation+0.899
Top resid features:
both
Token both
Feature activation+0.333
Top resid features:
the
Token the
Feature activation+1.148
Top resid features:
ultra
Token ultra
Feature activation+0.098
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
modern
Tokenmodern
Feature activation+0.446
Top resid features:
/
Token/
Feature activation+0.012
Top resid features:
super
Tokensuper
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.399
Top resid features:
state
Token state
Feature activation+0.120
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.852
Top resid features:
blue
Token blue
Feature activation+1.202
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
collar
Tokencollar
Feature activation+0.000
Top resid features:
workers
Token workers
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
places
Token places
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
popular
Token popular
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.598
Top resid features:
both
Token both
Feature activation+0.340
Top resid features:
the
Token the
Feature activation+1.737
Top resid features:
ultra
Token ultra
Feature activation+0.064
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
modern
Tokenmodern
Feature activation+0.077
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
super
Tokensuper
Feature activation+0.000
Top resid features:
over
Token over
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
safety
Token safety
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
welfare
Token welfare
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+2.891
Top resid features:
construction
Token construction
Feature activation+0.038
Top resid features:
workers
Token workers
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Qatar
Token Qatar
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
failed
Token failed
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
improve
Token improve
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.945
Top resid features:
millions
Token millions
Feature activation+0.942
Top resid features:
of
Token of
Feature activation+0.877
Top resid features:
its
Token its
Feature activation+0.079
Top resid features:
poorest
Token poorest
Feature activation+0.000
Top resid features:
citizens
Token citizens
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.05

Head 3: 0.58

Head 4: 0.02

Head 5: 0.08

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.02

Head 10: 0.09

Head 11: 0.02

Positive logits

listeners4.23

readers3.88

enthusiasts3.77

viewers3.77

drinkers3.73

populace3.69

attendees3.66

audiences3.65

shoppers3.58

audience3.56

commuters3.56

goers3.55

arers3.55

residents3.53

consumers3.52

citizens3.52

learners3.52

subscribers3.51

spectators3.50

fans3.47

Negative logits

THING-1.98

aration-1.93

Potion-1.90

ゴン-1.86

chemy-1.86

inventoryQuantity-1.82

sorcery-1.81

Artifact-1.75

Blessing-1.74

Relic-1.72

omial-1.71

Hai-1.70

tesy-1.70

iHUD-1.70

illac-1.69

Deadly-1.67

interference-1.64

arrangement-1.63

Operation-1.62

potion-1.60

INTERVAL 2.800 - 3.111
CONTAINS 0.000%

-
Token-
Feature activation+0.514
plus
Tokenplus
Feature activation+0.617
strong
Token strong
Feature activation+0.642
crowd
Token crowd
Feature activation+0.201
of
Token of
Feature activation+0.412
Toronto
Token Toronto
Feature activation+3.087
fans
Token fans
Feature activation+0.421
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.176
vast
Token vast
Feature activation+0.000
majority
Token majority
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.185
Ċ
TokenĊ
Feature activation+0.079
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
52
Token52
Feature activation+2.844
people
Token people
Feature activation+0.741
outside
Token outside
Feature activation+0.898
of
Token of
Feature activation+0.263
Google
Token Google
Feature activation+0.211
.
Token.
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+1.044
average
Token average
Feature activation+0.224
internet
Token internet
Feature activation+3.111
user
Token user
Feature activation+0.281
to
Token to
Feature activation+0.248
watch
Token watch
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
programs
Token programs
Feature activation+0.000

INTERVAL 2.489 - 2.800
CONTAINS 0.001%

sell
Token sell
Feature activation+1.966
out
Tokenout
Feature activation+0.318
crowd
Token crowd
Feature activation+0.945
of
Token of
Feature activation+0.931
11
Token 11
Feature activation+1.045
,
Token,
Feature activation+2.651
5
Token5
Feature activation+1.415
69
Token69
Feature activation+0.770
fans
Token fans
Feature activation+0.322
at
Token at
Feature activation+0.114
Papa
Token Papa
Feature activation+0.000
disappointing
Token disappointing
Feature activation+0.000
to
Token to
Feature activation+0.406
many
Token many
Feature activation+0.870
Linux
Token Linux
Feature activation+1.691
and
Token and
Feature activation+1.299
Mac
Token Mac
Feature activation+2.797
OS
Token OS
Feature activation+1.884
X
Token X
Feature activation+2.844
users
Token users
Feature activation+0.430
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.006
comments
Token comments
Feature activation+0.000
caused
Token caused
Feature activation+0.000
a
Token a
Feature activation+0.000
backlash
Token backlash
Feature activation+0.000
among
Token among
Feature activation+0.162
football
Token football
Feature activation+2.564
players
Token players
Feature activation+0.228
and
Token and
Feature activation+0.692
team
Token team
Feature activation+1.066
owners
Token owners
Feature activation+0.116
alike
Token alike
Feature activation+0.000
unres
Token unres
Feature activation+0.000
erved
Tokenerved
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
apologise
Token apologise
Feature activation+0.000
to
Token to
Feature activation+0.214
Nin
Token Nin
Feature activation+2.541
ems
Tokenems
Feature activation+2.256
n
Tokenn
Feature activation+1.447
's
Token's
Feature activation+1.825
staff
Token staff
Feature activation+0.749
for
Token for
Feature activation+0.153
the
Token the
Feature activation+0.443
illegal
Token illegal
Feature activation+0.083
sl
Token sl
Feature activation+0.000
ums
Tokenums
Feature activation+0.052
asking
Token asking
Feature activation+0.099
the
Token the
Feature activation+2.713
dwell
Token dwell
Feature activation+0.818
ers
Tokeners
Feature activation+1.203
to
Token to
Feature activation+0.480
vac
Token vac
Feature activation+0.000
ate
Tokenate
Feature activation+0.000

INTERVAL 2.178 - 2.489
CONTAINS 0.003%

state
Token state
Feature activation+1.995
âĢ
TokenâĢ
Feature activation+0.364
Ļ
TokenĻ
Feature activation+1.221
s
Tokens
Feature activation+2.144
blue
Token blue
Feature activation+0.888
-
Token-
Feature activation+2.368
collar
Tokencollar
Feature activation+2.197
workers
Token workers
Feature activation+1.226
in
Token in
Feature activation+0.399
places
Token places
Feature activation+0.000
such
Token such
Feature activation+0.046
well
Token well
Feature activation+0.089
as
Token as
Feature activation+0.623
the
Token the
Feature activation+1.718
hand
Token hand
Feature activation+1.273
-
Token-
Feature activation+2.321
built
Tokenbuilt
Feature activation+2.230
/
Token/
Feature activation+1.010
ret
Tokenret
Feature activation+0.000
ro
Tokenro
Feature activation+2.007
/
Token/
Feature activation+0.260
air
Tokenair
Feature activation+0.365
popular
Token popular
Feature activation+0.000
with
Token with
Feature activation+0.000
both
Token both
Feature activation+0.901
the
Token the
Feature activation+1.592
ultra
Token ultra
Feature activation+2.180
-
Token-
Feature activation+2.263
modern
Tokenmodern
Feature activation+2.359
/
Token/
Feature activation+1.418
super
Tokensuper
Feature activation+0.343
-
Token-
Feature activation+0.526
bike
Tokenbike
Feature activation+2.426
,
Token,
Feature activation+1.117
000
Token000
Feature activation+0.278
U
Token U
Feature activation+1.179
.
Token.
Feature activation+0.902
S
TokenS
Feature activation+1.529
.
Token.
Feature activation+2.306
residents
Token residents
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
-
Token-
Feature activation+2.263
modern
Tokenmodern
Feature activation+2.359
/
Token/
Feature activation+1.418
super
Tokensuper
Feature activation+0.343
-
Token-
Feature activation+0.526
bike
Tokenbike
Feature activation+2.426
crowd
Token crowd
Feature activation+0.090
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.089
as
Token as
Feature activation+0.623
the
Token the
Feature activation+1.718

INTERVAL 1.867 - 2.178
CONTAINS 0.007%

with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.317
mass
Token mass
Feature activation+0.529
of
Token of
Feature activation+0.682
the
Token the
Feature activation+1.288
Chinese
Token Chinese
Feature activation+1.931
working
Token working
Feature activation+1.595
class
Token class
Feature activation+0.704
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
PS
Token PS
Feature activation+0.000
which
Token which
Feature activation+0.000
they
Token they
Feature activation+0.000
asked
Token asked
Feature activation+0.000
likely
Token likely
Feature activation+0.902
Ohio
Token Ohio
Feature activation+2.277
primary
Token primary
Feature activation+2.170
voters
Token voters
Feature activation+0.904
different
Token different
Feature activation+0.000
combinations
Token combinations
Feature activation+0.000
of
Token of
Feature activation+0.117
Republican
Token Republican
Feature activation+0.000
of
Tokenof
Feature activation+0.807
-
Token-
Feature activation+0.749
mill
Tokenmill
Feature activation+0.972
ions
Tokenions
Feature activation+0.000
of
Token of
Feature activation+1.885
American
Token American
Feature activation+2.049
citizens
Token citizens
Feature activation+0.184
,
Token,
Feature activation+0.185
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.000
reassure
Token reassure
Feature activation+0.000
a
Token a
Feature activation+2.059
growing
Token growing
Feature activation+1.129
number
Token number
Feature activation+0.000
of
Token of
Feature activation+1.946
influential
Token influential
Feature activation+2.178
figures
Token figures
Feature activation+0.817
in
Token in
Feature activation+1.134
the
Token the
Feature activation+0.651
US
Token US
Feature activation+0.581
military
Token military
Feature activation+0.504
poll
Token poll
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
run
Token run
Feature activation+0.000
among
Token among
Feature activation+0.012
Hornets
Token Hornets
Feature activation+1.871
fans
Token fans
Feature activation+0.493
before
Token before
Feature activation+0.052
the
Token the
Feature activation+0.000
draft
Token draft
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 1.555 - 1.867
CONTAINS 0.016%

President
Token President
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
stunned
Token stunned
Feature activation+0.179
the
Token the
Feature activation+2.214
political
Token political
Feature activation+1.604
world
Token world
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
imp
Token imp
Feature activation+0.000
sober
Token sober
Feature activation+0.044
ly
Tokenly
Feature activation+0.076
,
Token,
Feature activation+0.406
to
Token to
Feature activation+0.310
their
Token their
Feature activation+1.377
public
Token public
Feature activation+1.797
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
station
Token station
Feature activation+0.199
Wa
Token Wa
Feature activation+0.000
q
Tokenq
Feature activation+0.000
f
Tokenf
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.684
masses
Token masses
Feature activation+0.000
to
Token to
Feature activation+0.000
arrive
Token arrive
Feature activation+0.000
at
Token at
Feature activation+0.000
16
Token 16
Feature activation+0.000
4
Token 4
Feature activation+1.324
,
Token,
Feature activation+0.586
387
Token387
Feature activation+1.039
low
Token low
Feature activation+1.127
-
Token-
Feature activation+1.394
wage
Tokenwage
Feature activation+1.796
workers
Token workers
Feature activation+0.845
in
Token in
Feature activation+0.033
Chicago
Token Chicago
Feature activation+0.150
,
Token,
Feature activation+0.000
Los
Token Los
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.061
working
Token working
Feature activation+0.207
-
Token-
Feature activation+1.569
class
Tokenclass
Feature activation+0.075
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.251
poor
Token poor
Feature activation+0.121
.
Token.
Feature activation+0.000

INTERVAL 1.244 - 1.555
CONTAINS 0.033%

teaching
Token teaching
Feature activation+0.000
that
Token that
Feature activation+0.000
lesson
Token lesson
Feature activation+0.000
to
Token to
Feature activation+0.000
New
Token New
Feature activation+0.265
York
Token York
Feature activation+1.492
City
Token City
Feature activation+1.630
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
but
Token but
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
Feature activation+0.000
telling
Token telling
Feature activation+0.000
his
Token his
Feature activation+0.827
people
Token people
Feature activation+1.321
that
Token that
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
only
Token only
Feature activation+0.000
goal
Token goal
Feature activation+0.000
Star
TokenStar
Feature activation+0.000
bucks
Tokenbucks
Feature activation+0.000
apolog
Token apolog
Feature activation+0.000
izes
Tokenizes
Feature activation+0.000
to
Token to
Feature activation+0.408
Louisiana
Token Louisiana
Feature activation+1.455
woman
Token woman
Feature activation+0.900
for
Token for
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
Satanic
Token Satanic
Feature activation+0.000
symbols
Token symbols
Feature activation+0.000
community
Token community
Feature activation+0.000
college
Token college
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.190
hard
Token hard
Feature activation+1.182
working
Tokenworking
Feature activation+1.336
American
Token American
Feature activation+0.889
student
Token student
Feature activation+0.630
,
Token,
Feature activation+0.141
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
10
Token 10
Feature activation+0.391
,
Token,
Feature activation+1.117
000
Token000
Feature activation+0.278
U
Token U
Feature activation+1.179
.
Token.
Feature activation+0.902
S
TokenS
Feature activation+1.529
.
Token.
Feature activation+2.306
residents
Token residents
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.933 - 1.244
CONTAINS 0.075%

"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
scares
Token scares
Feature activation+0.000
a
Token a
Feature activation+0.141
lot
Token lot
Feature activation+0.164
of
Token of
Feature activation+1.093
customers
Token customers
Feature activation+0.468
,"
Token,"
Feature activation+0.022
Pop
Token Pop
Feature activation+0.000
al
Tokenal
Feature activation+0.000
said
Token said
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
population
Token population
Feature activation+0.000
under
Token under
Feature activation+0.000
100
Token 100
Feature activation+0.006
,
Token,
Feature activation+1.083
000
Token000
Feature activation+0.000
rose
Token rose
Feature activation+0.000
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
has
Token has
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
exh
Token exh
Feature activation+0.000
orted
Tokenorted
Feature activation+0.000
its
Token its
Feature activation+1.118
modules
Token modules
Feature activation+0.255
in
Token in
Feature activation+0.000
Kerala
Token Kerala
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
"
Token"
Feature activation+0.000
Trans
TokenTrans
Feature activation+0.000
it
Tokenit
Feature activation+0.000
greatly
Token greatly
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
our
Token our
Feature activation+0.982
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.000
helping
Token helping
Feature activation+0.000
us
Token us
Feature activation+0.093
avoid
Token avoid
Feature activation+0.000
and
Token and
Feature activation+0.000
fun
Token fun
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
for
Token for
Feature activation+0.226
humans
Token humans
Feature activation+0.972
.
Token.
Feature activation+0.000
Since
Token Since
Feature activation+0.000
2004
Token 2004
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.622 - 0.933
CONTAINS 0.176%

achievements
Token achievements
Feature activation+0.000
was
Token was
Feature activation+0.000
signing
Token signing
Feature activation+0.000
up
Token up
Feature activation+0.000
some
Token some
Feature activation+0.926
big
Token big
Feature activation+0.876
clients
Token clients
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Af
Token Af
Feature activation+0.000
d
Tokend
Feature activation+0.000
Ya
Token Ya
Feature activation+0.000
ÅŁ
TokenÅŁ
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
was
Token was
Feature activation+0.000
urging
Token urging
Feature activation+0.101
his
Token his
Feature activation+0.770
contact
Token contact
Feature activation+0.337
to
Token to
Feature activation+0.033
locate
Token locate
Feature activation+0.000
these
Token these
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
fore
Token fore
Feature activation+0.564
lock
Tokenlock
Feature activation+0.501
-
Token-
Feature activation+0.416
t
Tokent
Feature activation+0.000
ug
Tokenug
Feature activation+0.289
ging
Tokenging
Feature activation+0.731
citizen
Token citizen
Feature activation+0.405
ry
Tokenry
Feature activation+0.251
.
Token.
Feature activation+0.000
Last
Token Last
Feature activation+0.000
I
Token I
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
and
Token and
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
geared
Token geared
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.649
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+1.054
taxpayers
Token taxpayers
Feature activation+0.458
.
Token.
Feature activation+0.000
Central
Token Central
Feature activation+0.000
was
Token was
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Gra
Token Gra
Feature activation+0.000
etz
Tokenetz
Feature activation+0.820
legacy
Token legacy
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
launched
Token launched
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.311 - 0.622
CONTAINS 0.489%

roof
Token roof
Feature activation+0.000
over
Token over
Feature activation+0.000
one
Token one
Feature activation+0.179
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.312
s
Tokens
Feature activation+0.338
head
Token head
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Token the
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
sound
Token sound
Feature activation+0.510
good
Token good
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Make
TokenMake
Feature activation+0.000
trauma
Token trauma
Feature activation+0.000
inflicted
Token inflicted
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.720
Sh
Token Sh
Feature activation+0.464
att
Tokenatt
Feature activation+0.603
uck
Tokenuck
Feature activation+0.859
children
Token children
Feature activation+0.008
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
raid
Token raid
Feature activation+0.000
the
Token the
Feature activation+0.000
middle
Token middle
Feature activation+0.000
of
Token of
Feature activation+0.123
any
Token any
Feature activation+0.000
sane
Token sane
Feature activation+0.172
political
Token political
Feature activation+0.321
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
only
Token only
Feature activation+0.000
seems
Token seems
Feature activation+0.000
copies
Token copies
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.000
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.415
friends
Token friends
Feature activation+0.000
and
Token and
Feature activation+0.446
family
Token family
Feature activation+0.109
members
Token members
Feature activation+0.002
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.311
CONTAINS 99.200%

,
Token,
Feature activation+0.000
Anarch
Token Anarch
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
-
Token-
Feature activation+0.000
Commun
TokenCommun
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
strain
Token strain
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
core
Token core
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
identity
Token identity
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
heart
Token heart
Feature activation+0.000
of
Token of
Feature activation+0.000
hearts
Token hearts
Feature activation+0.000
,
Token,
Feature activation+0.000
captured
Token captured
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
militar
Token militar
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
police
Token police
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
has
Token has
Feature activation+0.000
sparked
Token sparked
Feature activation+0.000
huge
Token huge
Feature activation+0.000
protests
Token protests
Feature activation+0.000
are
Token are
Feature activation+0.000
Kell
Token Kell
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
went
Token went
Feature activation+0.000
0
Token 0
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
while
Token while
Feature activation+0.000
us
Token us
Feature activation+0.000
the
Token the
Feature activation+0.000
ban
Token ban
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
effect
Token effect
Feature activation+0.000
on
Token on
Feature activation+0.000
gun
Token gun
Feature activation+0.000
crime
Token crime
Feature activation+0.000
,
Token,
Feature activation+0.000
politicians
Token politicians
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 H9.3: (feature 16520)

TOP ACTIVATIONS
MAX = 2.417

st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token-
Feature activation+1.049
and
Tokenand
Feature activation+0.217
-
Token-
Feature activation+0.002
p
Tokenp
Feature activation+0.000
roud
Tokenroud
Feature activation+1.348
music
Token music
Feature activation+2.260
g
Token g
Feature activation+1.709
eeks
Tokeneeks
Feature activation+0.608
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000
place
Token place
Feature activation+0.000
20
Token 20
Feature activation+0.372
part
Token part
Feature activation+0.623
-
Token-
Feature activation+1.341
time
Tokentime
Feature activation+0.622
recovery
Token recovery
Feature activation+2.240
coaches
Token coaches
Feature activation+0.645
and
Token and
Feature activation+0.376
five
Token five
Feature activation+0.221
full
Token full
Feature activation+0.639
-
Token-
Feature activation+0.806
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.175
passionate
Token passionate
Feature activation+1.077
garden
Token garden
Feature activation+2.199
ers
Tokeners
Feature activation+0.352
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
FREE
Token FREE
Feature activation+0.000
cheating
Token cheating
Feature activation+0.000
on
Token on
Feature activation+0.000
Johnny
Token Johnny
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.300
bisexual
Token bisexual
Feature activation+2.101
celebrities
Token celebrities
Feature activation+0.251
âĢĶ
Token âĢĶ
Feature activation+0.000
like
Token like
Feature activation+0.000
Car
Token Car
Feature activation+0.000
a
Tokena
Feature activation+0.000
recruit
Token recruit
Feature activation+0.000
and
Token and
Feature activation+0.000
retain
Token retain
Feature activation+0.000
the
Token the
Feature activation+0.814
high
Token high
Feature activation+1.807
-
Token-
Feature activation+2.101
caliber
Tokencaliber
Feature activation+0.765
employees
Token employees
Feature activation+0.000
it
Token it
Feature activation+0.183
needs
Token needs
Feature activation+0.000
if
Token if
Feature activation+0.000
that
Token that
Feature activation+0.000
growing
Token growing
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.107
London
Token London
Feature activation+1.773
Knights
Token Knights
Feature activation+2.086
alumni
Token alumni
Feature activation+0.366
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hunter
TokenHunter
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.522
best
Token best
Feature activation+0.456
under
Token under
Feature activation+0.698
-
Token-
Feature activation+1.268
21
Token21
Feature activation+2.065
star
Token star
Feature activation+0.498
lets
Tokenlets
Feature activation+0.436
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
by
Tokenby
Feature activation+0.000
inspiring
Token inspiring
Feature activation+0.000
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+0.116
future
Token future
Feature activation+0.889
video
Token video
Feature activation+2.016
artists
Token artists
Feature activation+0.000
.
Token.
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
has
Token has
Feature activation+0.000
career
Token career
Feature activation+0.000
histories
Token histories
Feature activation+0.000
of
Token of
Feature activation+0.357
senior
Token senior
Feature activation+1.339
executive
Token executive
Feature activation+1.464
branch
Token branch
Feature activation+2.008
staff
Token staff
Feature activation+1.158
who
Token who
Feature activation+0.491
enter
Token enter
Feature activation+0.091
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
staffed
Token staffed
Feature activation+0.000
by
Token by
Feature activation+0.655
grown
Token grown
Feature activation+0.639
-
Token-
Feature activation+1.363
ass
Tokenass
Feature activation+2.005
humans
Token humans
Feature activation+0.601
who
Token who
Feature activation+0.352
file
Token file
Feature activation+0.103
lawsuits
Token lawsuits
Feature activation+0.000
against
Token against
Feature activation+0.120
two
Token two
Feature activation+0.733
returning
Token returning
Feature activation+1.027
1
Token 1
Feature activation+0.986
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
undeniable
Token undeniable
Feature activation+0.000
factor
Token factor
Feature activation+0.000
motivating
Token motivating
Feature activation+0.000
many
Token many
Feature activation+0.000
seasoned
Token seasoned
Feature activation+0.392
rock
Token rock
Feature activation+1.956
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
plenty
Token plenty
Feature activation+0.000
of
Token of
Feature activation+0.000
1
Token 1
Feature activation+0.986
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.236
's
Token's
Feature activation+0.255
assistant
Token assistant
Feature activation+1.402
dance
Token dance
Feature activation+1.916
captains
Token captains
Feature activation+0.532
,
Token,
Feature activation+0.000
works
Token works
Feature activation+0.000
out
Token out
Feature activation+0.000
at
Token at
Feature activation+0.000
returning
Token returning
Feature activation+1.027
1
Token 1
Feature activation+0.986
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.272
most
Token most
Feature activation+0.236
senior
Token senior
Feature activation+0.960
and
Token and
Feature activation+1.017
respected
Token respected
Feature activation+1.903
officers
Token officers
Feature activation+0.640
in
Token in
Feature activation+0.584
the
Token the
Feature activation+0.000
Agency
Token Agency
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+1.096
successful
Token successful
Feature activation+1.620
-
Token -
Feature activation+0.482
and
Token and
Feature activation+1.620
infamous
Token infamous
Feature activation+0.925
-
Token -
Feature activation+1.901
lobbyists
Token lobbyists
Feature activation+0.632
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
lobbyist
Token lobbyist
Feature activation+0.031
Rick
Token Rick
Feature activation+0.000
-
Token -
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
top
Token top
Feature activation+0.651
junior
Token junior
Feature activation+1.899
prospects
Token prospects
Feature activation+0.738
in
Token in
Feature activation+0.292
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
appointed
Token appointed
Feature activation+0.564
tribal
Token tribal
Feature activation+1.891
leaders
Token leaders
Feature activation+0.000
compliant
Token compliant
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
manip
Token manip
Feature activation+0.000

Top DFA by src position
MAX = 2.442

Johnny
Token Johnny
Feature activation+0.000
Top resid features:
Bans
Token Bans
Feature activation-0.002
Top resid features:
field
Tokenfield
Feature activation+0.011
Top resid features:
as
Token as
Feature activation+0.121
Top resid features:
two
Token two
Feature activation+0.098
Top resid features:
returning
Token returning
Feature activation+1.551
Top resid features:
1
Token 1
Feature activation+0.010
Top resid features:
st
Tokenst
Feature activation+0.123
Top resid features:
-
Token-
Feature activation+0.009
Top resid features:
team
Tokenteam
Feature activation+0.650
Top resid features:
all
Token all
Feature activation+0.025
Top resid features:
loud
Token loud
Feature activation+0.022
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
and
Tokenand
Feature activation-0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
p
Tokenp
Feature activation-0.000
Top resid features:
roud
Tokenroud
Feature activation+2.295
Top resid features:
music
Token music
Feature activation+0.016
Top resid features:
g
Token g
Feature activation+0.000
Top resid features:
eeks
Tokeneeks
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
To
Token To
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
place
Token place
Feature activation+0.133
Top resid features:
20
Token 20
Feature activation+0.473
Top resid features:
part
Token part
Feature activation+0.040
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
time
Tokentime
Feature activation+1.975
Top resid features:
recovery
Token recovery
Feature activation+0.043
Top resid features:
coaches
Token coaches
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
full
Token full
Feature activation+0.000
Top resid features:
led
Token led
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
group
Token group
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.528
Top resid features:
passionate
Token passionate
Feature activation+2.056
Top resid features:
garden
Token garden
Feature activation+0.066
Top resid features:
ers
Tokeners
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:
is
Token is
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
cheating
Token cheating
Feature activation+0.015
Top resid features:
on
Token on
Feature activation+0.039
Top resid features:
Johnny
Token Johnny
Feature activation+0.016
Top resid features:
with
Token with
Feature activation+0.073
Top resid features:
other
Token other
Feature activation+2.316
Top resid features:
bisexual
Token bisexual
Feature activation+0.153
Top resid features:
celebrities
Token celebrities
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
Car
Token Car
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.009
Top resid features:
able
Token able
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
recruit
Token recruit
Feature activation+0.292
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
retain
Token retain
Feature activation+1.333
Top resid features:
the
Token the
Feature activation+0.778
Top resid features:
high
Token high
Feature activation+0.145
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
caliber
Tokencaliber
Feature activation+0.000
Top resid features:
employees
Token employees
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
join
Token join
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.042
Top resid features:
growing
Token growing
Feature activation+0.020
Top resid features:
list
Token list
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+2.442
Top resid features:
London
Token London
Feature activation+0.016
Top resid features:
Knights
Token Knights
Feature activation+0.021
Top resid features:
alumni
Token alumni
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
including
Token including
Feature activation+0.027
Top resid features:
most
Token most
Feature activation+0.199
Top resid features:
of
Token of
Feature activation+0.054
Top resid features:
their
Token their
Feature activation+0.845
Top resid features:
best
Token best
Feature activation+1.352
Top resid features:
under
Token under
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
21
Token21
Feature activation+0.043
Top resid features:
star
Token star
Feature activation+0.000
Top resid features:
lets
Tokenlets
Feature activation+0.000
Top resid features:
there
Tokenthere
Feature activation-0.000
Top resid features:
by
Tokenby
Feature activation-0.001
Top resid features:
inspiring
Token inspiring
Feature activation+0.025
Top resid features:
generations
Token generations
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.482
Top resid features:
future
Token future
Feature activation+1.983
Top resid features:
video
Token video
Feature activation+0.018
Top resid features:
artists
Token artists
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Pa
Token Pa
Feature activation+0.000
Top resid features:
ik
Tokenik
Feature activation+0.000
Top resid features:
ees
Tokenees
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
career
Token career
Feature activation+0.062
Top resid features:
histories
Token histories
Feature activation+0.021
Top resid features:
of
Token of
Feature activation+0.980
Top resid features:
senior
Token senior
Feature activation+0.788
Top resid features:
executive
Token executive
Feature activation+0.191
Top resid features:
branch
Token branch
Feature activation+0.144
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
aters
Tokenaters
Feature activation-0.005
Top resid features:
?
Token?
Feature activation+0.009
Top resid features:
Corpor
Token Corpor
Feature activation+0.020
Top resid features:
ations
Tokenations
Feature activation+0.021
Top resid features:
staffed
Token staffed
Feature activation+0.029
Top resid features:
by
Token by
Feature activation+1.751
Top resid features:
grown
Token grown
Feature activation+0.538
Top resid features:
-
Token-
Feature activation+0.014
Top resid features:
ass
Tokenass
Feature activation+0.085
Top resid features:
humans
Token humans
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
Johnny
Token Johnny
Feature activation-0.002
Top resid features:
Bans
Token Bans
Feature activation-0.007
Top resid features:
field
Tokenfield
Feature activation+0.023
Top resid features:
as
Token as
Feature activation+0.168
Top resid features:
two
Token two
Feature activation+0.191
Top resid features:
returning
Token returning
Feature activation+1.359
Top resid features:
1
Token 1
Feature activation+0.030
Top resid features:
st
Tokenst
Feature activation+0.237
Top resid features:
-
Token-
Feature activation+0.038
Top resid features:
team
Tokenteam
Feature activation+0.382
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.004
Top resid features:
undeniable
Token undeniable
Feature activation-0.015
Top resid features:
factor
Token factor
Feature activation-0.002
Top resid features:
motivating
Token motivating
Feature activation+0.026
Top resid features:
many
Token many
Feature activation+0.212
Top resid features:
seasoned
Token seasoned
Feature activation+2.139
Top resid features:
rock
Token rock
Feature activation+0.020
Top resid features:
ers
Tokeners
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:
plenty
Token plenty
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.036
Top resid features:
returning
Token returning
Feature activation+0.637
Top resid features:
1
Token 1
Feature activation+0.008
Top resid features:
st
Tokenst
Feature activation+0.057
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
team
Tokenteam
Feature activation+1.442
Top resid features:
all
Token all
Feature activation+0.043
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
region
Tokenregion
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.039
Top resid features:
show
Token show
Feature activation+0.075
Top resid features:
's
Token's
Feature activation+0.115
Top resid features:
assistant
Token assistant
Feature activation+2.041
Top resid features:
dance
Token dance
Feature activation+0.063
Top resid features:
captains
Token captains
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
works
Token works
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.030
Top resid features:
returning
Token returning
Feature activation+0.303
Top resid features:
1
Token 1
Feature activation+0.005
Top resid features:
st
Tokenst
Feature activation+0.060
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
team
Tokenteam
Feature activation+1.489
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
region
Tokenregion
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
is
Tokenis
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.168
Top resid features:
most
Token most
Feature activation+0.075
Top resid features:
senior
Token senior
Feature activation+1.807
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
respected
Token respected
Feature activation+0.250
Top resid features:
officers
Token officers
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:
some
Token some
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
Washington
Token Washington
Feature activation+0.102
Top resid features:
's
Token's
Feature activation+0.142
Top resid features:
most
Token most
Feature activation+0.197
Top resid features:
successful
Token successful
Feature activation+1.256
Top resid features:
-
Token -
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
infamous
Token infamous
Feature activation+0.505
Top resid features:
-
Token -
Feature activation+0.045
Top resid features:
lobbyists
Token lobbyists
Feature activation+0.000
Top resid features:
age
Tokenage
Feature activation+0.001
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
One
Token One
Feature activation-0.010
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.250
Top resid features:
top
Token top
Feature activation+1.930
Top resid features:
junior
Token junior
Feature activation+0.157
Top resid features:
prospects
Token prospects
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:
within
Token within
Feature activation+0.027
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
small
Token small
Feature activation-0.023
Top resid features:
group
Token group
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+0.587
Top resid features:
appointed
Token appointed
Feature activation+1.535
Top resid features:
tribal
Token tribal
Feature activation+0.111
Top resid features:
leaders
Token leaders
Feature activation+0.000
Top resid features:
compliant
Token compliant
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: 0.06

Head 1: 0.02

Head 2: 0.06

Head 3: 0.58

Head 4: 0.02

Head 5: 0.09

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.05

Head 11: 0.01

Positive logits

professionals3.75

specialists3.67

practitioners3.54

thinkers3.47

fellows3.43

secretaries3.42

enthusiasts3.36

regulars3.34

artists3.34

captains3.29

performers3.28

members3.26

ambassadors3.26

masters3.24

technicians3.24

graduates3.24

instructors3.23

contributors3.23

leaders3.22

retirees3.21

Negative logits

ridor-2.07

ifice-1.99

rama-1.96

airspace-1.89

iggurat-1.83

inconsistency-1.82

Volume-1.80

Volume-1.76

oxicity-1.76

omial-1.75

passage-1.74

outage-1.71

poem-1.71

expiration-1.71

reement-1.69

iseum-1.68

Regulation-1.68

equation-1.68

cture-1.67

uberty-1.67

INTERVAL 2.175 - 2.417
CONTAINS 0.000%

place
Token place
Feature activation+0.000
20
Token 20
Feature activation+0.372
part
Token part
Feature activation+0.623
-
Token-
Feature activation+1.341
time
Tokentime
Feature activation+0.622
recovery
Token recovery
Feature activation+2.240
coaches
Token coaches
Feature activation+0.645
and
Token and
Feature activation+0.376
five
Token five
Feature activation+0.221
full
Token full
Feature activation+0.639
-
Token-
Feature activation+0.806
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.175
passionate
Token passionate
Feature activation+1.077
garden
Token garden
Feature activation+2.199
ers
Tokeners
Feature activation+0.352
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
FREE
Token FREE
Feature activation+0.000
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token-
Feature activation+1.049
and
Tokenand
Feature activation+0.217
-
Token-
Feature activation+0.002
p
Tokenp
Feature activation+0.000
roud
Tokenroud
Feature activation+1.348
music
Token music
Feature activation+2.260
g
Token g
Feature activation+1.709
eeks
Tokeneeks
Feature activation+0.608
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000

INTERVAL 1.933 - 2.175
CONTAINS 0.001%

undeniable
Token undeniable
Feature activation+0.000
factor
Token factor
Feature activation+0.000
motivating
Token motivating
Feature activation+0.000
many
Token many
Feature activation+0.000
seasoned
Token seasoned
Feature activation+0.392
rock
Token rock
Feature activation+1.956
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
plenty
Token plenty
Feature activation+0.000
of
Token of
Feature activation+0.000
career
Token career
Feature activation+0.000
histories
Token histories
Feature activation+0.000
of
Token of
Feature activation+0.357
senior
Token senior
Feature activation+1.339
executive
Token executive
Feature activation+1.464
branch
Token branch
Feature activation+2.008
staff
Token staff
Feature activation+1.158
who
Token who
Feature activation+0.491
enter
Token enter
Feature activation+0.091
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
two
Token two
Feature activation+0.733
returning
Token returning
Feature activation+1.027
1
Token 1
Feature activation+0.986
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
by
Tokenby
Feature activation+0.000
inspiring
Token inspiring
Feature activation+0.000
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+0.116
future
Token future
Feature activation+0.889
video
Token video
Feature activation+2.016
artists
Token artists
Feature activation+0.000
.
Token.
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
has
Token has
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.522
best
Token best
Feature activation+0.456
under
Token under
Feature activation+0.698
-
Token-
Feature activation+1.268
21
Token21
Feature activation+2.065
star
Token star
Feature activation+0.498
lets
Tokenlets
Feature activation+0.436
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.692 - 1.933
CONTAINS 0.004%

all
Token all
Feature activation+0.000
would
Token would
Feature activation+0.048
-
Token-
Feature activation+0.574
be
Tokenbe
Feature activation+0.987
eco
Token eco
Feature activation+1.444
-
Token-
Feature activation+1.782
c
Tokenc
Feature activation+1.445
ities
Tokenities
Feature activation+0.571
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Copenhagen
Token Copenhagen
Feature activation+0.000
joined
Token joined
Feature activation+0.000
an
Token an
Feature activation+0.000
exclusive
Token exclusive
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.254
CIA
Token CIA
Feature activation+1.718
directors
Token directors
Feature activation+0.602
and
Token and
Feature activation+0.595
deputy
Token deputy
Feature activation+1.074
directors
Token directors
Feature activation+0.755
who
Token who
Feature activation+0.338
agers
Tokenagers
Feature activation+0.000
keep
Token keep
Feature activation+0.000
hiring
Token hiring
Feature activation+0.000
the
Token the
Feature activation+0.476
wrong
Token wrong
Feature activation+0.791
sales
Token sales
Feature activation+1.716
people
Tokenpeople
Feature activation+0.089
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
returning
Token returning
Feature activation+1.027
1
Token 1
Feature activation+0.986
st
Tokenst
Feature activation+1.418
-
Token-
Feature activation+1.526
team
Tokenteam
Feature activation+1.974
all
Token all
Feature activation+1.909
-
Token-
Feature activation+1.918
region
Tokenregion
Feature activation+2.417
players
Token players
Feature activation+0.696
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
and
Token and
Feature activation+0.889
hearing
Token hearing
Feature activation+1.743
-
Token-
Feature activation+1.111
im
Tokenim
Feature activation+0.672
pa
Tokenpa
Feature activation+0.052
ired
Tokenired
Feature activation+1.737
fans
Token fans
Feature activation+0.097
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
forced
Token forced
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 1.450 - 1.692
CONTAINS 0.008%

2
Token2
Feature activation+0.000
million
Token million
Feature activation+0.000
current
Token current
Feature activation+0.241
and
Token and
Feature activation+0.000
former
Token former
Feature activation+0.717
government
Token government
Feature activation+1.536
workers
Token workers
Feature activation+0.044
.
Token.
Feature activation+0.000
China
Token China
Feature activation+0.000
has
Token has
Feature activation+0.000
denied
Token denied
Feature activation+0.000
and
Token and
Feature activation+0.376
five
Token five
Feature activation+0.221
full
Token full
Feature activation+0.639
-
Token-
Feature activation+0.806
time
Tokentime
Feature activation+0.559
program
Token program
Feature activation+1.482
coordin
Token coordin
Feature activation+1.113
ators
Tokenators
Feature activation+0.692
with
Token with
Feature activation+0.195
police
Token police
Feature activation+0.039
departments
Token departments
Feature activation+0.000
-
Token-
Feature activation+1.040
looking
Tokenlooking
Feature activation+0.764
,
Token,
Feature activation+1.094
muscle
Token muscle
Feature activation+0.683
-
Token-
Feature activation+1.038
bound
Tokenbound
Feature activation+1.691
superst
Token superst
Feature activation+0.371
ars
Tokenars
Feature activation+0.084
could
Token could
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
communal
Token communal
Feature activation+0.000
spirit
Token spirit
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.138
surf
Token surf
Feature activation+1.558
ers
Tokeners
Feature activation+0.350
of
Token of
Feature activation+0.000
stone
Token stone
Feature activation+0.000
followed
Token followed
Feature activation+0.000
the
Token the
Feature activation+0.027
,
Token,
Feature activation+0.000
joined
Token joined
Feature activation+0.000
by
Token by
Feature activation+0.044
other
Token other
Feature activation+0.502
SH
Token SH
Feature activation+0.693
U
TokenU
Feature activation+1.475
prisoners
Token prisoners
Feature activation+0.471
throughout
Token throughout
Feature activation+0.000
California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
showed
Token showed
Feature activation+0.000

INTERVAL 1.208 - 1.450
CONTAINS 0.020%

in
Token in
Feature activation+0.038
the
Token the
Feature activation+0.111
house
Token house
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
lone
Token lone
Feature activation+0.349
gr
Token gr
Feature activation+1.389
anny
Tokenanny
Feature activation+1.006
,
Token,
Feature activation+0.499
lone
Token lone
Feature activation+0.468
mum
Token mum
Feature activation+0.315
and
Token and
Feature activation+0.157
âĢ
TokenâĢ
Feature activation+0.408
Ļ
TokenĻ
Feature activation+1.123
s
Tokens
Feature activation+0.934
high
Token high
Feature activation+1.138
-
Token-
Feature activation+1.204
level
Tokenlevel
Feature activation+1.269
employees
Token employees
Feature activation+0.003
and
Token and
Feature activation+0.000
rescind
Token rescind
Feature activation+0.000
ed
Tokened
Feature activation+0.000
a
Token a
Feature activation+0.000
care
Token care
Feature activation+0.000
as
Token as
Feature activation+0.000
20
Token 20
Feature activation+0.000
-
Token-
Feature activation+0.575
year
Tokenyear
Feature activation+0.062
-
Token-
Feature activation+1.393
olds
Tokenolds
Feature activation+0.092
,
Token,
Feature activation+0.000
yet
Token yet
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
decre
Token decre
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
show
Token show
Feature activation+0.236
's
Token's
Feature activation+0.255
assistant
Token assistant
Feature activation+1.402
dance
Token dance
Feature activation+1.916
captains
Token captains
Feature activation+0.532
,
Token,
Feature activation+0.000
works
Token works
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.076
including
Token including
Feature activation+0.379
some
Token some
Feature activation+0.712
newly
Token newly
Feature activation+1.073
arrived
Token arrived
Feature activation+1.186
asylum
Token asylum
Feature activation+1.344
seekers
Token seekers
Feature activation+0.643
and
Token and
Feature activation+0.908
many
Token many
Feature activation+0.726
other
Token other
Feature activation+1.119
immigrants
Token immigrants
Feature activation+0.462

INTERVAL 0.967 - 1.208
CONTAINS 0.048%

their
Token their
Feature activation+0.000
fellow
Token fellow
Feature activation+0.150
âĢ
Token âĢ
Feature activation+0.557
ľ
Tokenľ
Feature activation+1.112
atomic
Tokenatomic
Feature activation+1.006
bomb
Token bomb
Feature activation+1.192
spies
Token spies
Feature activation+0.610
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.693
brown
Token brown
Feature activation+0.550
shirt
Tokenshirt
Feature activation+0.604
alt
Token alt
Feature activation+0.651
-
Token-
Feature activation+1.409
right
Tokenright
Feature activation+1.107
en
Token en
Feature activation+1.056
for
Tokenfor
Feature activation+1.084
cers
Tokencers
Feature activation+0.516
,
Token,
Feature activation+0.763
the
Token the
Feature activation+0.757
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
top
Token top
Feature activation+0.371
Jewish
Token Jewish
Feature activation+1.099
figures
Token figures
Feature activation+0.000
in
Token in
Feature activation+0.007
the
Token the
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.000
party
Token party
Feature activation+0.014
discrim
Token discrim
Feature activation+0.000
inates
Tokeninates
Feature activation+0.000
against
Token against
Feature activation+0.000
non
Token non
Feature activation+0.258
-
Token-
Feature activation+0.283
bel
Tokenbel
Feature activation+1.071
ievers
Tokenievers
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
includes
Token includes
Feature activation+0.000
the
Token the
Feature activation+0.000
against
Token against
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
Target
Token Target
Feature activation+1.197
's
Token's
Feature activation+1.146
first
Token first
Feature activation+1.033
union
Token union
Feature activation+1.130
ized
Tokenized
Feature activation+0.766
employees
Token employees
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.725 - 0.967
CONTAINS 0.102%

different
Token different
Feature activation+0.000
from
Token from
Feature activation+0.000
what
Token what
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.609
working
Token working
Feature activation+0.877
class
Token class
Feature activation+0.785
children
Token children
Feature activation+0.000
of
Token of
Feature activation+0.000
color
Token color
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.957
s
Tokens
Feature activation+1.713
blue
Token blue
Feature activation+0.722
-
Token-
Feature activation+1.783
collar
Tokencollar
Feature activation+1.670
workers
Token workers
Feature activation+0.761
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
El
Token El
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
should
Token should
Feature activation+0.000
concern
Token concern
Feature activation+0.000
all
Token all
Feature activation+0.314
dog
Token dog
Feature activation+0.900
owners
Token owners
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
heroes
Token heroes
Feature activation+0.237
who
Token who
Feature activation+0.000
turn
Token turn
Feature activation+0.000
into
Token into
Feature activation+0.091
giant
Token giant
Feature activation+0.793
sand
Token sand
Feature activation+0.823
worms
Tokenworms
Feature activation+0.108
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
7
Token7
Feature activation+0.000
people
Token people
Feature activation+0.525
,
Token,
Feature activation+0.276
they
Token they
Feature activation+0.034
're
Token're
Feature activation+0.253
terrific
Token terrific
Feature activation+0.884
people
Token people
Feature activation+0.763
but
Token but
Feature activation+0.221
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
make
Token make
Feature activation+0.000

INTERVAL 0.483 - 0.725
CONTAINS 0.239%

are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.194
best
Token best
Feature activation+0.135
of
Token of
Feature activation+0.019
the
Token the
Feature activation+0.627
best
Token best
Feature activation+0.525
in
Token in
Feature activation+0.477
this
Token this
Feature activation+0.000
business
Token business
Feature activation+0.000
.
Token.
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
and
Token and
Feature activation+0.000
D
Token D
Feature activation+0.000
HL
TokenHL
Feature activation+0.000
),
Token),
Feature activation+0.498
and
Token and
Feature activation+0.309
academics
Token academics
Feature activation+0.498
and
Token and
Feature activation+0.732
researchers
Token researchers
Feature activation+0.573
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ranks
Token ranks
Feature activation+0.000
of
Token of
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.496
mortgage
Token mortgage
Feature activation+0.733
borrowers
Token borrowers
Feature activation+0.000
with
Token with
Feature activation+0.000
high
Token high
Feature activation+0.000
loan
Token loan
Feature activation+0.000
planted
Token planted
Feature activation+0.000
by
Token by
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.193
ľ
Tokenľ
Feature activation+0.502
stud
Tokenstud
Feature activation+0.658
ents
Tokenents
Feature activation+0.720
of
Token of
Feature activation+0.100
all
Token all
Feature activation+0.000
backgrounds
Token backgrounds
Feature activation+0.057
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
violence
Token violence
Feature activation+0.000
and
Token and
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
assault
Token assault
Feature activation+0.000
among
Token among
Feature activation+0.116
the
Token the
Feature activation+0.697
population
Token population
Feature activation+0.000
.
Token.
Feature activation+0.000
Traditional
Token Traditional
Feature activation+0.000
sources
Token sources
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.242 - 0.483
CONTAINS 0.553%

books
Tokenbooks
Feature activation+0.158
featuring
Token featuring
Feature activation+0.048
women
Token women
Feature activation+0.285
,
Token,
Feature activation+0.615
gay
Token gay
Feature activation+0.449
and
Token and
Feature activation+0.345
lesbian
Token lesbian
Feature activation+0.985
characters
Token characters
Feature activation+0.484
,
Token,
Feature activation+0.665
and
Token and
Feature activation+0.572
people
Token people
Feature activation+0.352
THERE
Token THERE
Feature activation+0.000
ARE
Token ARE
Feature activation+0.000
MORE
Token MORE
Feature activation+0.084
TH
Token TH
Feature activation+0.510
AN
TokenAN
Feature activation+0.000
JUST
Token JUST
Feature activation+0.360
WHITE
Token WHITE
Feature activation+0.774
ACT
Token ACT
Feature activation+1.401
ORS
TokenORS
Feature activation+0.175
,
Token,
Feature activation+0.000
PEOPLE
Token PEOPLE
Feature activation+0.084
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+0.127
credible
Token credible
Feature activation+0.395
,
Token,
Feature activation+0.517
serious
Token serious
Feature activation+0.586
choices
Token choices
Feature activation+0.000
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
up
Token up
Feature activation+0.000
of
Token of
Feature activation+0.000
83
Token 83
Feature activation+0.311
,
Token,
Feature activation+0.345
000
Token000
Feature activation+0.119
phot
Token phot
Feature activation+0.282
ov
Tokenov
Feature activation+0.346
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+0.176
panels
Token panels
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.098
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.174
s
Tokens
Feature activation+0.300
best
Token best
Feature activation+0.460
fighters
Token fighters
Feature activation+0.000
and
Token and
Feature activation+0.565
bombers
Token bombers
Feature activation+0.269
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.242
CONTAINS 99.025%

globe
Token globe
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
story
Token story
Feature activation+0.000
ended
Token ended
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
DC
Token DC
Feature activation+0.000
Comics
Token Comics
Feature activation+0.000
universe
Token universe
Feature activation+0.000
being
Token being
Feature activation+0.000
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
17
Token 17
Feature activation+0.000
76
Token76
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
reality
Token reality
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
database
Token database
Feature activation+0.000
dump
Token dump
Feature activation+0.000
created
Token created
Feature activation+0.000
by
Token by
Feature activation+0.000
m
Token m
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
od
Tokenod
Feature activation+0.000
ump
Tokenump
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Mongo
Token Mongo
Feature activation+0.000
f
Tokenf
Feature activation+0.000
in
Token in
Feature activation+0.000
September
Token September
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
expect
Token expect
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
drive
Token drive
Feature activation+0.000
-
Token-
Feature activation+0.000
c
Tokenc
Feature activation+0.000
ripp
Tokenripp
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
incom
Token incom
Feature activation+0.000
plet
Tokenplet
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H9.3: (feature 20496)

TOP ACTIVATIONS
MAX = 9.560

The
Token The
Feature activation+0.000
internet
Token internet
Feature activation+0.000
knows
Token knows
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+1.527
us
Token us
Feature activation+9.560
than
Token than
Feature activation+0.589
our
Token our
Feature activation+0.000
parents
Token parents
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
depends
Token depends
Feature activation+0.000
more
Token more
Feature activation+0.000
on
Token on
Feature activation+1.513
our
Token our
Feature activation+3.500
social
Token social
Feature activation+1.010
ity
Tokenity
Feature activation+7.696
than
Token than
Feature activation+0.198
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
intellect
Token intellect
Feature activation+0.249
,
Token,
Feature activation+0.313
for
Token for
Feature activation+2.091
organizers
Token organizers
Feature activation+5.129
to
Token to
Feature activation+4.239
explore
Token explore
Feature activation+3.071
their
Token their
Feature activation+0.316
work
Token work
Feature activation+7.664
than
Token than
Feature activation+0.000
through
Token through
Feature activation+0.000
writing
Token writing
Feature activation+0.000
science
Token science
Feature activation+0.000
fiction
Token fiction
Feature activation+0.000
the
Token the
Feature activation+2.016
European
Token European
Feature activation+1.890
side
Token side
Feature activation+6.870
of
Token of
Feature activation+0.888
the
Token the
Feature activation+0.282
pond
Token pond
Feature activation+7.420
throughout
Token throughout
Feature activation+1.346
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.451
its
Token its
Feature activation+0.264
history
Token history
Feature activation+3.595
and
Token and
Feature activation+5.671
learn
Token learn
Feature activation+5.307
from
Token from
Feature activation+3.817
a
Token a
Feature activation+0.578
good
Token good
Feature activation+0.739
instructor
Token instructor
Feature activation+7.166
versus
Token versus
Feature activation+0.371
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
champion
Token champion
Feature activation+0.393
.
Token.
Feature activation+0.000
I
TokenI
Feature activation+0.000
would
Token would
Feature activation+0.000
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+5.847
up
Token up
Feature activation+7.063
the
Token the
Feature activation+0.938
BBC
Token BBC
Feature activation+6.433
than
Token than
Feature activation+0.674
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.654
more
Token more
Feature activation+0.000
every
Token every
Feature activation+2.314
time
Token time
Feature activation+5.588
I
Token I
Feature activation+2.381
hear
Token hear
Feature activation+1.987
them
Token them
Feature activation+6.925
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+2.436
on
Token on
Feature activation+2.444
the
Token the
Feature activation+2.016
European
Token European
Feature activation+1.890
side
Token side
Feature activation+6.870
of
Token of
Feature activation+0.888
the
Token the
Feature activation+0.282
pond
Token pond
Feature activation+7.420
throughout
Token throughout
Feature activation+1.346
much
Token much
Feature activation+0.000
tion
Tokention
Feature activation+0.000
more
Token more
Feature activation+0.000
Demo
Token Demo
Feature activation+2.480
ÂŃ
TokenÂŃ
Feature activation+0.832
cr
Tokencr
Feature activation+1.624
at
Tokenat
Feature activation+6.676
ÂŃ
TokenÂŃ
Feature activation+1.107
ic
Tokenic
Feature activation+5.506
Sen
Token Sen
Feature activation+0.639
ÂŃ
TokenÂŃ
Feature activation+0.714
ate
Tokenate
Feature activation+3.543
learned
Token learned
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+2.456
life
Token life
Feature activation+5.613
and
Token and
Feature activation+2.295
history
Token history
Feature activation+6.636
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
before
Token before
Feature activation+0.119
,
Token,
Feature activation+0.695
âĢ
TokenâĢ
Feature activation+0.000
would
Token would
Feature activation+0.000
much
Token much
Feature activation+0.000
rather
Token rather
Feature activation+0.000
learn
Token learn
Feature activation+5.874
a
Token a
Feature activation+2.745
technique
Token technique
Feature activation+6.471
and
Token and
Feature activation+5.671
learn
Token learn
Feature activation+5.307
from
Token from
Feature activation+3.817
a
Token a
Feature activation+0.578
good
Token good
Feature activation+0.739
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+5.847
up
Token up
Feature activation+7.063
the
Token the
Feature activation+0.938
BBC
Token BBC
Feature activation+6.433
than
Token than
Feature activation+0.674
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.654
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.402
your
Token your
Feature activation+0.000
face
Token face
Feature activation+0.000
faster
Token faster
Feature activation+1.450
this
Token this
Feature activation+3.822
holiday
Token holiday
Feature activation+1.738
season
Token season
Feature activation+6.374
than
Token than
Feature activation+0.105
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
no
Token no
Feature activation+0.000
better
Token better
Feature activation+0.000
way
Token way
Feature activation+2.397
to
Token to
Feature activation+2.051
do
Token do
Feature activation+2.037
it
Token it
Feature activation+6.314
than
Token than
Feature activation+0.340
through
Token through
Feature activation+0.233
the
Token the
Feature activation+0.018
J
Token J
Feature activation+0.000
CT
TokenCT
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+1.756
to
Token to
Feature activation+1.348
me
Token me
Feature activation+6.216
and
Token and
Feature activation+3.115
to
Token to
Feature activation+2.810
Canada
Token Canada
Feature activation+5.726
than
Token than
Feature activation+0.232
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
is
Token is
Feature activation+0.000
vastly
Token vastly
Feature activation+0.000
larger
Token larger
Feature activation+0.175
today
Token today
Feature activation+6.077
,
Token,
Feature activation+1.216
in
Token in
Feature activation+0.926
inflation
Token inflation
Feature activation+0.523
-
Token-
Feature activation+0.275
adjusted
Tokenadjusted
Feature activation+0.099
policy
Token policy
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+1.571
to
Token to
Feature activation+2.911
people
Token people
Feature activation+5.999
of
Token of
Feature activation+2.244
color
Token color
Feature activation+4.729
than
Token than
Feature activation+0.205
debates
Token debates
Feature activation+0.096
over
Token over
Feature activation+0.000
to
Token to
Feature activation+1.912
the
Token the
Feature activation+2.079
surface
Token surface
Feature activation+4.619
of
Token of
Feature activation+1.750
the
Token the
Feature activation+0.472
earth
Token earth
Feature activation+5.940
.[
Token.[
Feature activation+0.000
13
Token13
Feature activation+0.000
][
Token][
Feature activation+0.000
14
Token14
Feature activation+0.000
]
Token]
Feature activation+0.000
had
Token had
Feature activation+0.000
more
Token more
Feature activation+0.000
interest
Token interest
Feature activation+1.535
in
Token in
Feature activation+1.451
the
Token the
Feature activation+2.344
facts
Token facts
Feature activation+5.934
than
Token than
Feature activation+0.385
the
Token the
Feature activation+0.200
Belt
Token Belt
Feature activation+0.000
way
Tokenway
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
much
Token much
Feature activation+0.000
rather
Token rather
Feature activation+0.000
learn
Token learn
Feature activation+5.874
a
Token a
Feature activation+2.745
technique
Token technique
Feature activation+6.471
and
Token and
Feature activation+5.671
learn
Token learn
Feature activation+5.307
from
Token from
Feature activation+3.817

Top DFA by src position
MAX = 9.685

online
Token online
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
internet
Token internet
Feature activation-0.008
Top resid features:
knows
Token knows
Feature activation+0.036
Top resid features:
more
Token more
Feature activation+9.685
Top resid features:
about
Token about
Feature activation+0.381
Top resid features:
us
Token us
Feature activation+0.052
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
parents
Token parents
Feature activation+0.000
Top resid features:
ovation
Tokenovation
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
our
Token our
Feature activation+0.009
Top resid features:
species
Token species
Feature activation+0.001
Top resid features:
depends
Token depends
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+7.465
Top resid features:
on
Token on
Feature activation+0.755
Top resid features:
our
Token our
Feature activation+0.004
Top resid features:
social
Token social
Feature activation+0.011
Top resid features:
ity
Tokenity
Feature activation+0.023
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
worlds
Token worlds
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
so
Token so
Feature activation-0.001
Top resid features:
what
Token what
Feature activation+0.001
Top resid features:
better
Token better
Feature activation+7.782
Top resid features:
venue
Token venue
Feature activation+0.267
Top resid features:
for
Token for
Feature activation+0.070
Top resid features:
organizers
Token organizers
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.147
Top resid features:
explore
Token explore
Feature activation+0.032
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
motors
Token motors
Feature activation+0.001
Top resid features:
port
Tokenport
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.018
Top resid features:
been
Token been
Feature activation-0.010
Top resid features:
more
Token more
Feature activation+5.563
Top resid features:
popular
Token popular
Feature activation+2.176
Top resid features:
on
Token on
Feature activation+0.135
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
European
Token European
Feature activation-0.001
Top resid features:
side
Token side
Feature activation+0.030
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
would
Token would
Feature activation-0.001
Top resid features:
much
Token much
Feature activation+0.005
Top resid features:
rather
Token rather
Feature activation+7.401
Top resid features:
learn
Token learn
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
technique
Token technique
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
learn
Token learn
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation+0.003
Top resid features:
would
Token would
Feature activation-0.009
Top resid features:
no
Token no
Feature activation-0.010
Top resid features:
more
Token more
Feature activation+7.700
Top resid features:
split
Token split
Feature activation+0.012
Top resid features:
up
Token up
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
BBC
Token BBC
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
mant
Token mant
Feature activation-0.010
Top resid features:
ras
Tokenras
Feature activation-0.006
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
bother
Token bother
Feature activation+0.002
Top resid features:
me
Token me
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+7.554
Top resid features:
every
Token every
Feature activation+0.047
Top resid features:
time
Token time
Feature activation+0.111
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
hear
Token hear
Feature activation-0.185
Top resid features:
them
Token them
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
motors
Token motors
Feature activation+0.001
Top resid features:
port
Tokenport
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.011
Top resid features:
been
Token been
Feature activation-0.022
Top resid features:
more
Token more
Feature activation+4.982
Top resid features:
popular
Token popular
Feature activation+2.236
Top resid features:
on
Token on
Feature activation+0.186
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
side
Token side
Feature activation+0.023
Top resid features:
set
Token set
Feature activation-0.002
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
mo
Token mo
Feature activation+0.004
Top resid features:
ÂŃ
TokenÂŃ
Feature activation-0.007
Top resid features:
tion
Tokention
Feature activation+0.005
Top resid features:
more
Token more
Feature activation+7.299
Top resid features:
Demo
Token Demo
Feature activation+0.029
Top resid features:
ÂŃ
TokenÂŃ
Feature activation+0.008
Top resid features:
cr
Tokencr
Feature activation-0.001
Top resid features:
at
Tokenat
Feature activation+0.001
Top resid features:
ÂŃ
TokenÂŃ
Feature activation+0.000
Top resid features:
history
Token history
Feature activation+0.008
Top resid features:
class
Token class
Feature activation+0.007
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
learned
Token learned
Feature activation-0.001
Top resid features:
more
Token more
Feature activation+6.847
Top resid features:
about
Token about
Feature activation+0.327
Top resid features:
life
Token life
Feature activation+0.038
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
history
Token history
Feature activation-0.005
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
much
Token much
Feature activation+0.009
Top resid features:
rather
Token rather
Feature activation+6.956
Top resid features:
learn
Token learn
Feature activation+0.045
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
technique
Token technique
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
learn
Token learn
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
I
TokenI
Feature activation+0.003
Top resid features:
would
Token would
Feature activation-0.005
Top resid features:
no
Token no
Feature activation-0.006
Top resid features:
more
Token more
Feature activation+7.140
Top resid features:
split
Token split
Feature activation-0.019
Top resid features:
up
Token up
Feature activation-0.087
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
BBC
Token BBC
Feature activation-0.005
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
smile
Token smile
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
your
Token your
Feature activation+0.002
Top resid features:
face
Token face
Feature activation+0.056
Top resid features:
faster
Token faster
Feature activation+6.848
Top resid features:
this
Token this
Feature activation+0.016
Top resid features:
holiday
Token holiday
Feature activation+0.007
Top resid features:
season
Token season
Feature activation+0.038
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
scoring
Token scoring
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
there
Token there
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
no
Token no
Feature activation-0.007
Top resid features:
better
Token better
Feature activation+3.897
Top resid features:
way
Token way
Feature activation+1.296
Top resid features:
to
Token to
Feature activation+1.454
Top resid features:
do
Token do
Feature activation+0.218
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
No
TokenNo
Feature activation-0.001
Top resid features:
relationship
Token relationship
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+3.700
Top resid features:
important
Token important
Feature activation+2.562
Top resid features:
to
Token to
Feature activation+0.515
Top resid features:
me
Token me
Feature activation+0.070
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
education
Token education
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
America
Token America
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
vastly
Token vastly
Feature activation+0.012
Top resid features:
larger
Token larger
Feature activation+6.338
Top resid features:
today
Token today
Feature activation+0.254
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
inflation
Token inflation
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
good
Token good
Feature activation+0.013
Top resid features:
policy
Token policy
Feature activation+0.011
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
more
Token more
Feature activation+1.672
Top resid features:
important
Token important
Feature activation+3.731
Top resid features:
to
Token to
Feature activation+1.109
Top resid features:
people
Token people
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
color
Token color
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
ridge
Tokenridge
Feature activation-0.000
Top resid features:
earthquake
Token earthquake
Feature activation-0.011
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
much
Token much
Feature activation-0.001
Top resid features:
shall
Token shall
Feature activation+0.005
Top resid features:
ower
Tokenower
Feature activation+4.467
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
closer
Token closer
Feature activation+1.820
Top resid features:
to
Token to
Feature activation+0.201
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
surface
Token surface
Feature activation+0.026
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.006
Top resid features:
who
Token who
Feature activation-0.011
Top resid features:
evidently
Token evidently
Feature activation+0.003
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
more
Token more
Feature activation+1.837
Top resid features:
interest
Token interest
Feature activation+3.213
Top resid features:
in
Token in
Feature activation+1.390
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
facts
Token facts
Feature activation+0.019
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
would
Token would
Feature activation-0.004
Top resid features:
much
Token much
Feature activation+0.025
Top resid features:
rather
Token rather
Feature activation+6.347
Top resid features:
learn
Token learn
Feature activation+0.066
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
technique
Token technique
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
learn
Token learn
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.03

Head 3: 0.58

Head 4: 0.01

Head 5: 0.05

Head 6: 0.02

Head 7: 0.03

Head 8: 0.01

Head 9: 0.01

Head 10: 0.18

Head 11: 0.03

Positive logits

than5.94

than5.52

Than4.30

ihad2.12

compared1.80

Th1.79

TH1.76

ategories1.74

iating1.71

zb1.69

��1.67

yk1.65

wx1.63

ront1.63

wiser1.62

urate1.61

imil1.60

abil1.59

ened1.56

iltr1.56

Negative logits

}}}-2.07

Gum-1.65

everlasting-1.64

Continuous-1.51

memorandum-1.48

innumerable-1.46

Quote-1.44

forever-1.43

cornerstone-1.43

slightest-1.42

Lakes-1.34

Sharp-1.33

unin-1.32

Dictionary-1.31

Registry-1.31

cellar-1.31

illac-1.30

Globe-1.29

endless-1.29

penny-1.27

INTERVAL 8.604 - 9.560
CONTAINS 0.000%

The
Token The
Feature activation+0.000
internet
Token internet
Feature activation+0.000
knows
Token knows
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+1.527
us
Token us
Feature activation+9.560
than
Token than
Feature activation+0.589
our
Token our
Feature activation+0.000
parents
Token parents
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000

INTERVAL 7.648 - 8.604
CONTAINS 0.000%

depends
Token depends
Feature activation+0.000
more
Token more
Feature activation+0.000
on
Token on
Feature activation+1.513
our
Token our
Feature activation+3.500
social
Token social
Feature activation+1.010
ity
Tokenity
Feature activation+7.696
than
Token than
Feature activation+0.198
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
intellect
Token intellect
Feature activation+0.249
,
Token,
Feature activation+0.313
for
Token for
Feature activation+2.091
organizers
Token organizers
Feature activation+5.129
to
Token to
Feature activation+4.239
explore
Token explore
Feature activation+3.071
their
Token their
Feature activation+0.316
work
Token work
Feature activation+7.664
than
Token than
Feature activation+0.000
through
Token through
Feature activation+0.000
writing
Token writing
Feature activation+0.000
science
Token science
Feature activation+0.000
fiction
Token fiction
Feature activation+0.000

INTERVAL 6.692 - 7.648
CONTAINS 0.001%

and
Token and
Feature activation+5.671
learn
Token learn
Feature activation+5.307
from
Token from
Feature activation+3.817
a
Token a
Feature activation+0.578
good
Token good
Feature activation+0.739
instructor
Token instructor
Feature activation+7.166
versus
Token versus
Feature activation+0.371
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
champion
Token champion
Feature activation+0.393
.
Token.
Feature activation+0.000
I
TokenI
Feature activation+0.000
would
Token would
Feature activation+0.000
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+5.847
up
Token up
Feature activation+7.063
the
Token the
Feature activation+0.938
BBC
Token BBC
Feature activation+6.433
than
Token than
Feature activation+0.674
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.654
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+2.436
on
Token on
Feature activation+2.444
the
Token the
Feature activation+2.016
European
Token European
Feature activation+1.890
side
Token side
Feature activation+6.870
of
Token of
Feature activation+0.888
the
Token the
Feature activation+0.282
pond
Token pond
Feature activation+7.420
throughout
Token throughout
Feature activation+1.346
much
Token much
Feature activation+0.000
the
Token the
Feature activation+2.016
European
Token European
Feature activation+1.890
side
Token side
Feature activation+6.870
of
Token of
Feature activation+0.888
the
Token the
Feature activation+0.282
pond
Token pond
Feature activation+7.420
throughout
Token throughout
Feature activation+1.346
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.451
its
Token its
Feature activation+0.264
history
Token history
Feature activation+3.595
more
Token more
Feature activation+0.000
every
Token every
Feature activation+2.314
time
Token time
Feature activation+5.588
I
Token I
Feature activation+2.381
hear
Token hear
Feature activation+1.987
them
Token them
Feature activation+6.925
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000

INTERVAL 5.736 - 6.692
CONTAINS 0.002%

a
Token a
Feature activation+0.578
little
Token little
Feature activation+0.000
more
Token more
Feature activation+0.256
in
Token in
Feature activation+1.582
this
Token this
Feature activation+1.522
environment
Token environment
Feature activation+5.818
when
Token when
Feature activation+1.119
people
Token people
Feature activation+0.313
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
spending
Token spending
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+1.756
to
Token to
Feature activation+1.348
me
Token me
Feature activation+6.216
and
Token and
Feature activation+3.115
to
Token to
Feature activation+2.810
Canada
Token Canada
Feature activation+5.726
than
Token than
Feature activation+0.232
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
much
Token much
Feature activation+0.000
rather
Token rather
Feature activation+0.000
learn
Token learn
Feature activation+5.874
a
Token a
Feature activation+2.745
technique
Token technique
Feature activation+6.471
and
Token and
Feature activation+5.671
learn
Token learn
Feature activation+5.307
from
Token from
Feature activation+3.817
were
Token were
Feature activation+0.000
based
Token based
Feature activation+0.000
more
Token more
Feature activation+0.000
on
Token on
Feature activation+1.372
hears
Token hears
Feature activation+0.290
ay
Tokenay
Feature activation+5.803
than
Token than
Feature activation+0.000
facts
Token facts
Feature activation+0.341
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
split
Token split
Feature activation+5.847
up
Token up
Feature activation+7.063
the
Token the
Feature activation+0.938
BBC
Token BBC
Feature activation+6.433
than
Token than
Feature activation+0.674
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.654
split
Token split
Feature activation+0.000
up
Token up
Feature activation+0.402

INTERVAL 4.780 - 5.736
CONTAINS 0.004%

available
Token available
Feature activation+0.000
on
Token on
Feature activation+0.000
more
Token more
Feature activation+0.000
Des
Token Des
Feature activation+1.321
kt
Tokenkt
Feature activation+0.559
ops
Tokenops
Feature activation+5.216
like
Token like
Feature activation+0.442
Mate
Token Mate
Feature activation+0.000
and
Token and
Feature activation+0.139
X
Token X
Feature activation+0.000
FC
TokenFC
Feature activation+0.000
on
Token on
Feature activation+1.310
reducing
Token reducing
Feature activation+2.629
my
Token my
Feature activation+0.765
mig
Token mig
Feature activation+0.000
rain
Tokenrain
Feature activation+0.000
es
Tokenes
Feature activation+5.457
and
Token and
Feature activation+1.343
acne
Token acne
Feature activation+1.916
,
Token,
Feature activation+1.623
but
Token but
Feature activation+0.000
(
Token (
Feature activation+0.000
so
Token so
Feature activation+0.000
what
Token what
Feature activation+0.000
better
Token better
Feature activation+0.000
venue
Token venue
Feature activation+4.686
for
Token for
Feature activation+2.091
organizers
Token organizers
Feature activation+5.129
to
Token to
Feature activation+4.239
explore
Token explore
Feature activation+3.071
their
Token their
Feature activation+0.316
work
Token work
Feature activation+7.664
than
Token than
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
concept
Token concept
Feature activation+5.018
car
Token car
Feature activation+5.664
than
Token than
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
speed
Token speed
Feature activation+0.000
ster
Tokenster
Feature activation+0.000
tech
Tokentech
Feature activation+1.625
theme
Token theme
Feature activation+0.950
park
Token park
Feature activation+1.537
robots
Token robots
Feature activation+1.387
malfunction
Token malfunction
Feature activation+1.153
"
Token"
Feature activation+5.174
than
Token than
Feature activation+0.283
"
Token "
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
begin
Token begin
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.824 - 4.780
CONTAINS 0.008%

in
Token in
Feature activation+1.472
their
Token their
Feature activation+2.390
opposition
Token opposition
Feature activation+3.868
to
Token to
Feature activation+0.793
creeping
Token creeping
Feature activation+0.854
professionalism
Token professionalism
Feature activation+3.863
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
union
Token union
Feature activation+0.448
.
Token.
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
zoom
Token zoom
Feature activation+2.112
ed
Tokened
Feature activation+2.136
out
Token out
Feature activation+3.924
than
Token than
Feature activation+0.021
normal
Token normal
Feature activation+0.363
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
were
Token were
Feature activation+0.000
both
Token both
Feature activation+0.000
closer
Token closer
Feature activation+0.000
friends
Token friends
Feature activation+3.501
to
Token to
Feature activation+1.598
him
Token him
Feature activation+4.703
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.119
to
Token to
Feature activation+0.000
each
Token each
Feature activation+0.000
trust
Token trust
Feature activation+2.812
scientists
Token scientists
Feature activation+4.517
to
Token to
Feature activation+3.257
tell
Token tell
Feature activation+1.201
the
Token the
Feature activation+1.154
truth
Token truth
Feature activation+3.899
(
Token (
Feature activation+1.137
79
Token79
Feature activation+0.000
%)
Token%)
Feature activation+2.581
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
BET
Token BET
Feature activation+0.000
TER
TokenTER
Feature activation+0.000
P
Token P
Feature activation+1.689
ED
TokenED
Feature activation+0.475
IG
TokenIG
Feature activation+0.000
REE
TokenREE
Feature activation+4.388
TH
Token TH
Feature activation+4.033
AN
TokenAN
Feature activation+0.000
ANC
Token ANC
Feature activation+0.000
EL
TokenEL
Feature activation+0.000
OT
TokenOT
Feature activation+0.000

INTERVAL 2.868 - 3.824
CONTAINS 0.018%

more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.725
to
Token to
Feature activation+1.293
find
Token find
Feature activation+1.471
the
Token the
Feature activation+0.724
latter
Token latter
Feature activation+2.927
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.200
at
Token at
Feature activation+0.679
Donald
Token Donald
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
machines
Token machines
Feature activation+3.081
and
Token and
Feature activation+1.502
more
Token more
Feature activation+0.749
men
Token men
Feature activation+1.373
.
Token.
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
comprehens
Token comprehens
Feature activation+0.308
ively
Tokenively
Feature activation+0.681
the
Token the
Feature activation+3.420
attitudes
Token attitudes
Feature activation+2.169
and
Token and
Feature activation+1.169
outlook
Token outlook
Feature activation+3.033
of
Token of
Feature activation+0.793
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+2.065
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
safer
Token safer
Feature activation+0.000
closer
Token closer
Feature activation+0.000
to
Token to
Feature activation+2.015
shore
Token shore
Feature activation+2.920
where
Token where
Feature activation+0.174
they
Token they
Feature activation+0.266
could
Token could
Feature activation+0.363
be
Token be
Feature activation+0.203
rescued
Token rescued
Feature activation+0.153
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
more
Token more
Feature activation+0.000
oxidation
Token oxidation
Feature activation+2.574
involved
Token involved
Feature activation+1.815
in
Token in
Feature activation+3.234
the
Token the
Feature activation+3.430
new
Token new
Feature activation+2.336
sample
Token sample
Feature activation+2.855
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 1.912 - 2.868
CONTAINS 0.051%

to
Token to
Feature activation+0.000
wear
Token wear
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
more
Token more
Feature activation+0.012
clothes
Token clothes
Feature activation+2.380
than
Token than
Feature activation+0.000
Quiet
Token Quiet
Feature activation+0.000
does
Token does
Feature activation+0.000
.
Token.
Feature activation+0.000
Probably
Token Probably
Feature activation+0.000
at
Token at
Feature activation+0.000
age
Token age
Feature activation+0.000
five
Token five
Feature activation+0.000
do
Token do
Feature activation+0.000
better
Token better
Feature activation+0.000
in
Token in
Feature activation+2.311
the
Token the
Feature activation+1.673
long
Token long
Feature activation+0.813
run
Token run
Feature activation+2.717
than
Token than
Feature activation+0.000
children
Token children
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
better
Token better
Feature activation+0.000
at
Token at
Feature activation+0.279
the
Token the
Feature activation+1.019
game
Token game
Feature activation+2.594
than
Token than
Feature activation+0.000
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
Short
Token Short
Feature activation+0.000
,
Token,
Feature activation+0.000
deployments
Token deployments
Feature activation+0.000
are
Token are
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
more
Token more
Feature activation+0.000
temporary
Token temporary
Feature activation+2.519
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+0.000
of
Token of
Feature activation+0.000
3
Token 3
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
only
Token only
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
more
Token more
Feature activation+0.000
in
Token in
Feature activation+2.280
love
Token love
Feature activation+3.769
with
Token with
Feature activation+1.131
the
Token the
Feature activation+1.468
fastest
Token fastest
Feature activation+0.691
game
Token game
Feature activation+0.954

INTERVAL 0.956 - 1.912
CONTAINS 0.150%

president
Token president
Feature activation+0.000
who
Token who
Feature activation+0.000
wants
Token wants
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
military
Token military
Feature activation+1.314
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
majorities
Token majorities
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
Bell
Token Bell
Feature activation+0.136
ator
Tokenator
Feature activation+1.237
news
Token news
Feature activation+0.085
and
Token and
Feature activation+0.000
updates
Token updates
Feature activation+0.056
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
straightforward
Token straightforward
Feature activation+0.435
to
Token to
Feature activation+0.905
encode
Token encode
Feature activation+3.135
and
Token and
Feature activation+2.740
decode
Token decode
Feature activation+3.101
with
Token with
Feature activation+1.494
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
would
Token would
Feature activation+0.000
offer
Token offer
Feature activation+0.000
them
Token them
Feature activation+0.000
greater
Token greater
Feature activation+0.000
security
Token security
Feature activation+1.027
and
Token and
Feature activation+1.152
influence
Token influence
Feature activation+1.029
.
Token.
Feature activation+0.000
Others
Token Others
Feature activation+0.000
backed
Token backed
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Remember
TokenRemember
Feature activation+0.000
the
Token the
Feature activation+0.000
Future
Token Future
Feature activation+0.000
Less
Token Less
Feature activation+0.000
V
Token V
Feature activation+1.049
ivid
Tokenivid
Feature activation+0.000
condition
Token condition
Feature activation+0.000
?
Token?
Feature activation+0.000
Probably
Token Probably
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 0.000 - 0.956
CONTAINS 99.768%

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
We
TokenWe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
to
Token to
Feature activation+0.000
dev
Token dev
Feature activation+0.000
our
Tokenour
Feature activation+0.000
their
Token their
Feature activation+0.000
bones
Token bones
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
worms
Token worms
Feature activation+0.000
heroes
Token heroes
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Com
TokenCom
Feature activation+0.000
in
Tokenin
Feature activation+0.000
are
Token are
Feature activation+0.000
"
Token "
Feature activation+0.000
marg
Tokenmarg
Feature activation+0.000
inally
Tokeninally
Feature activation+0.000
attached
Token attached
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
labor
Token labor
Feature activation+0.000
force
Token force
Feature activation+0.000
,
Token,
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+0.000
awards
Token awards
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Off
TokenOff
Feature activation+0.000
ensive
Tokenensive
Feature activation+0.000
Player
Token Player
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 H9.3: (feature 18434)

TOP ACTIVATIONS
MAX = 2.037

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Number
TokenNumber
Feature activation+0.000
of
Token of
Feature activation+0.098
Don
Token Don
Feature activation+2.037
ors
Tokenors
Feature activation+0.048
:
Token:
Feature activation+0.000
47
Token 47
Feature activation+0.000
,
Token,
Feature activation+0.000
048
Token048
Feature activation+0.000
for
Token for
Feature activation+0.000
75
Token 75
Feature activation+0.000
years
Token years
Feature activation+0.000
and
Token and
Feature activation+0.000
14
Token 14
Feature activation+0.000
pres
Token pres
Feature activation+1.958
id
Tokenid
Feature activation+0.000
encies
Tokenencies
Feature activation+0.000
.
Token.
Feature activation+0.000
Members
Token Members
Feature activation+0.000
from
Token from
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
gave
Token gave
Feature activation+0.000
three
Token three
Feature activation+0.277
very
Token very
Feature activation+1.797
clear
Token clear
Feature activation+1.919
directives
Token directives
Feature activation+0.153
.
Token.
Feature activation+0.000
Number
Token Number
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
?
Token?
Feature activation+0.000
Join
Token Join
Feature activation+0.000
three
Token three
Feature activation+0.000
COP
Token COP
Feature activation+0.309
I
TokenI
Feature activation+1.511
OUS
TokenOUS
Feature activation+1.900
engineers
Token engineers
Feature activation+0.070
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
share
Token share
Feature activation+0.000
their
Token their
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.029
Wil
Token Wil
Feature activation+0.066
ley
Tokenley
Feature activation+0.137
's
Token's
Feature activation+1.892
closest
Token closest
Feature activation+1.352
friends
Token friends
Feature activation+0.084
directly
Token directly
Feature activation+0.261
contradicted
Token contradicted
Feature activation+0.000
her
Token her
Feature activation+0.000
was
Token was
Feature activation+0.000
nominated
Token nominated
Feature activation+0.000
for
Token for
Feature activation+0.000
three
Token three
Feature activation+0.000
Helen
Token Helen
Feature activation+0.364
Hayes
Token Hayes
Feature activation+1.877
Awards
Token Awards
Feature activation+0.000
for
Token for
Feature activation+0.000
Best
Token Best
Feature activation+0.000
Supporting
Token Supporting
Feature activation+0.000
Actor
Token Actor
Feature activation+0.000
the
Token the
Feature activation+0.000
Song
Token Song
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Three
Token Three
Feature activation+0.328
Holy
Token Holy
Feature activation+1.848
Children
Token Children
Feature activation+0.000
,
Token,
Feature activation+0.000
Sus
Token Sus
Feature activation+0.000
anna
Tokenanna
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
gave
Token gave
Feature activation+0.000
three
Token three
Feature activation+0.277
very
Token very
Feature activation+1.797
clear
Token clear
Feature activation+1.919
directives
Token directives
Feature activation+0.153
.
Token.
Feature activation+0.000
Number
Token Number
Feature activation+0.000
one
Token one
Feature activation+0.000
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
before
Token before
Feature activation+0.000
three
Token three
Feature activation+0.000
Pacific
Token Pacific
Feature activation+1.445
Northwest
Token Northwest
Feature activation+1.780
states
Token states
Feature activation+0.046
are
Token are
Feature activation+0.094
authorized
Token authorized
Feature activation+0.000
to
Token to
Feature activation+0.009
begin
Token begin
Feature activation+0.000
separate
Token separate
Feature activation+1.146
approaches
Token approaches
Feature activation+0.000
for
Token for
Feature activation+0.279
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.000
separate
Token separate
Feature activation+1.764
sets
Token sets
Feature activation+0.475
of
Token of
Feature activation+1.201
data
Token data
Feature activation+0.469
presented
Token presented
Feature activation+0.000
in
Token in
Feature activation+0.000
AR
TokenAR
Feature activation+0.000
N
Token N
Feature activation+0.000
900
Token900
Feature activation+0.000
's
Token's
Feature activation+0.000
six
Token six
Feature activation+0.000
highly
Token highly
Feature activation+1.754
sensitive
Token sensitive
Feature activation+1.071
internal
Token internal
Feature activation+0.829
antennas
Token antennas
Feature activation+0.000
,
Token,
Feature activation+0.000
boosted
Token boosted
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
past
Token past
Feature activation+0.000
four
Token four
Feature activation+0.035
Fed
Token Fed
Feature activation+1.748
chairs
Token chairs
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
been
Token been
Feature activation+0.000
economists
Token economists
Feature activation+0.000
.
Token.
Feature activation+0.000
Having
Token Having
Feature activation+0.000
out
Token out
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
two
Token two
Feature activation+0.000
crown
Token crown
Feature activation+1.739
princes
Token princes
Feature activation+0.000
,
Token,
Feature activation+0.000
Sultan
Token Sultan
Feature activation+0.000
and
Token and
Feature activation+0.000
Nay
Token Nay
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
two
Token two
Feature activation+0.000
first
Token first
Feature activation+0.887
-
Token-
Feature activation+1.470
class
Tokenclass
Feature activation+1.716
games
Token games
Feature activation+0.000
"
Token"
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
pink
Token pink
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.000
just
Token just
Feature activation+0.000
two
Token two
Feature activation+0.024
on
Token on
Feature activation+1.692
-
Token-
Feature activation+1.292
prem
Tokenprem
Feature activation+0.199
ises
Tokenises
Feature activation+1.611
servers
Token servers
Feature activation+0.040
.
Token.
Feature activation+0.000
union
Token union
Feature activation+0.000
government
Token government
Feature activation+0.000
withdrew
Token withdrew
Feature activation+0.000
two
Token two
Feature activation+0.000
high
Token high
Feature activation+1.428
-
Token-
Feature activation+1.692
den
Tokenden
Feature activation+0.153
omination
Tokenomination
Feature activation+0.711
currency
Token currency
Feature activation+0.626
notes
Token notes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Dig
Token Dig
Feature activation+0.234
il
Tokenil
Feature activation+0.554
ent
Tokenent
Feature activation+1.691
PM
Token PM
Feature activation+1.266
OD
TokenOD
Feature activation+0.708
ports
Token ports
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
two
Token two
Feature activation+0.000
full
Token full
Feature activation+1.672
weekends
Token weekends
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
adding
Token adding
Feature activation+0.000
the
Token the
Feature activation+0.000
cores
Token cores
Feature activation+0.000
with
Token with
Feature activation+0.000
four
Token four
Feature activation+0.000
"
Token "
Feature activation+1.146
big
Tokenbig
Feature activation+0.828
"
Token"
Feature activation+1.657
high
Token high
Feature activation+0.996
-
Token-
Feature activation+0.970
performance
Tokenperformance
Feature activation+1.222
cores
Token cores
Feature activation+0.096
.
Token.
Feature activation+0.000
Reed
Token Reed
Feature activation+0.000
/
Token/
Feature activation+0.000
Reuters
TokenReuters
Feature activation+0.000
))
Token))
Feature activation+0.000
Two
Token Two
Feature activation+0.000
white
Token white
Feature activation+1.655
supremacists
Token supremacists
Feature activation+0.320
allegedly
Token allegedly
Feature activation+0.000
plotted
Token plotted
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000

Top DFA by src position
MAX = 2.706

100
Token100
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.003
Top resid features:
Number
TokenNumber
Feature activation+0.139
Top resid features:
of
Token of
Feature activation+2.480
Top resid features:
Don
Token Don
Feature activation+0.015
Top resid features:
ors
Tokenors
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
47
Token 47
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fashion
Token fashion
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.008
Top resid features:
75
Token 75
Feature activation+0.112
Top resid features:
years
Token years
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
14
Token 14
Feature activation+2.706
Top resid features:
pres
Token pres
Feature activation+0.006
Top resid features:
id
Tokenid
Feature activation+0.000
Top resid features:
encies
Tokenencies
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Members
Token Members
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
I
TokenI
Feature activation+0.024
Top resid features:
gave
Token gave
Feature activation+0.068
Top resid features:
three
Token three
Feature activation+2.206
Top resid features:
very
Token very
Feature activation+0.175
Top resid features:
clear
Token clear
Feature activation+0.079
Top resid features:
directives
Token directives
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Number
Token Number
Feature activation+0.000
Top resid features:
e
Token e
Feature activation+0.008
Top resid features:
commerce
Tokencommerce
Feature activation+0.013
Top resid features:
store
Token store
Feature activation-0.006
Top resid features:
?
Token?
Feature activation-0.024
Top resid features:
Join
Token Join
Feature activation+0.088
Top resid features:
three
Token three
Feature activation+2.504
Top resid features:
COP
Token COP
Feature activation+0.038
Top resid features:
I
TokenI
Feature activation+0.056
Top resid features:
OUS
TokenOUS
Feature activation+0.067
Top resid features:
engineers
Token engineers
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
overcome
Token overcome
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
Under
Token Under
Feature activation-0.003
Top resid features:
oath
Token oath
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.203
Top resid features:
two
Token two
Feature activation+1.933
Top resid features:
of
Token of
Feature activation+0.345
Top resid features:
Wil
Token Wil
Feature activation-0.012
Top resid features:
ley
Tokenley
Feature activation+0.027
Top resid features:
's
Token's
Feature activation+0.072
Top resid features:
closest
Token closest
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
nominated
Token nominated
Feature activation+0.003
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
three
Token three
Feature activation+2.639
Top resid features:
Helen
Token Helen
Feature activation+0.037
Top resid features:
Hayes
Token Hayes
Feature activation+0.016
Top resid features:
Awards
Token Awards
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Best
Token Best
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
Song
Token Song
Feature activation-0.021
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.449
Top resid features:
Three
Token Three
Feature activation+1.812
Top resid features:
Holy
Token Holy
Feature activation+0.157
Top resid features:
Children
Token Children
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sus
Token Sus
Feature activation+0.000
Top resid features:
anna
Tokenanna
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
I
TokenI
Feature activation+0.019
Top resid features:
gave
Token gave
Feature activation+0.086
Top resid features:
three
Token three
Feature activation+2.406
Top resid features:
very
Token very
Feature activation+0.087
Top resid features:
clear
Token clear
Feature activation+0.000
Top resid features:
directives
Token directives
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Number
Token Number
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
animals
Token animals
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
day
Token day
Feature activation-0.000
Top resid features:
before
Token before
Feature activation+0.039
Top resid features:
three
Token three
Feature activation+2.472
Top resid features:
Pacific
Token Pacific
Feature activation+0.035
Top resid features:
Northwest
Token Northwest
Feature activation+0.070
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
authorized
Token authorized
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.149
Top resid features:
separate
Token separate
Feature activation+0.046
Top resid features:
approaches
Token approaches
Feature activation+0.151
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
three
Token three
Feature activation+1.771
Top resid features:
separate
Token separate
Feature activation+0.214
Top resid features:
sets
Token sets
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
data
Token data
Feature activation+0.000
Top resid features:
presented
Token presented
Feature activation+0.000
Top resid features:
GE
TokenGE
Feature activation+0.000
Top resid features:
AR
TokenAR
Feature activation+0.006
Top resid features:
N
Token N
Feature activation+0.001
Top resid features:
900
Token900
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.077
Top resid features:
six
Token six
Feature activation+2.234
Top resid features:
highly
Token highly
Feature activation+0.037
Top resid features:
sensitive
Token sensitive
Feature activation+0.000
Top resid features:
internal
Token internal
Feature activation+0.000
Top resid features:
antennas
Token antennas
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.020
Top resid features:
appointment
Token appointment
Feature activation-0.047
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
past
Token past
Feature activation+0.255
Top resid features:
four
Token four
Feature activation+2.261
Top resid features:
Fed
Token Fed
Feature activation+0.096
Top resid features:
chairs
Token chairs
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Having
Token Having
Feature activation+0.040
Top resid features:
out
Token out
Feature activation-0.005
Top resid features:
lived
Tokenlived
Feature activation-0.024
Top resid features:
two
Token two
Feature activation+2.548
Top resid features:
crown
Token crown
Feature activation+0.021
Top resid features:
princes
Token princes
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sultan
Token Sultan
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
confident
Token confident
Feature activation-0.006
Top resid features:
"
Token "
Feature activation+0.032
Top resid features:
one
Tokenone
Feature activation+0.144
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
maybe
Token maybe
Feature activation+0.012
Top resid features:
two
Token two
Feature activation+1.607
Top resid features:
first
Token first
Feature activation+0.227
Top resid features:
-
Token-
Feature activation+0.030
Top resid features:
class
Tokenclass
Feature activation+0.343
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
March
Token March
Feature activation-0.005
Top resid features:
2012
Token 2012
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
using
Token using
Feature activation+0.011
Top resid features:
just
Token just
Feature activation+0.025
Top resid features:
two
Token two
Feature activation+2.147
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
prem
Tokenprem
Feature activation+0.000
Top resid features:
ises
Tokenises
Feature activation+0.000
Top resid features:
servers
Token servers
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
union
Token union
Feature activation-0.013
Top resid features:
government
Token government
Feature activation-0.005
Top resid features:
withdrew
Token withdrew
Feature activation+0.057
Top resid features:
two
Token two
Feature activation+2.340
Top resid features:
high
Token high
Feature activation+0.163
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
den
Tokenden
Feature activation+0.000
Top resid features:
omination
Tokenomination
Feature activation+0.000
Top resid features:
currency
Token currency
Feature activation+0.000
Top resid features:
MI
TokenMI
Feature activation+0.004
Top resid features:
output
Token output
Feature activation+0.000
Top resid features:
port
Token port
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Two
TokenTwo
Feature activation+1.868
Top resid features:
Dig
Token Dig
Feature activation+0.101
Top resid features:
il
Tokenil
Feature activation+0.011
Top resid features:
ent
Tokenent
Feature activation+0.281
Top resid features:
PM
Token PM
Feature activation+0.000
Top resid features:
OD
TokenOD
Feature activation+0.000
Top resid features:
itself
Token itself
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
estimate
Token estimate
Feature activation-0.013
Top resid features:
roughly
Token roughly
Feature activation+0.012
Top resid features:
two
Token two
Feature activation+2.116
Top resid features:
full
Token full
Feature activation+0.233
Top resid features:
weekends
Token weekends
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
adding
Token adding
Feature activation+0.000
Top resid features:
A
Token A
Feature activation-0.008
Top resid features:
53
Token53
Feature activation-0.007
Top resid features:
CPU
Token CPU
Feature activation+0.023
Top resid features:
cores
Token cores
Feature activation-0.014
Top resid features:
with
Token with
Feature activation+0.084
Top resid features:
four
Token four
Feature activation+1.973
Top resid features:
"
Token "
Feature activation+0.057
Top resid features:
big
Tokenbig
Feature activation+0.222
Top resid features:
"
Token"
Feature activation+0.034
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Jason
TokenJason
Feature activation+0.000
Top resid features:
Reed
Token Reed
Feature activation-0.002
Top resid features:
/
Token/
Feature activation-0.001
Top resid features:
Reuters
TokenReuters
Feature activation+0.005
Top resid features:
))
Token))
Feature activation+0.005
Top resid features:
Two
Token Two
Feature activation+2.231
Top resid features:
white
Token white
Feature activation+0.150
Top resid features:
supremacists
Token supremacists
Feature activation+0.000
Top resid features:
allegedly
Token allegedly
Feature activation+0.000
Top resid features:
plotted
Token plotted
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.04

Head 3: 0.58

Head 4: 0.02

Head 5: 0.06

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.02

Head 10: 0.08

Head 11: 0.02

Positive logits

secretaries2.98

Cups2.89

pairs2.82

sisters2.70

columns2.64

mentors2.63

towers2.62

slots2.62

finalists2.62

pillars2.56

atories2.56

presidents2.54

senators2.54

xes2.54

chairs2.52

nominees2.52

assistants2.52

captains2.50

partners2.49

brothers2.48

Negative logits

realism-2.24

nostalgia-2.10

inconvenience-2.01

sentiment-1.95

expression-1.94

nationalism-1.92

population-1.91

ismo-1.90

icism-1.88

atism-1.87

folklore-1.87

mythology-1.86

exaggeration-1.85

annoyance-1.84

uana-1.82

enance-1.82

oday-1.81

urden-1.81

globalization-1.81

atmosphere-1.80

INTERVAL 1.833 - 2.037
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Number
TokenNumber
Feature activation+0.000
of
Token of
Feature activation+0.098
Don
Token Don
Feature activation+2.037
ors
Tokenors
Feature activation+0.048
:
Token:
Feature activation+0.000
47
Token 47
Feature activation+0.000
,
Token,
Feature activation+0.000
048
Token048
Feature activation+0.000
the
Token the
Feature activation+0.000
Song
Token Song
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Three
Token Three
Feature activation+0.328
Holy
Token Holy
Feature activation+1.848
Children
Token Children
Feature activation+0.000
,
Token,
Feature activation+0.000
Sus
Token Sus
Feature activation+0.000
anna
Tokenanna
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.029
Wil
Token Wil
Feature activation+0.066
ley
Tokenley
Feature activation+0.137
's
Token's
Feature activation+1.892
closest
Token closest
Feature activation+1.352
friends
Token friends
Feature activation+0.084
directly
Token directly
Feature activation+0.261
contradicted
Token contradicted
Feature activation+0.000
her
Token her
Feature activation+0.000
for
Token for
Feature activation+0.000
75
Token 75
Feature activation+0.000
years
Token years
Feature activation+0.000
and
Token and
Feature activation+0.000
14
Token 14
Feature activation+0.000
pres
Token pres
Feature activation+1.958
id
Tokenid
Feature activation+0.000
encies
Tokenencies
Feature activation+0.000
.
Token.
Feature activation+0.000
Members
Token Members
Feature activation+0.000
from
Token from
Feature activation+0.000
?
Token?
Feature activation+0.000
Join
Token Join
Feature activation+0.000
three
Token three
Feature activation+0.000
COP
Token COP
Feature activation+0.309
I
TokenI
Feature activation+1.511
OUS
TokenOUS
Feature activation+1.900
engineers
Token engineers
Feature activation+0.070
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
share
Token share
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 1.629 - 1.833
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Dig
Token Dig
Feature activation+0.234
il
Tokenil
Feature activation+0.554
ent
Tokenent
Feature activation+1.691
PM
Token PM
Feature activation+1.266
OD
TokenOD
Feature activation+0.708
ports
Token ports
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
two
Token two
Feature activation+0.000
full
Token full
Feature activation+1.672
weekends
Token weekends
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
adding
Token adding
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Two
Token Two
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.864
three
Token three
Feature activation+1.552
j
Token j
Feature activation+1.647
agu
Tokenagu
Feature activation+0.926
ars
Tokenars
Feature activation+0.000
are
Token are
Feature activation+0.000
thought
Token thought
Feature activation+0.000
to
Token to
Feature activation+0.000
cores
Token cores
Feature activation+0.000
with
Token with
Feature activation+0.000
four
Token four
Feature activation+0.000
"
Token "
Feature activation+1.146
big
Tokenbig
Feature activation+0.828
"
Token"
Feature activation+1.657
high
Token high
Feature activation+0.996
-
Token-
Feature activation+0.970
performance
Tokenperformance
Feature activation+1.222
cores
Token cores
Feature activation+0.096
.
Token.
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
past
Token past
Feature activation+0.000
four
Token four
Feature activation+0.035
Fed
Token Fed
Feature activation+1.748
chairs
Token chairs
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
been
Token been
Feature activation+0.000
economists
Token economists
Feature activation+0.000

INTERVAL 1.426 - 1.629
CONTAINS 0.003%

animals
Token animals
Feature activation+0.000
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
before
Token before
Feature activation+0.000
three
Token three
Feature activation+0.000
Pacific
Token Pacific
Feature activation+1.445
Northwest
Token Northwest
Feature activation+1.780
states
Token states
Feature activation+0.046
are
Token are
Feature activation+0.094
authorized
Token authorized
Feature activation+0.000
to
Token to
Feature activation+0.009
information
Token information
Feature activation+0.000
.
Token.
Feature activation+0.000
Two
Token Two
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.864
three
Token three
Feature activation+1.552
j
Token j
Feature activation+1.647
agu
Tokenagu
Feature activation+0.926
ars
Tokenars
Feature activation+0.000
are
Token are
Feature activation+0.000
thought
Token thought
Feature activation+0.000
creation
Token creation
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
two
Token two
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.245
ľ
Tokenľ
Feature activation+1.475
highly
Tokenhighly
Feature activation+0.692
effective
Token effective
Feature activation+0.674
and
Token and
Feature activation+0.260
compact
Token compact
Feature activation+0.702
âĢ
TokenâĢ
Feature activation+0.000
took
Token took
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
five
Token five
Feature activation+0.000
front
Token front
Feature activation+1.455
men
Tokenmen
Feature activation+0.000
(
Token (
Feature activation+0.000
H
TokenH
Feature activation+0.000
arrison
Tokenarrison
Feature activation+0.000
,
Token,
Feature activation+0.000
He
Token He
Feature activation+0.000
had
Token had
Feature activation+0.000
already
Token already
Feature activation+0.000
expelled
Token expelled
Feature activation+0.000
three
Token three
Feature activation+0.178
US
Token US
Feature activation+1.488
diplomats
Token diplomats
Feature activation+0.042
,
Token,
Feature activation+0.000
claiming
Token claiming
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000

INTERVAL 1.222 - 1.426
CONTAINS 0.005%

on
Token on
Feature activation+0.000
four
Token four
Feature activation+0.000
or
Token or
Feature activation+0.000
five
Token five
Feature activation+0.395
simple
Token simple
Feature activation+0.827
but
Token but
Feature activation+1.336
compelling
Token compelling
Feature activation+0.983
examples
Token examples
Feature activation+0.066
of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.000
government
Token government
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Dutch
Token Dutch
Feature activation+1.394
men
Token men
Feature activation+0.000
who
Token who
Feature activation+0.203
ran
Token ran
Feature activation+0.239
the
Token the
Feature activation+0.000
cleaning
Token cleaning
Feature activation+0.000
two
Token two
Feature activation+0.000
brand
Token brand
Feature activation+0.513
new
Token new
Feature activation+1.128
and
Token and
Feature activation+0.721
un
Token un
Feature activation+0.174
proven
Tokenproven
Feature activation+1.330
breweries
Token breweries
Feature activation+0.000
had
Token had
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
first
Token first
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
special
Token special
Feature activation+0.392
BO
Token BO
Feature activation+0.458
J
TokenJ
Feature activation+1.345
programs
Token programs
Feature activation+0.000
was
Token was
Feature activation+0.000
created
Token created
Feature activation+0.000
in
Token in
Feature activation+0.000
June
Token June
Feature activation+0.000
was
Token was
Feature activation+0.000
given
Token given
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.017
other
Token other
Feature activation+1.321
documents
Token documents
Feature activation+0.162
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
Prism
Token Prism
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.018 - 1.222
CONTAINS 0.009%

Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
currently
Token currently
Feature activation+0.000
three
Token three
Feature activation+0.000
medical
Token medical
Feature activation+1.209
marijuana
Token marijuana
Feature activation+0.637
dispensaries
Token dispensaries
Feature activation+0.275
operating
Token operating
Feature activation+0.491
in
Token in
Feature activation+0.066
New
Token New
Feature activation+0.000
are
Token are
Feature activation+0.000
also
Token also
Feature activation+0.000
seven
Token seven
Feature activation+0.000
Dig
Token Dig
Feature activation+0.150
ides
Tokenides
Feature activation+0.027
ign
Tokenign
Feature activation+1.121
Pro
Token Pro
Feature activation+0.943
-
Token-
Feature activation+0.660
Tools
TokenTools
Feature activation+0.772
HD
Token HD
Feature activation+0.805
systems
Token systems
Feature activation+0.335
the
Token the
Feature activation+0.000
names
Token names
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.499
other
Token other
Feature activation+1.100
teenage
Token teenage
Feature activation+1.132
heroes
Token heroes
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.068
team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.101
New
Token New
Feature activation+0.425
York
Token York
Feature activation+1.422
Police
Token Police
Feature activation+1.132
Department
Token Department
Feature activation+1.048
officers
Token officers
Feature activation+0.027
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
death
Token death
Feature activation+0.000
1
Token 1
Feature activation+0.450
st
Tokenst
Feature activation+0.855
-
Token-
Feature activation+1.083
team
Tokenteam
Feature activation+1.031
all
Token all
Feature activation+1.247
-
Token-
Feature activation+1.126
region
Tokenregion
Feature activation+0.919
players
Token players
Feature activation+0.178
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.815 - 1.018
CONTAINS 0.019%

IP
TokenIP
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
se
Tokense
Feature activation+0.908
am
Tokenam
Feature activation+0.000
fastball
Token fastball
Feature activation+0.000
averages
Token averages
Feature activation+0.000
99
Token 99
Feature activation+0.000
mph
Token mph
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
at
Tokenat
Feature activation+0.276
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
co
Token co
Feature activation+0.892
-
Token-
Feature activation+0.797
found
Tokenfound
Feature activation+0.283
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
Edwin
Token Edwin
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
obscured
Token obscured
Feature activation+1.592
inv
Token inv
Feature activation+0.925
id
Tokenid
Feature activation+0.075
ual
Tokenual
Feature activation+0.928
s
Tokens
Feature activation+0.093
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
words
Token words
Feature activation+0.000
was
Token was
Feature activation+0.000
indicted
Token indicted
Feature activation+0.000
on
Token on
Feature activation+0.000
three
Token three
Feature activation+0.000
criminal
Token criminal
Feature activation+1.514
charge
Token charge
Feature activation+0.848
counts
Token counts
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
40
Token40
Feature activation+0.000
million
Token million
Feature activation+0.000
from
Token from
Feature activation+0.000
three
Token three
Feature activation+0.000
benefit
Token benefit
Feature activation+1.105
funds
Token funds
Feature activation+0.858
she
Token she
Feature activation+0.000
oversaw
Token oversaw
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.611 - 0.815
CONTAINS 0.034%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+0.000
big
Token big
Feature activation+0.089
prototype
Token prototype
Feature activation+0.611
lenses
Token lenses
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
on
Token on
Feature activation+0.000
display
Token display
Feature activation+0.000
marry
Token marry
Feature activation+0.000
the
Token the
Feature activation+0.000
mother
Token mother
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.052
three
Token three
Feature activation+0.625
children
Token children
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
recently
Token recently
Feature activation+0.000
bought
Token bought
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
four
Token four
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.249
sent
Token sent
Feature activation+0.571
another
Token another
Feature activation+0.625
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.756
acting
Token acting
Feature activation+0.154
ATF
Token ATF
Feature activation+0.000
Director
Token Director
Feature activation+0.000
followed
Token followed
Feature activation+0.000
their
Token their
Feature activation+0.000
muse
Token muse
Feature activation+0.000
to
Token to
Feature activation+0.000
four
Token four
Feature activation+0.000
stellar
Token stellar
Feature activation+0.741
No
Token No
Feature activation+0.443
.
Token.
Feature activation+0.396
1
Token 1
Feature activation+1.352
songs
Token songs
Feature activation+0.000
,
Token,
Feature activation+0.000
three
Token three
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.904
City
Token City
Feature activation+1.433
âĢ
TokenâĢ
Feature activation+0.181
Ļ
TokenĻ
Feature activation+0.926
s
Tokens
Feature activation+0.695
high
Token high
Feature activation+0.765
-
Token-
Feature activation+0.891
level
Tokenlevel
Feature activation+0.727
employees
Token employees
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.407 - 0.611
CONTAINS 0.056%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
now
Token now
Feature activation+0.000
-
Token-
Feature activation+0.355
re
Tokenre
Feature activation+0.523
branded
Tokenbranded
Feature activation+0.000
N
Token N
Feature activation+0.000
usra
Tokenusra
Feature activation+0.000
Front
Token Front
Feature activation+0.000
,
Token,
Feature activation+0.000
range
Token range
Feature activation+0.000
.
Token.
Feature activation+0.000
Fif
Token Fif
Feature activation+0.000
teen
Tokenteen
Feature activation+0.000
four
Token four
Feature activation+0.123
-
Token-
Feature activation+0.418
stars
Tokenstars
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Top
Token Top
Feature activation+0.000
247
Token247
Feature activation+0.000
50
Token 50
Feature activation+0.265
W
TokenW
Feature activation+0.367
/
Token/
Feature activation+0.084
12
Token12
Feature activation+0.000
V
TokenV
Feature activation+0.608
solar
Token solar
Feature activation+0.494
panel
Token panel
Feature activation+0.083
(
Token (
Feature activation+0.000
F
TokenF
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
female
Tokenfemale
Feature activation+0.000
connector
Token connector
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
2
Token 2
Feature activation+0.009
U
Token U
Feature activation+0.446
B
TokenB
Feature activation+0.316
NT
TokenNT
Feature activation+0.493
50
Token 50
Feature activation+0.265
W
TokenW
Feature activation+0.367
/
Token/
Feature activation+0.084
room
Token room
Feature activation+0.000
but
Token but
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.237
accus
Token accus
Feature activation+0.526
ers
Tokeners
Feature activation+0.000
shouts
Token shouts
Feature activation+0.000
him
Token him
Feature activation+0.000
down
Token down
Feature activation+0.000
saying
Token saying
Feature activation+0.000

INTERVAL 0.204 - 0.407
CONTAINS 0.126%

have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
two
Token two
Feature activation+0.000
vertical
Token vertical
Feature activation+0.240
trials
Token trials
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
Further
Token Further
Feature activation+0.000
,
Token,
Feature activation+0.000
154
Token 154
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
169
Token 169
Feature activation+0.233
were
Token were
Feature activation+0.000
released
Token released
Feature activation+0.000
pursuant
Token pursuant
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.000
Liverpool
Token Liverpool
Feature activation+0.000
supporter
Token supporter
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.000
best
Token best
Feature activation+0.372
feelings
Token feelings
Feature activation+0.073
are
Token are
Feature activation+0.000
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
trial
Token trial
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
pro
Token pro
Feature activation+0.247
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
has
Token has
Feature activation+0.000
yet
Token yet
Feature activation+0.000
Kaw
Token Kaw
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
ima
Tokenima
Feature activation+0.000
has
Token has
Feature activation+0.000
72
Token 72
Feature activation+0.000
Japan
Token Japan
Feature activation+0.370
caps
Token caps
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Japan
TokenJapan
Feature activation+0.000
international
Token international
Feature activation+0.000

INTERVAL 0.000 - 0.204
CONTAINS 99.747%

know
Token know
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
g
Tokeng
Feature activation+0.000
awa
Tokenawa
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
Con
TokenCon
Feature activation+0.000
cussion
Tokencussion
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
I
Token I
Feature activation+0.000
reached
Token reached
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
stro
Token stro
Feature activation+0.000
ked
Tokenked
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
conception
Token conception
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
light
Token light
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
recent
Token recent
Feature activation+0.000
comments
Token comments
Feature activation+0.000
families
Token families
Feature activation+0.000
are
Token are
Feature activation+0.000
strong
Token strong
Feature activation+0.000
,
Token,
Feature activation+0.000
America
Token America
Feature activation+0.000
is
Token is
Feature activation+0.000
strong
Token strong
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
over
Token over
Feature activation+0.000
party
Token party
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Raj
Token Raj
Feature activation+0.000
la
Tokenla
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H9.3: (feature 1891)

TOP ACTIVATIONS
MAX = 2.289

"
Token "
Feature activation+0.675
re
Tokenre
Feature activation+1.722
-
Token-
Feature activation+1.296
emer
Tokenemer
Feature activation+1.003
ging
Tokenging
Feature activation+1.537
gate
Token gate
Feature activation+2.289
ways
Tokenways
Feature activation+1.776
"
Token"
Feature activation+0.906
in
Token in
Feature activation+0.565
America
Token America
Feature activation+0.185
due
Token due
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+1.079
European
Token European
Feature activation+2.285
leagues
Token leagues
Feature activation+0.133
,
Token,
Feature activation+0.181
for
Token for
Feature activation+0.000
instance
Token instance
Feature activation+0.001
,
Token,
Feature activation+0.118
2016
Token 2016
Feature activation+0.000
.
Token.
Feature activation+0.000
Other
Token Other
Feature activation+0.000
Ubisoft
Token Ubisoft
Feature activation+1.969
Motion
Token Motion
Feature activation+1.024
Pictures
Token Pictures
Feature activation+2.178
projects
Token projects
Feature activation+0.000
currently
Token currently
Feature activation+0.000
in
Token in
Feature activation+0.274
development
Token development
Feature activation+0.019
include
Token include
Feature activation+0.000
ocking
Tokenocking
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
prec
Token prec
Feature activation+1.573
ocious
Tokenocious
Feature activation+2.121
youth
Token youth
Feature activation+1.043
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
all
Token all
Feature activation+0.000
other
Token other
Feature activation+0.494
BR
Token BR
Feature activation+1.255
IC
TokenIC
Feature activation+2.100
nations
Token nations
Feature activation+0.221
are
Token are
Feature activation+0.033
showcasing
Token showcasing
Feature activation+0.415
their
Token their
Feature activation+0.553
talent
Token talent
Feature activation+0.169
affordable
Token affordable
Feature activation+0.000
,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
most
Token most
Feature activation+0.725
other
Token other
Feature activation+2.079
nations
Token nations
Feature activation+0.000
with
Token with
Feature activation+0.247
that
Token that
Feature activation+0.000
rating
Token rating
Feature activation+0.000
,
Token,
Feature activation+0.000
among
Token among
Feature activation+0.023
major
Token major
Feature activation+1.101
U
Token U
Feature activation+1.170
.
Token.
Feature activation+0.900
S
TokenS
Feature activation+1.716
.
Token.
Feature activation+1.990
metro
Token metro
Feature activation+0.542
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Hum
Token Hum
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.565
health
Token health
Feature activation+1.955
insurance
Token insurance
Feature activation+1.989
companies
Token companies
Feature activation+0.378
that
Token that
Feature activation+0.169
cover
Token cover
Feature activation+0.388
surgical
Token surgical
Feature activation+0.000
abortions
Token abortions
Feature activation+0.316
States
Token States
Feature activation+0.000
topped
Token topped
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.203
per
Token per
Feature activation+1.979
capita
Token capita
Feature activation+1.584
meat
Token meat
Feature activation+0.674
consumption
Token consumption
Feature activation+0.786
with
Token with
Feature activation+0.000
89
Token 89
Feature activation+0.000
21
Token 21
Feature activation+0.000
st
Tokenst
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
.
Token.
Feature activation+0.000
Other
Token Other
Feature activation+0.000
Ubisoft
Token Ubisoft
Feature activation+1.969
Motion
Token Motion
Feature activation+1.024
Pictures
Token Pictures
Feature activation+2.178
projects
Token projects
Feature activation+0.000
currently
Token currently
Feature activation+0.000
in
Token in
Feature activation+0.274
traffic
Token traffic
Feature activation+0.000
decline
Token decline
Feature activation+0.000
of
Token of
Feature activation+0.000
several
Token several
Feature activation+0.041
major
Token major
Feature activation+1.122
cyber
Token cyber
Feature activation+1.969
lock
Tokenlock
Feature activation+1.269
ers
Tokeners
Feature activation+0.054
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lions
Token Lions
Feature activation+0.000
were
Token were
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.580
active
Token active
Feature activation+1.967
clubs
Token clubs
Feature activation+0.951
in
Token in
Feature activation+0.196
Stage
Token Stage
Feature activation+0.000
1
Token 1
Feature activation+0.000
last
Token last
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
13
Token 13
Feature activation+1.198
other
Token other
Feature activation+1.043
court
Token court
Feature activation+1.958
orders
Token orders
Feature activation+0.508
it
Token it
Feature activation+0.097
received
Token received
Feature activation+0.000
,
Token,
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
and
Token and
Feature activation+0.000
Hum
Token Hum
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.565
health
Token health
Feature activation+1.955
insurance
Token insurance
Feature activation+1.989
companies
Token companies
Feature activation+0.378
that
Token that
Feature activation+0.169
cover
Token cover
Feature activation+0.388
surgical
Token surgical
Feature activation+0.000
The
TokenThe
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
these
Token these
Feature activation+0.000
two
Token two
Feature activation+1.003
agricultural
Token agricultural
Feature activation+1.887
traditions
Token traditions
Feature activation+0.000
is
Token is
Feature activation+0.000
less
Token less
Feature activation+0.000
transparent
Token transparent
Feature activation+0.000
however
Token however
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.032
of
Token of
Feature activation+0.462
the
Token the
Feature activation+0.782
leading
Token leading
Feature activation+0.977
GOP
Token GOP
Feature activation+1.870
organizations
Token organizations
Feature activation+0.171
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.091
top
Token top
Feature activation+0.792
10
Token 10
Feature activation+1.175
global
Token global
Feature activation+1.842
economies
Token economies
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
its
Token its
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.035
the
Token the
Feature activation+0.529
state
Token state
Feature activation+0.928
's
Token's
Feature activation+1.037
67
Token 67
Feature activation+1.839
counties
Token counties
Feature activation+0.000
have
Token have
Feature activation+0.000
now
Token now
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
13
Token 13
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.445
ľ
Tokenľ
Feature activation+0.775
major
Tokenmajor
Feature activation+0.405
âĢ
TokenâĢ
Feature activation+1.428
Ŀ
TokenĿ
Feature activation+1.839
rebel
Token rebel
Feature activation+1.264
groups
Token groups
Feature activation+0.514
were
Token were
Feature activation+0.168
operating
Token operating
Feature activation+0.366
in
Token in
Feature activation+0.275
instance
Token instance
Feature activation+0.000
,
Token,
Feature activation+0.000
than
Token than
Feature activation+0.000
other
Token other
Feature activation+0.594
big
Token big
Feature activation+1.273
news
Token news
Feature activation+1.838
outlets
Token outlets
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000

Top DFA by src position
MAX = 2.402

the
Token the
Feature activation+0.282
Top resid features:
"
Token "
Feature activation+0.279
Top resid features:
re
Tokenre
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
emer
Tokenemer
Feature activation+0.007
Top resid features:
ging
Tokenging
Feature activation+1.921
Top resid features:
gate
Token gate
Feature activation+0.048
Top resid features:
ways
Tokenways
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
question
Token question
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
representatives
Token representatives
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.310
Top resid features:
other
Token other
Feature activation+2.227
Top resid features:
European
Token European
Feature activation+0.057
Top resid features:
leagues
Token leagues
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
instance
Token instance
Feature activation+0.000
Top resid features:
December
Token December
Feature activation-0.001
Top resid features:
21
Token 21
Feature activation-0.001
Top resid features:
st
Tokenst
Feature activation+0.000
Top resid features:
2016
Token 2016
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Other
Token Other
Feature activation+2.402
Top resid features:
Ubisoft
Token Ubisoft
Feature activation+0.130
Top resid features:
Motion
Token Motion
Feature activation-0.001
Top resid features:
Pictures
Token Pictures
Feature activation+0.001
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
Long
Token Long
Feature activation-0.001
Top resid features:
st
Tokenst
Feature activation-0.000
Top resid features:
ocking
Tokenocking
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:
other
Token other
Feature activation+2.238
Top resid features:
prec
Token prec
Feature activation+0.011
Top resid features:
ocious
Tokenocious
Feature activation+0.115
Top resid features:
youth
Token youth
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
VR
Token VR
Feature activation-0.002
Top resid features:
technology
Token technology
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
While
Token While
Feature activation+0.007
Top resid features:
all
Token all
Feature activation+0.569
Top resid features:
other
Token other
Feature activation+1.810
Top resid features:
BR
Token BR
Feature activation+0.070
Top resid features:
IC
TokenIC
Feature activation+0.017
Top resid features:
nations
Token nations
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
showcasing
Token showcasing
Feature activation+0.000
Top resid features:
easily
Token easily
Feature activation+0.000
Top resid features:
affordable
Token affordable
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
compared
Token compared
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.230
Top resid features:
most
Token most
Feature activation+1.954
Top resid features:
other
Token other
Feature activation+0.365
Top resid features:
nations
Token nations
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
rating
Token rating
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
their
Token their
Feature activation-0.003
Top resid features:
household
Token household
Feature activation-0.002
Top resid features:
pay
Token pay
Feature activation-0.018
Top resid features:
among
Token among
Feature activation+0.838
Top resid features:
major
Token major
Feature activation+1.446
Top resid features:
U
Token U
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
S
TokenS
Feature activation+0.066
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
metro
Token metro
Feature activation+0.000
Top resid features:
na
Tokenna
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
Hum
Token Hum
Feature activation+0.001
Top resid features:
ana
Tokenana
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.171
Top resid features:
two
Token two
Feature activation+1.925
Top resid features:
health
Token health
Feature activation+0.095
Top resid features:
insurance
Token insurance
Feature activation+0.081
Top resid features:
companies
Token companies
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
United
Token United
Feature activation+0.004
Top resid features:
States
Token States
Feature activation+0.000
Top resid features:
topped
Token topped
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
list
Token list
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+2.213
Top resid features:
per
Token per
Feature activation-0.008
Top resid features:
capita
Token capita
Feature activation+0.000
Top resid features:
meat
Token meat
Feature activation+0.000
Top resid features:
consumption
Token consumption
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
December
Token December
Feature activation-0.001
Top resid features:
21
Token 21
Feature activation-0.001
Top resid features:
st
Tokenst
Feature activation-0.000
Top resid features:
2016
Token 2016
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Other
Token Other
Feature activation+2.346
Top resid features:
Ubisoft
Token Ubisoft
Feature activation+0.008
Top resid features:
Motion
Token Motion
Feature activation+0.000
Top resid features:
Pictures
Token Pictures
Feature activation+0.000
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
traffic
Token traffic
Feature activation-0.007
Top resid features:
decline
Token decline
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.077
Top resid features:
several
Token several
Feature activation+0.631
Top resid features:
major
Token major
Feature activation+1.521
Top resid features:
cyber
Token cyber
Feature activation+0.092
Top resid features:
lock
Tokenlock
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.003
Top resid features:
Lions
Token Lions
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.118
Top resid features:
three
Token three
Feature activation+2.090
Top resid features:
active
Token active
Feature activation+0.159
Top resid features:
clubs
Token clubs
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Stage
Token Stage
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
Out
TokenOut
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
other
Token other
Feature activation+0.568
Top resid features:
13
Token 13
Feature activation+0.446
Top resid features:
other
Token other
Feature activation+1.230
Top resid features:
court
Token court
Feature activation+0.019
Top resid features:
orders
Token orders
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
received
Token received
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
na
Tokenna
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
Hum
Token Hum
Feature activation+0.000
Top resid features:
ana
Tokenana
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.267
Top resid features:
two
Token two
Feature activation+1.961
Top resid features:
health
Token health
Feature activation+0.011
Top resid features:
insurance
Token insurance
Feature activation+0.000
Top resid features:
companies
Token companies
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation-0.002
Top resid features:
relationship
Token relationship
Feature activation+0.003
Top resid features:
between
Token between
Feature activation+0.013
Top resid features:
these
Token these
Feature activation+0.845
Top resid features:
two
Token two
Feature activation+1.255
Top resid features:
agricultural
Token agricultural
Feature activation+0.070
Top resid features:
traditions
Token traditions
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
transparent
Token transparent
Feature activation+0.000
Top resid features:
leader
Token leader
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
one
Token one
Feature activation+0.060
Top resid features:
of
Token of
Feature activation+0.146
Top resid features:
the
Token the
Feature activation+0.202
Top resid features:
leading
Token leading
Feature activation+1.651
Top resid features:
GOP
Token GOP
Feature activation+0.107
Top resid features:
organizations
Token organizations
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
become
Token become
Feature activation+0.015
Top resid features:
one
Token one
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.193
Top resid features:
top
Token top
Feature activation+0.989
Top resid features:
10
Token 10
Feature activation+0.784
Top resid features:
global
Token global
Feature activation+0.182
Top resid features:
economies
Token economies
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.043
Top resid features:
each
Token each
Feature activation+0.146
Top resid features:
of
Token of
Feature activation+0.171
Top resid features:
the
Token the
Feature activation+0.227
Top resid features:
state
Token state
Feature activation+0.073
Top resid features:
's
Token's
Feature activation+1.472
Top resid features:
67
Token 67
Feature activation+0.119
Top resid features:
counties
Token counties
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
refused
Token refused
Feature activation+0.000
Top resid features:
2013
Token 2013
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
13
Token 13
Feature activation+0.440
Top resid features:
âĢ
Token âĢ
Feature activation+0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
major
Tokenmajor
Feature activation+1.906
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
rebel
Token rebel
Feature activation+0.000
Top resid features:
groups
Token groups
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
for
Token for
Feature activation-0.004
Top resid features:
instance
Token instance
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
than
Token than
Feature activation+0.167
Top resid features:
other
Token other
Feature activation+1.304
Top resid features:
big
Token big
Feature activation+0.672
Top resid features:
news
Token news
Feature activation+0.040
Top resid features:
outlets
Token outlets
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.02

Head 2: 0.05

Head 3: 0.58

Head 4: 0.03

Head 5: 0.06

Head 6: 0.03

Head 7: 0.04

Head 8: 0.03

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

establishments3.72

institutions3.58

venues3.56

destinations3.55

franchises3.54

enterprises3.47

centres3.45

hubs3.42

organizations3.39

entities3.37

providers3.35

cities3.35

industries3.31

centers3.29

arenas3.29

regimes3.28

sites3.27

platforms3.21

locations3.21

places3.20

Negative logits

��-2.21

epad-2.18

Sergeant-2.12

Trayvon-2.10

courage-1.99

misunderstanding-1.97

Spock-1.96

eanor-1.94

grin-1.93

apology-1.93

Shame-1.91

remorse-1.86

Woman-1.86

forcer-1.85

Sgt-1.84

voice-1.82

gratitude-1.81

Constable-1.81

obia-1.80

resemblance-1.77

INTERVAL 2.060 - 2.289
CONTAINS 0.001%

"
Token "
Feature activation+0.675
re
Tokenre
Feature activation+1.722
-
Token-
Feature activation+1.296
emer
Tokenemer
Feature activation+1.003
ging
Tokenging
Feature activation+1.537
gate
Token gate
Feature activation+2.289
ways
Tokenways
Feature activation+1.776
"
Token"
Feature activation+0.906
in
Token in
Feature activation+0.565
America
Token America
Feature activation+0.185
due
Token due
Feature activation+0.000
ocking
Tokenocking
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
prec
Token prec
Feature activation+1.573
ocious
Tokenocious
Feature activation+2.121
youth
Token youth
Feature activation+1.043
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+1.079
European
Token European
Feature activation+2.285
leagues
Token leagues
Feature activation+0.133
,
Token,
Feature activation+0.181
for
Token for
Feature activation+0.000
instance
Token instance
Feature activation+0.001
,
Token,
Feature activation+0.118
affordable
Token affordable
Feature activation+0.000
,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
most
Token most
Feature activation+0.725
other
Token other
Feature activation+2.079
nations
Token nations
Feature activation+0.000
with
Token with
Feature activation+0.247
that
Token that
Feature activation+0.000
rating
Token rating
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
all
Token all
Feature activation+0.000
other
Token other
Feature activation+0.494
BR
Token BR
Feature activation+1.255
IC
TokenIC
Feature activation+2.100
nations
Token nations
Feature activation+0.221
are
Token are
Feature activation+0.033
showcasing
Token showcasing
Feature activation+0.415
their
Token their
Feature activation+0.553
talent
Token talent
Feature activation+0.169

INTERVAL 1.831 - 2.060
CONTAINS 0.001%

States
Token States
Feature activation+0.000
topped
Token topped
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.203
per
Token per
Feature activation+1.979
capita
Token capita
Feature activation+1.584
meat
Token meat
Feature activation+0.674
consumption
Token consumption
Feature activation+0.786
with
Token with
Feature activation+0.000
89
Token 89
Feature activation+0.000
Hum
Token Hum
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.565
health
Token health
Feature activation+1.955
insurance
Token insurance
Feature activation+1.989
companies
Token companies
Feature activation+0.378
that
Token that
Feature activation+0.169
cover
Token cover
Feature activation+0.388
surgical
Token surgical
Feature activation+0.000
abortions
Token abortions
Feature activation+0.316
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
13
Token 13
Feature activation+1.198
other
Token other
Feature activation+1.043
court
Token court
Feature activation+1.958
orders
Token orders
Feature activation+0.508
it
Token it
Feature activation+0.097
received
Token received
Feature activation+0.000
,
Token,
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
13
Token 13
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.445
ľ
Tokenľ
Feature activation+0.775
major
Tokenmajor
Feature activation+0.405
âĢ
TokenâĢ
Feature activation+1.428
Ŀ
TokenĿ
Feature activation+1.839
rebel
Token rebel
Feature activation+1.264
groups
Token groups
Feature activation+0.514
were
Token were
Feature activation+0.168
operating
Token operating
Feature activation+0.366
in
Token in
Feature activation+0.275
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.035
the
Token the
Feature activation+0.529
state
Token state
Feature activation+0.928
's
Token's
Feature activation+1.037
67
Token 67
Feature activation+1.839
counties
Token counties
Feature activation+0.000
have
Token have
Feature activation+0.000
now
Token now
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.602 - 1.831
CONTAINS 0.004%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.168
major
Token major
Feature activation+0.429
Jude
Token Jude
Feature activation+0.644
an
Tokenan
Feature activation+1.700
rebel
Token rebel
Feature activation+0.825
factions
Token factions
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.073
most
Token most
Feature activation+0.277
played
Token played
Feature activation+1.622
games
Token games
Feature activation+0.298
in
Token in
Feature activation+0.327
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
County
Token County
Feature activation+0.000
Court
Token Court
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
state
Token state
Feature activation+1.784
Assembly
Token Assembly
Feature activation+1.668
districts
Token districts
Feature activation+0.261
have
Token have
Feature activation+0.236
primaries
Token primaries
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
large
Token large
Feature activation+0.066
,
Token,
Feature activation+1.336
unde
Token unde
Feature activation+0.613
velop
Tokenvelop
Feature activation+0.285
ed
Tokened
Feature activation+1.642
,
Token,
Feature activation+1.601
low
Token low
Feature activation+1.243
grade
Token grade
Feature activation+0.961
copper
Token copper
Feature activation+0.909
deposits
Token deposits
Feature activation+0.135
women
Token women
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
mass
Token mass
Feature activation+1.479
drunken
Token drunken
Feature activation+1.768
gatherings
Token gatherings
Feature activation+0.000
to
Token to
Feature activation+0.000
remember
Token remember
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.373 - 1.602
CONTAINS 0.007%

is
Token is
Feature activation+0.000
home
Token home
Feature activation+0.000
to
Token to
Feature activation+0.024
three
Token three
Feature activation+0.159
leading
Token leading
Feature activation+0.734
state
Token state
Feature activation+1.488
newspapers
Token newspapers
Feature activation+0.481
,
Token,
Feature activation+0.222
including
Token including
Feature activation+0.000
The
Token The
Feature activation+0.000
Birmingham
Token Birmingham
Feature activation+0.000
offering
Token offering
Feature activation+0.088
the
Token the
Feature activation+0.000
card
Token card
Feature activation+0.118
at
Token at
Feature activation+0.000
their
Token their
Feature activation+0.000
Dallas
Token Dallas
Feature activation+1.460
locations
Token locations
Feature activation+0.001
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Un
TokenUn
Feature activation+0.000
the
Token the
Feature activation+0.168
biggest
Token biggest
Feature activation+0.131
global
Token global
Feature activation+1.270
PR
Token PR
Feature activation+1.467
and
Token and
Feature activation+0.433
communications
Token communications
Feature activation+1.393
groups
Token groups
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
spread
Token spread
Feature activation+0.000
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.510
vulnerable
Token vulnerable
Feature activation+1.335
periphery
Token periphery
Feature activation+0.784
euro
Token euro
Feature activation+1.513
countries
Token countries
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
established
Token established
Feature activation+0.000
in
Token in
Feature activation+0.253
1984
Token 1984
Feature activation+0.000
;
Token;
Feature activation+0.000
other
Token other
Feature activation+0.225
immersion
Token immersion
Feature activation+1.488
schools
Token schools
Feature activation+0.000
followed
Token followed
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.144 - 1.373
CONTAINS 0.018%

Ļ
TokenĻ
Feature activation+0.390
s
Tokens
Feature activation+1.088
previous
Token previous
Feature activation+1.197
non
Token non
Feature activation+0.930
-
Token-
Feature activation+1.211
new
Tokennew
Feature activation+1.168
-
Token-
Feature activation+1.058
release
Tokenrelease
Feature activation+1.721
special
Token special
Feature activation+1.270
event
Token event
Feature activation+1.237
screenings
Token screenings
Feature activation+0.247
among
Tokenamong
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.073
5
Token 5
Feature activation+0.326
antiv
Token antiv
Feature activation+0.360
irus
Tokenirus
Feature activation+1.145
soft
Token soft
Feature activation+0.777
w
Tokenw
Feature activation+0.551
ares
Tokenares
Feature activation+0.431
globally
Token globally
Feature activation+0.000
with
Token with
Feature activation+0.000
(
Token (
Feature activation+0.000
among
Tokenamong
Feature activation+0.000
the
Token the
Feature activation+0.138
Top
Token Top
Feature activation+0.161
20
Token 20
Feature activation+0.586
Facebook
Token Facebook
Feature activation+1.372
games
Token games
Feature activation+0.707
globally
Token globally
Feature activation+0.125
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Together
Token Together
Feature activation+0.000
,
Token,
Feature activation+0.119
the
Token the
Feature activation+0.359
three
Token three
Feature activation+0.526
sub
Token sub
Feature activation+0.715
-
Token-
Feature activation+1.367
groups
Tokengroups
Feature activation+0.005
form
Token form
Feature activation+0.037
the
Token the
Feature activation+0.192
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.129
similar
Token similar
Feature activation+0.316
in
Token in
Feature activation+0.576
low
Token low
Feature activation+0.782
-
Token-
Feature activation+0.883
budget
Tokenbudget
Feature activation+0.877
indie
Token indie
Feature activation+1.291
Japanese
Token Japanese
Feature activation+1.725
titles
Token titles
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.916 - 1.144
CONTAINS 0.038%

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+0.236
two
Token two
Feature activation+1.046
main
Token main
Feature activation+0.929
elements
Token elements
Feature activation+0.562
of
Token of
Feature activation+0.650
Europe
Token Europe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.151
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
prospective
Token prospective
Feature activation+0.964
Vancouver
Token Vancouver
Feature activation+0.948
Giants
Token Giants
Feature activation+1.067
head
Token head
Feature activation+0.623
coaches
Token coaches
Feature activation+0.082
.
Token.
Feature activation+0.000
Sc
Token Sc
Feature activation+0.000
ratch
Tokenratch
Feature activation+0.000
with
Token with
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
Arabia
Token Arabia
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
regional
Token regional
Feature activation+1.093
nations
Token nations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.000
istan
Tokenistan
Feature activation+0.000
and
Token and
Feature activation+0.000
Sind
Token Sind
Feature activation+0.000
h
Tokenh
Feature activation+0.000
were
Token were
Feature activation+0.000
Ind
Token Ind
Feature activation+1.084
ic
Tokenic
Feature activation+1.299
minority
Token minority
Feature activation+0.984
;
Token;
Feature activation+0.000
both
Token both
Feature activation+0.000
Bengal
Token Bengal
Feature activation+0.620
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
many
Token many
Feature activation+0.010
consumer
Token consumer
Feature activation+0.585
-
Token-
Feature activation+0.957
oriented
Tokenoriented
Feature activation+0.844
Linux
Token Linux
Feature activation+1.111
distributions
Token distributions
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.290

INTERVAL 0.687 - 0.916
CONTAINS 0.081%

from
Token from
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.044
the
Token the
Feature activation+0.186
handful
Token handful
Feature activation+0.007
of
Token of
Feature activation+0.824
civic
Token civic
Feature activation+1.248
groups
Token groups
Feature activation+0.722
in
Token in
Feature activation+0.319
El
Token El
Feature activation+0.000
mont
Tokenmont
Feature activation+0.014
U
TokenU
Feature activation+0.324
.
Token.
Feature activation+0.233
S
TokenS
Feature activation+0.221
.
Token.
Feature activation+0.404
A
TokenA
Feature activation+0.494
.
Token.
Feature activation+0.872
addresses
Token addresses
Feature activation+0.000
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+0.000
at
Token at
Feature activation+0.000
$
Token $
Feature activation+0.000
a
Token a
Feature activation+0.000
basic
Token basic
Feature activation+0.000
whit
Token whit
Feature activation+0.000
elist
Tokenelist
Feature activation+0.000
of
Token of
Feature activation+0.000
major
Token major
Feature activation+0.737
news
Token news
Feature activation+1.060
sites
Token sites
Feature activation+0.017
,
Token,
Feature activation+0.205
a
Token a
Feature activation+0.000
listing
Token listing
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+0.211
credible
Token credible
Feature activation+0.669
,
Token,
Feature activation+0.652
serious
Token serious
Feature activation+0.731
choices
Token choices
Feature activation+0.000
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Comments
TokenComments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
flags
Token flags
Feature activation+0.317
hips
Tokenhips
Feature activation+0.103
,
Token,
Feature activation+0.000
among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.194
biggest
Token biggest
Feature activation+0.734
of
Token of
Feature activation+0.602
the
Token the
Feature activation+0.872
chain
Token chain
Feature activation+0.508
at
Token at
Feature activation+0.000
149
Token 149
Feature activation+0.000

INTERVAL 0.458 - 0.687
CONTAINS 0.190%

Portland
Token Portland
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
int
Token int
Feature activation+0.193
rast
Tokenrast
Feature activation+0.516
ate
Tokenate
Feature activation+0.025
service
Token service
Feature activation+0.000
to
Token to
Feature activation+0.067
Anchorage
Token Anchorage
Feature activation+0.000
,
Token,
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000
seen
Token seen
Feature activation+0.000
similar
Token similar
Feature activation+0.316
in
Token in
Feature activation+0.576
low
Token low
Feature activation+0.782
-
Token-
Feature activation+0.883
budget
Tokenbudget
Feature activation+0.877
indie
Token indie
Feature activation+1.291
Japanese
Token Japanese
Feature activation+1.725
posit
Token posit
Feature activation+0.000
that
Token that
Feature activation+0.000
investors
Token investors
Feature activation+0.000
in
Token in
Feature activation+0.000
oil
Token oil
Feature activation+0.418
,
Token,
Feature activation+0.478
and
Token and
Feature activation+0.303
eventually
Token eventually
Feature activation+0.158
even
Token even
Feature activation+0.112
natural
Token natural
Feature activation+0.169
gas
Token gas
Feature activation+0.098
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+0.000
investments
Token investments
Feature activation+0.000
in
Token in
Feature activation+0.072
non
Token non
Feature activation+0.535
-
Token-
Feature activation+0.827
profits
Tokenprofits
Feature activation+0.000
like
Token like
Feature activation+0.180
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+0.000
were
Token were
Feature activation+0.000
African
Token African
Feature activation+0.083
-
Token-
Feature activation+0.583
Americans
TokenAmericans
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
did
Token did
Feature activation+0.000

INTERVAL 0.229 - 0.458
CONTAINS 0.505%

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
primary
Token primary
Feature activation+0.343
organizing
Token organizing
Feature activation+0.411
principles
Token principles
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
getting
Token getting
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
owning
Token owning
Feature activation+0.134
a
Token a
Feature activation+0.261
club
Token club
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Eagles
Token Eagles
Feature activation+0.000
only
Token only
Feature activation+0.000
have
Token have
Feature activation+0.000
six
Token six
Feature activation+0.000
passing
Token passing
Feature activation+0.418
touchdowns
Token touchdowns
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
areas
Token areas
Feature activation+0.075
routinely
Token routinely
Feature activation+0.004
have
Token have
Feature activation+0.028
to
Token to
Feature activation+0.282
wait
Token wait
Feature activation+0.112
an
Token an
Feature activation+0.147
hour
Token hour
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
mainland
Token mainland
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
nearest
Token nearest
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.305
island
Token island
Feature activation+0.000
,
Token,
Feature activation+0.000
O
Token O
Feature activation+0.000
ki
Tokenki
Feature activation+0.000
Islands
Token Islands
Feature activation+0.000

INTERVAL 0.000 - 0.229
CONTAINS 99.157%

has
Token has
Feature activation+0.000
surfaced
Token surfaced
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
still
Token still
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
Be
Token Be
Feature activation+0.000
An
Token An
Feature activation+0.000
Emergency
Token Emergency
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
theory
Token theory
Feature activation+0.000
,
Token,
Feature activation+0.000
your
Token your
Feature activation+0.000
That
Token That
Feature activation+0.000
will
Token will
Feature activation+0.000
change
Token change
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
officers
Token officers
Feature activation+0.000
will
Token will
Feature activation+0.000
become
Token become
Feature activation+0.000
targets
Token targets
Feature activation+0.000
of
Token of
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
.
Token.
Feature activation+0.000
Luckily
Token Luckily
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
clean
Token clean
Feature activation+0.000
HP
Token HP
Feature activation+0.000
print
Token print
Feature activation+0.000
heads
Token heads
Feature activation+0.000
almost
Token almost
Feature activation+0.000
all
Token all
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
How
TokenHow
Feature activation+0.000
often
Token often
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
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 7 in H9.3: (feature 476)

TOP ACTIVATIONS
MAX = 3.206

Hall
Token Hall
Feature activation+0.150
of
Token of
Feature activation+0.890
Fame
Token Fame
Feature activation+1.063
football
Token football
Feature activation+3.106
and
Token and
Feature activation+0.986
wrestling
Token wrestling
Feature activation+3.119
coach
Token coach
Feature activation+0.141
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.150
of
Token of
Feature activation+0.890
Fame
Token Fame
Feature activation+1.063
football
Token football
Feature activation+3.106
and
Token and
Feature activation+0.986
wrestling
Token wrestling
Feature activation+3.119
coach
Token coach
Feature activation+0.141
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
am
Token am
Feature activation+0.000
a
Token a
Feature activation+0.000
lifelong
Token lifelong
Feature activation+0.497
off
Token off
Feature activation+2.068
-
Token-
Feature activation+2.196
road
Tokenroad
Feature activation+2.993
cyclist
Token cyclist
Feature activation+0.742
,
Token,
Feature activation+0.000
n
Token n
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
ic
Tokenic
Feature activation+1.307
a
Token a
Feature activation+0.232
conservative
Token conservative
Feature activation+1.263
gun
Token gun
Feature activation+2.398
-
Token-
Feature activation+2.353
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
bible
Token bible
Feature activation+1.837
-
Token-
Feature activation+2.421
cling
Tokencling
Feature activation+1.623
the
Token the
Feature activation+0.165
expert
Token expert
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.848
licensed
Token licensed
Feature activation+1.750
medical
Token medical
Feature activation+2.756
professional
Token professional
Feature activation+0.762
and
Token and
Feature activation+0.042
has
Token has
Feature activation+0.142
a
Token a
Feature activation+0.165
specialty
Token specialty
Feature activation+0.000
skilled
Token skilled
Feature activation+0.880
,
Token,
Feature activation+1.965
fast
Token fast
Feature activation+2.161
,
Token,
Feature activation+2.020
and
Token and
Feature activation+1.620
powerful
Token powerful
Feature activation+2.718
warrior
Token warrior
Feature activation+1.030
,
Token,
Feature activation+0.029
well
Token well
Feature activation+0.125
deserving
Token deserving
Feature activation+0.000
of
Token of
Feature activation+0.000
er
Tokener
Feature activation+0.863
,
Token,
Feature activation+1.293
or
Token or
Feature activation+1.602
p
Token p
Feature activation+1.829
ogo
Tokenogo
Feature activation+1.130
-
Token-
Feature activation+2.601
stick
Tokenstick
Feature activation+2.076
jumper
Token jumper
Feature activation+1.537
(
Token (
Feature activation+0.239
ok
Tokenok
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
author
Token author
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.122
lifelong
Token lifelong
Feature activation+0.677
sports
Token sports
Feature activation+2.574
enthusiast
Token enthusiast
Feature activation+0.661
and
Token and
Feature activation+1.153
firm
Token firm
Feature activation+0.714
believer
Token believer
Feature activation+1.071
in
Token in
Feature activation+0.562
,
Token,
Feature activation+1.396
bright
Token bright
Feature activation+1.866
,
Token,
Feature activation+1.663
caring
Token caring
Feature activation+2.494
and
Token and
Feature activation+1.288
loving
Token loving
Feature activation+2.560
young
Token young
Feature activation+2.050
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
consider
Token consider
Feature activation+0.000
conservative
Token conservative
Feature activation+0.525
,
Token,
Feature activation+0.840
consensus
Token consensus
Feature activation+1.703
-
Token-
Feature activation+2.352
building
Tokenbuilding
Feature activation+2.148
former
Token former
Feature activation+2.545
budget
Token budget
Feature activation+2.004
chief
Token chief
Feature activation+0.901
under
Token under
Feature activation+0.459
David
Token David
Feature activation+0.000
Miller
Token Miller
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
fearless
Token fearless
Feature activation+0.979
and
Token and
Feature activation+0.990
exceptional
Token exceptional
Feature activation+2.534
soldier
Token soldier
Feature activation+0.207
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
a
Token a
Feature activation+0.149
great
Token great
Feature activation+1.326
an
Token an
Feature activation+0.000
exceptional
Token exceptional
Feature activation+1.080
,
Token,
Feature activation+1.396
bright
Token bright
Feature activation+1.866
,
Token,
Feature activation+1.663
caring
Token caring
Feature activation+2.494
and
Token and
Feature activation+1.288
loving
Token loving
Feature activation+2.560
young
Token young
Feature activation+2.050
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.000
well
Token well
Feature activation+0.435
as
Token as
Feature activation+0.867
a
Token a
Feature activation+0.960
fan
Token fan
Feature activation+1.833
atical
Tokenatical
Feature activation+1.939
football
Token football
Feature activation+2.481
fan
Token fan
Feature activation+1.604
who
Token who
Feature activation+0.350
loved
Token loved
Feature activation+0.000
bl
Token bl
Feature activation+0.000
oke
Tokenoke
Feature activation+0.000
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
bible
Token bible
Feature activation+1.837
-
Token-
Feature activation+2.421
cling
Tokencling
Feature activation+1.623
in
Tokenin
Feature activation+1.402
âĢ
TokenâĢ
Feature activation+0.145
Ļ
TokenĻ
Feature activation+2.243
literary
Token literary
Feature activation+1.671
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.232
conservative
Token conservative
Feature activation+1.263
gun
Token gun
Feature activation+2.398
-
Token-
Feature activation+2.353
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
bible
Token bible
Feature activation+1.837
-
Token-
Feature activation+2.421
describes
Token describes
Feature activation+0.000
himself
Token himself
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.232
conservative
Token conservative
Feature activation+1.263
gun
Token gun
Feature activation+2.398
-
Token-
Feature activation+2.353
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
're
Token're
Feature activation+0.000
driving
Token driving
Feature activation+0.000
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.512
absolute
Token absolute
Feature activation+1.327
c
Token c
Feature activation+2.387
***
Token***
Feature activation+1.093
mate
Token mate
Feature activation+0.924
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
program
Token program
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.261
respected
Tokenrespected
Feature activation+0.986
public
Token public
Feature activation+2.367
servant
Token servant
Feature activation+0.722
,
Token,
Feature activation+0.438
business
Token business
Feature activation+1.572
executive
Token executive
Feature activation+0.897
,
Token,
Feature activation+1.180
self
Token self
Feature activation+0.170
-
Token-
Feature activation+0.883
described
Tokendescribed
Feature activation+1.388
âĢ
Token âĢ
Feature activation+0.235
ľ
Tokenľ
Feature activation+1.485
trans
Tokentrans
Feature activation+2.364
-
Token-
Feature activation+2.155
national
Tokennational
Feature activation+1.414
ist
Tokenist
Feature activation+1.322
âĢ
TokenâĢ
Feature activation+0.284
Ŀ
TokenĿ
Feature activation+1.294
Daniel
TokenDaniel
Feature activation+1.199
supporter
Token supporter
Feature activation+0.432
and
Token and
Feature activation+0.493
an
Token an
Feature activation+0.988
aspiring
Token aspiring
Feature activation+1.515
political
Token political
Feature activation+2.363
blogger
Token blogger
Feature activation+0.725
with
Token with
Feature activation+0.067
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
"
Token "
Feature activation+0.000

Top DFA by src position
MAX = 3.449

Bill
Token Bill
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
A
Token A
Feature activation-0.009
Top resid features:
Hall
Token Hall
Feature activation+0.046
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Fame
Token Fame
Feature activation+3.321
Top resid features:
football
Token football
Feature activation+0.181
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
wrestling
Token wrestling
Feature activation+0.004
Top resid features:
coach
Token coach
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Bill
Token Bill
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
A
Token A
Feature activation+0.003
Top resid features:
Hall
Token Hall
Feature activation+0.036
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
Fame
Token Fame
Feature activation+3.449
Top resid features:
football
Token football
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
wrestling
Token wrestling
Feature activation+0.000
Top resid features:
coach
Token coach
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
even
Token even
Feature activation-0.010
Top resid features:
though
Token though
Feature activation-0.009
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
am
Token am
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.288
Top resid features:
lifelong
Token lifelong
Feature activation+2.733
Top resid features:
off
Token off
Feature activation+0.100
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
road
Tokenroad
Feature activation+0.217
Top resid features:
cyclist
Token cyclist
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
McH
Token McH
Feature activation+0.002
Top resid features:
ale
Tokenale
Feature activation+0.002
Top resid features:
describes
Token describes
Feature activation-0.004
Top resid features:
himself
Token himself
Feature activation-0.009
Top resid features:
as
Token as
Feature activation+0.036
Top resid features:
a
Token a
Feature activation+1.564
Top resid features:
conservative
Token conservative
Feature activation+1.216
Top resid features:
gun
Token gun
Feature activation+0.242
Top resid features:
-
Token-
Feature activation+0.099
Top resid features:
t
Tokent
Feature activation+0.030
Top resid features:
otin
Tokenotin
Feature activation+0.026
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
expert
Token expert
Feature activation+0.014
Top resid features:
is
Token is
Feature activation+0.039
Top resid features:
a
Token a
Feature activation+0.292
Top resid features:
licensed
Token licensed
Feature activation+2.718
Top resid features:
medical
Token medical
Feature activation+0.050
Top resid features:
professional
Token professional
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.178
Top resid features:
he
Token he
Feature activation+0.010
Top resid features:
isn
Token isn
Feature activation-0.005
Top resid features:
't
Token't
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.115
Top resid features:
skilled
Token skilled
Feature activation+2.467
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
fast
Token fast
Feature activation+0.194
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
powerful
Token powerful
Feature activation+0.230
Top resid features:
board
Tokenboard
Feature activation+0.255
Top resid features:
er
Tokener
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.176
Top resid features:
or
Token or
Feature activation+0.230
Top resid features:
p
Token p
Feature activation+0.034
Top resid features:
ogo
Tokenogo
Feature activation+1.682
Top resid features:
-
Token-
Feature activation+0.017
Top resid features:
stick
Tokenstick
Feature activation+0.000
Top resid features:
jumper
Token jumper
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
ok
Tokenok
Feature activation+0.000
Top resid features:
lead
Token lead
Feature activation+0.032
Top resid features:
author
Token author
Feature activation-0.005
Top resid features:
has
Token has
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.263
Top resid features:
lifelong
Token lifelong
Feature activation+2.550
Top resid features:
sports
Token sports
Feature activation+0.070
Top resid features:
enthusiast
Token enthusiast
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
firm
Token firm
Feature activation+0.000
Top resid features:
believer
Token believer
Feature activation+0.000
Top resid features:
compassion
Token compassion
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
David
Token David
Feature activation-0.009
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
an
Token an
Feature activation+0.103
Top resid features:
exceptional
Token exceptional
Feature activation+1.658
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
bright
Token bright
Feature activation+0.411
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
caring
Token caring
Feature activation+0.580
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
fiscal
Token fiscal
Feature activation+0.082
Top resid features:
conservative
Token conservative
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+0.119
Top resid features:
consensus
Token consensus
Feature activation+0.740
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
building
Tokenbuilding
Feature activation+1.686
Top resid features:
former
Token former
Feature activation+0.147
Top resid features:
budget
Token budget
Feature activation+0.000
Top resid features:
chief
Token chief
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
civilians
Token civilians
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.026
Top resid features:
He
Token He
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.019
Top resid features:
a
Token a
Feature activation+0.342
Top resid features:
fearless
Token fearless
Feature activation+1.961
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
exceptional
Token exceptional
Feature activation+0.493
Top resid features:
soldier
Token soldier
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
compassion
Token compassion
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
David
Token David
Feature activation-0.007
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
an
Token an
Feature activation+0.270
Top resid features:
exceptional
Token exceptional
Feature activation+1.888
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
bright
Token bright
Feature activation+0.253
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
caring
Token caring
Feature activation+0.402
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
well
Token well
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+0.094
Top resid features:
a
Token a
Feature activation+0.238
Top resid features:
fan
Token fan
Feature activation+0.024
Top resid features:
atical
Tokenatical
Feature activation+2.092
Top resid features:
football
Token football
Feature activation+0.106
Top resid features:
fan
Token fan
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
loved
Token loved
Feature activation+0.000
Top resid features:
bl
Token bl
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.024
Top resid features:
t
Tokent
Feature activation+0.014
Top resid features:
otin
Tokenotin
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation-0.016
Top resid features:
bible
Token bible
Feature activation+1.366
Top resid features:
-
Token-
Feature activation+0.146
Top resid features:
cling
Tokencling
Feature activation+0.000
Top resid features:
in
Tokenin
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:
describes
Token describes
Feature activation-0.001
Top resid features:
himself
Token himself
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.220
Top resid features:
conservative
Token conservative
Feature activation+0.406
Top resid features:
gun
Token gun
Feature activation+1.081
Top resid features:
-
Token-
Feature activation+1.037
Top resid features:
t
Tokent
Feature activation+0.014
Top resid features:
otin
Tokenotin
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:
ale
Tokenale
Feature activation+0.002
Top resid features:
describes
Token describes
Feature activation-0.002
Top resid features:
himself
Token himself
Feature activation+0.017
Top resid features:
as
Token as
Feature activation+0.057
Top resid features:
a
Token a
Feature activation+0.389
Top resid features:
conservative
Token conservative
Feature activation+2.259
Top resid features:
gun
Token gun
Feature activation+0.059
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
otin
Tokenotin
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
're
Token're
Feature activation+0.005
Top resid features:
driving
Token driving
Feature activation+0.006
Top resid features:
like
Token like
Feature activation+0.091
Top resid features:
an
Token an
Feature activation+0.631
Top resid features:
absolute
Token absolute
Feature activation+1.987
Top resid features:
c
Token c
Feature activation+0.017
Top resid features:
***
Token***
Feature activation+0.000
Top resid features:
mate
Token mate
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:
the
Token the
Feature activation-0.000
Top resid features:
program
Token program
Feature activation-0.014
Top resid features:
as
Token as
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.144
Top resid features:
"
Token "
Feature activation+0.117
Top resid features:
respected
Tokenrespected
Feature activation+2.401
Top resid features:
public
Token public
Feature activation+0.136
Top resid features:
servant
Token servant
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
business
Token business
Feature activation+0.000
Top resid features:
executive
Token executive
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.158
Top resid features:
self
Token self
Feature activation+0.124
Top resid features:
-
Token-
Feature activation+0.116
Top resid features:
described
Tokendescribed
Feature activation+2.139
Top resid features:
âĢ
Token âĢ
Feature activation+0.012
Top resid features:
ľ
Tokenľ
Feature activation+0.117
Top resid features:
trans
Tokentrans
Feature activation+0.082
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
national
Tokennational
Feature activation+0.000
Top resid features:
Mc
Token Mc
Feature activation+0.007
Top resid features:
Daniel
TokenDaniel
Feature activation+0.033
Top resid features:
supporter
Token supporter
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.068
Top resid features:
an
Token an
Feature activation+0.166
Top resid features:
aspiring
Token aspiring
Feature activation+2.309
Top resid features:
political
Token political
Feature activation+0.065
Top resid features:
blogger
Token blogger
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:
site
Token site
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.04

Head 3: 0.58

Head 4: 0.04

Head 5: 0.07

Head 6: 0.02

Head 7: 0.05

Head 8: 0.03

Head 9: 0.02

Head 10: 0.07

Head 11: 0.02

Positive logits

enthusiast3.42

lover3.38

scholar3.22

ologist3.12

campaigner3.06

performer3.06

musician3.06

writer3.05

educator3.04

believer3.03

practitioner3.02

entrepreneur3.02

thinker3.00

historian2.99

investigator2.98

writer2.96

blogger2.94

racer2.93

proponent2.93

researcher2.90

Negative logits

partitions-2.56

residences-2.55

checkpoints-2.51

arrangements-2.51

iPads-2.42

exits-2.41

packages-2.40

apartments-2.40

assemblies-2.40

entrances-2.39

suspensions-2.39

suites-2.38

pockets-2.38

interfaces-2.36

gaps-2.35

clusters-2.34

licences-2.34

ements-2.33

ceilings-2.33

loopholes-2.32

INTERVAL 2.885 - 3.206
CONTAINS 0.000%

.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.150
of
Token of
Feature activation+0.890
Fame
Token Fame
Feature activation+1.063
football
Token football
Feature activation+3.106
and
Token and
Feature activation+0.986
wrestling
Token wrestling
Feature activation+3.119
coach
Token coach
Feature activation+0.141
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
Hall
Token Hall
Feature activation+0.150
of
Token of
Feature activation+0.890
Fame
Token Fame
Feature activation+1.063
football
Token football
Feature activation+3.106
and
Token and
Feature activation+0.986
wrestling
Token wrestling
Feature activation+3.119
coach
Token coach
Feature activation+0.141
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
am
Token am
Feature activation+0.000
a
Token a
Feature activation+0.000
lifelong
Token lifelong
Feature activation+0.497
off
Token off
Feature activation+2.068
-
Token-
Feature activation+2.196
road
Tokenroad
Feature activation+2.993
cyclist
Token cyclist
Feature activation+0.742
,
Token,
Feature activation+0.000
n
Token n
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
ic
Tokenic
Feature activation+1.307

INTERVAL 2.564 - 2.885
CONTAINS 0.001%

a
Token a
Feature activation+0.232
conservative
Token conservative
Feature activation+1.263
gun
Token gun
Feature activation+2.398
-
Token-
Feature activation+2.353
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
bible
Token bible
Feature activation+1.837
-
Token-
Feature activation+2.421
cling
Tokencling
Feature activation+1.623
skilled
Token skilled
Feature activation+0.880
,
Token,
Feature activation+1.965
fast
Token fast
Feature activation+2.161
,
Token,
Feature activation+2.020
and
Token and
Feature activation+1.620
powerful
Token powerful
Feature activation+2.718
warrior
Token warrior
Feature activation+1.030
,
Token,
Feature activation+0.029
well
Token well
Feature activation+0.125
deserving
Token deserving
Feature activation+0.000
of
Token of
Feature activation+0.000
er
Tokener
Feature activation+0.863
,
Token,
Feature activation+1.293
or
Token or
Feature activation+1.602
p
Token p
Feature activation+1.829
ogo
Tokenogo
Feature activation+1.130
-
Token-
Feature activation+2.601
stick
Tokenstick
Feature activation+2.076
jumper
Token jumper
Feature activation+1.537
(
Token (
Feature activation+0.239
ok
Tokenok
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
the
Token the
Feature activation+0.165
expert
Token expert
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.848
licensed
Token licensed
Feature activation+1.750
medical
Token medical
Feature activation+2.756
professional
Token professional
Feature activation+0.762
and
Token and
Feature activation+0.042
has
Token has
Feature activation+0.142
a
Token a
Feature activation+0.165
specialty
Token specialty
Feature activation+0.000
author
Token author
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.122
lifelong
Token lifelong
Feature activation+0.677
sports
Token sports
Feature activation+2.574
enthusiast
Token enthusiast
Feature activation+0.661
and
Token and
Feature activation+1.153
firm
Token firm
Feature activation+0.714
believer
Token believer
Feature activation+1.071
in
Token in
Feature activation+0.562

INTERVAL 2.244 - 2.564
CONTAINS 0.002%

Richard
Token Richard
Feature activation+0.000
Fleming
Token Fleming
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
accomplished
Token accomplished
Feature activation+0.572
nuclear
Token nuclear
Feature activation+2.311
card
Token card
Feature activation+2.005
iologist
Tokeniologist
Feature activation+0.403
,
Token,
Feature activation+0.000
enrolled
Token enrolled
Feature activation+0.000
26
Token 26
Feature activation+0.000
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.027
tough
Token tough
Feature activation+0.869
,
Token,
Feature activation+0.866
tough
Token tough
Feature activation+2.336
dude
Token dude
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
fought
Token fought
Feature activation+0.000
're
Token're
Feature activation+0.000
driving
Token driving
Feature activation+0.000
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.512
absolute
Token absolute
Feature activation+1.327
c
Token c
Feature activation+2.387
***
Token***
Feature activation+1.093
mate
Token mate
Feature activation+0.924
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
describes
Token describes
Feature activation+0.000
himself
Token himself
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.232
conservative
Token conservative
Feature activation+1.263
gun
Token gun
Feature activation+2.398
-
Token-
Feature activation+2.353
t
Tokent
Feature activation+2.406
otin
Tokenotin
Feature activation+2.775
âĢ
TokenâĢ
Feature activation+0.048
Ļ
TokenĻ
Feature activation+2.297
.
Token.
Feature activation+0.000
Hanson
Token Hanson
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
leading
Token leading
Feature activation+0.529
prediction
Token prediction
Feature activation+2.281
market
Token market
Feature activation+1.410
researcher
Token researcher
Feature activation+0.032
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 1.923 - 2.244
CONTAINS 0.005%

though
Token though
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
a
Token a
Feature activation+0.000
lifelong
Token lifelong
Feature activation+0.497
off
Token off
Feature activation+2.068
-
Token-
Feature activation+2.196
road
Tokenroad
Feature activation+2.993
cyclist
Token cyclist
Feature activation+0.742
,
Token,
Feature activation+0.000
n
Token n
Feature activation+0.000
-
Token-
Feature activation+0.171
year
Tokenyear
Feature activation+0.521
-
Token-
Feature activation+1.217
old
Tokenold
Feature activation+0.894
action
Token action
Feature activation+0.720
movie
Token movie
Feature activation+1.931
star
Token star
Feature activation+0.441
was
Token was
Feature activation+0.053
slapped
Token slapped
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
Trump
Token Trump
Feature activation+0.037
critic
Token critic
Feature activation+0.000
to
Token to
Feature activation+0.326
Donald
Token Donald
Feature activation+0.476
Trump
Token Trump
Feature activation+1.094
flatt
Token flatt
Feature activation+2.092
erer
Tokenerer
Feature activation+0.431
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
senator
Token senator
Feature activation+0.000
issued
Token issued
Feature activation+0.000
.
Token.
Feature activation+0.000
Madden
Token Madden
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
admitted
Token admitted
Feature activation+0.380
child
Token child
Feature activation+2.104
m
Token m
Feature activation+2.203
olester
Tokenolester
Feature activation+0.279
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
reass
Token reass
Feature activation+0.000
were
Token were
Feature activation+0.000
a
Token a
Feature activation+0.000
Titus
Token Titus
Feature activation+1.519
And
Token And
Feature activation+0.393
ronic
Tokenronic
Feature activation+0.352
us
Tokenus
Feature activation+1.937
fan
Token fan
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
or
Token or
Feature activation+0.000
near
Token near
Feature activation+0.000

INTERVAL 1.603 - 1.923
CONTAINS 0.013%

Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
fellow
Token fellow
Feature activation+0.105
AM
Token AM
Feature activation+0.276
VA
TokenVA
Feature activation+1.743
members
Token members
Feature activation+0.133
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
-
Token-
Feature activation+2.421
cling
Tokencling
Feature activation+1.623
in
Tokenin
Feature activation+1.402
âĢ
TokenâĢ
Feature activation+0.145
Ļ
TokenĻ
Feature activation+2.243
literary
Token literary
Feature activation+1.671
assault
Token assault
Feature activation+1.275
dude
Token dude
Feature activation+0.659
who
Token who
Feature activation+0.379
enjoys
Token enjoys
Feature activation+0.000
finding
Token finding
Feature activation+0.000
-
Token-
Feature activation+1.044
old
Tokenold
Feature activation+0.498
former
Token former
Feature activation+1.619
England
Token England
Feature activation+1.377
and
Token and
Feature activation+1.937
Arsenal
Token Arsenal
Feature activation+1.621
defender
Token defender
Feature activation+0.230
appeared
Token appeared
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
programme
Token programme
Feature activation+0.000
moderate
Token moderate
Feature activation+0.509
,
Token,
Feature activation+0.578
fiscal
Token fiscal
Feature activation+1.118
conservative
Token conservative
Feature activation+0.525
,
Token,
Feature activation+0.840
consensus
Token consensus
Feature activation+1.703
-
Token-
Feature activation+2.352
building
Tokenbuilding
Feature activation+2.148
former
Token former
Feature activation+2.545
budget
Token budget
Feature activation+2.004
chief
Token chief
Feature activation+0.901
suddenly
Token suddenly
Feature activation+0.000
become
Token become
Feature activation+0.000
an
Token an
Feature activation+0.000
A
Token A
Feature activation+1.061
-
Token-
Feature activation+1.040
list
Tokenlist
Feature activation+1.918
star
Token star
Feature activation+0.126
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 1.282 - 1.603
CONTAINS 0.032%

at
Tokenat
Feature activation+0.387
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
others
Token others
Feature activation+0.052
a
Token a
Feature activation+0.397
tor
Token tor
Feature activation+1.476
mented
Tokenmented
Feature activation+1.497
,
Token,
Feature activation+1.243
disabled
Token disabled
Feature activation+2.154
survivor
Token survivor
Feature activation+0.779
.
Token.
Feature activation+0.000
private
Tokenprivate
Feature activation+0.367
er
Tokener
Feature activation+0.000
)
Token)
Feature activation+0.629
and
Token and
Feature activation+0.947
all
Token all
Feature activation+1.358
-
Token-
Feature activation+1.328
around
Tokenaround
Feature activation+0.905
badass
Token badass
Feature activation+0.938
,
Token,
Feature activation+0.000
talking
Token talking
Feature activation+0.210
with
Token with
Feature activation+0.009
Bon
Token Bon
Feature activation+0.000
as
Tokenas
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.001
ixties
Tokenixties
Feature activation+0.237
"
Token "
Feature activation+1.528
It
TokenIt
Feature activation+0.685
girl
Token girl
Feature activation+0.555
"
Token"
Feature activation+1.763
Lady
Token Lady
Feature activation+0.543
Mary
Token Mary
Feature activation+0.225
p
Tokenp
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
:
Token:
Feature activation+0.333
Food
Token Food
Feature activation+0.690
critic
Token critic
Feature activation+0.137
/
Token/
Feature activation+1.311
rest
Tokenrest
Feature activation+1.285
aur
Tokenaur
Feature activation+1.537
ateur
Tokenateur
Feature activation+0.000
Z
Token Z
Feature activation+0.108
esty
Tokenesty
Feature activation+0.000
Kaine
Token Kaine
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.213
ľ
Tokenľ
Feature activation+0.776
eth
Tokeneth
Feature activation+1.334
ically
Tokenically
Feature activation+0.687
challenged
Token challenged
Feature activation+0.763
insider
Token insider
Feature activation+0.869
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.962 - 1.282
CONTAINS 0.064%

ison
Tokenison
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
four
Token four
Feature activation+0.324
-
Token-
Feature activation+0.593
star
Tokenstar
Feature activation+1.100
,
Token,
Feature activation+0.776
pro
Token pro
Feature activation+1.540
-
Token-
Feature activation+0.807
style
Tokenstyle
Feature activation+2.023
quarterback
Token quarterback
Feature activation+0.858
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.012
s
Tokens
Feature activation+0.350
most
Token most
Feature activation+0.213
famous
Token famous
Feature activation+1.054
atheist
Token atheist
Feature activation+1.175
,
Token,
Feature activation+0.369
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.149
chief
Token chief
Feature activation+0.102
law
Token law
Feature activation+1.158
-
Token-
Feature activation+1.222
enforcement
Tokenenforcement
Feature activation+1.128
officer
Token officer
Feature activation+0.000
.
Token.
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
announced
Token announced
Feature activation+0.000
his
Token his
Feature activation+0.000
skills
Token skills
Feature activation+0.000
as
Token as
Feature activation+0.642
both
Token both
Feature activation+1.296
a
Token a
Feature activation+1.396
journalist
Token journalist
Feature activation+0.976
and
Token and
Feature activation+1.019
a
Token a
Feature activation+1.495
fiction
Token fiction
Feature activation+1.719
writer
Token writer
Feature activation+0.815
,
Token,
Feature activation+0.000
recently
Token recently
Feature activation+0.000
a
Token a
Feature activation+0.000
Dud
Token Dud
Feature activation+0.279
amel
Tokenamel
Feature activation+1.660
Conduct
Token Conduct
Feature activation+0.614
ing
Tokening
Feature activation+1.148
Fellow
Token Fellow
Feature activation+0.391
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000

INTERVAL 0.641 - 0.962
CONTAINS 0.133%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Clark
Token Clark
Feature activation+0.043
ston
Tokenston
Feature activation+0.705
resident
Token resident
Feature activation+0.107
and
Token and
Feature activation+0.689
Romeo
Token Romeo
Feature activation+1.578
native
Token native
Feature activation+0.000
again
Token again
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
should
Token should
Feature activation+0.000
find
Token find
Feature activation+0.000
another
Token another
Feature activation+0.000
bre
Token bre
Feature activation+0.847
eder
Tokeneder
Feature activation+0.000
instead
Token instead
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Dec
TokenDec
Feature activation+0.000
student
Token student
Feature activation+0.992
,
Token,
Feature activation+0.328
minister
Token minister
Feature activation+0.947
,
Token,
Feature activation+0.800
professor
Token professor
Feature activation+0.744
,
Token,
Feature activation+0.744
author
Token author
Feature activation+0.741
,
Token,
Feature activation+0.894
and
Token and
Feature activation+1.192
speaker
Token speaker
Feature activation+0.745
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
unt
Token unt
Feature activation+0.000
r
Tokenr
Feature activation+0.821
uth
Tokenuth
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
,
Token,
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
doubled
Token doubled
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
which
Token which
Feature activation+0.000
a
Token a
Feature activation+0.000
ninth
Token ninth
Feature activation+0.229
-
Token-
Feature activation+0.660
gr
Tokengr
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
charged
Token charged
Feature activation+0.000

INTERVAL 0.321 - 0.641
CONTAINS 0.294%

)
Token)
Feature activation+0.000
Prof
TokenProf
Feature activation+0.000
ession
Tokenession
Feature activation+0.000
:
Token:
Feature activation+0.553
Fashion
Token Fashion
Feature activation+1.293
photographer
Token photographer
Feature activation+0.324
Special
TokenSpecial
Feature activation+0.000
Some
Token Some
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
:
Token:
Feature activation+0.333
will
Token will
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Am
TokenAm
Feature activation+0.000
ateur
Tokenateur
Feature activation+0.000
car
Token car
Feature activation+0.381
rac
Token rac
Feature activation+0.527
ers
Tokeners
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
shut
Token shut
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
22
Token 22
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
cake
Token cake
Feature activation+1.415
shop
Token shop
Feature activation+0.407
employee
Token employee
Feature activation+0.000
from
Token from
Feature activation+0.003
A
Token A
Feature activation+0.000
ts
Tokents
Feature activation+0.000
ugi
Tokenugi
Feature activation+0.000
rewarding
Token rewarding
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+0.000
an
Token an
Feature activation+0.000
evident
Token evident
Feature activation+0.405
ial
Tokenial
Feature activation+0.452
psychic
Token psychic
Feature activation+0.739
medium
Token medium
Feature activation+0.124
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Follow
TokenFollow
Feature activation+0.000
@
Token @
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
_
Token_
Feature activation+0.506
bon
Tokenbon
Feature activation+0.333
n
Tokenn
Feature activation+0.129
fire
Tokenfire
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Represent
TokenRepresent
Feature activation+0.000

INTERVAL 0.000 - 0.321
CONTAINS 99.456%

G
Token G
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
death
Token death
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
equally
Token equally
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
basis
Token basis
Feature activation+0.000
.
Token.
Feature activation+0.000
Frequ
Token Frequ
Feature activation+0.000
ently
Tokenently
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Unity
Token Unity
Feature activation+0.000
launcher
Token launcher
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
later
Token later
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
Turkey
Token Turkey
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
decade
Token decade
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
lobby
Token lobby
Feature activation+0.000
site
Token site
Feature activation+0.000
and
Token and
Feature activation+0.000
see
Token see
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
get
Token get
Feature activation+0.000
any
Token any
Feature activation+0.000
hits
Token hits
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.124
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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.124
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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.124
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
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.124
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
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+0.124
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+0.124
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.124
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+0.124
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 H9.3: (feature 9240)

TOP ACTIVATIONS
MAX = 5.727

to
Token to
Feature activation+0.594
talk
Token talk
Feature activation+0.639
to
Token to
Feature activation+0.304
them
Token them
Feature activation+3.962
about
Token about
Feature activation+0.916
it
Token it
Feature activation+5.606
.
Token.
Feature activation+3.925
Here
Token Here
Feature activation+0.503
's
Token's
Feature activation+0.000
what
Token what
Feature activation+0.318
we
Token we
Feature activation+0.000
become
Token become
Feature activation+0.263
a
Token a
Feature activation+0.071
parent
Token parent
Feature activation+4.289
against
Token against
Feature activation+0.594
her
Token her
Feature activation+0.164
will
Token will
Feature activation+5.544
or
Token or
Feature activation+0.000
question
Token question
Feature activation+0.379
her
Token her
Feature activation+0.313
decisions
Token decisions
Feature activation+4.920
about
Token about
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+5.308
all
Token all
Feature activation+0.269
the
Token the
Feature activation+0.125
time
Token time
Feature activation+5.727
and
Token and
Feature activation+2.032
flip
Token flip
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+3.155
and
Token and
Feature activation+1.316
really
Token really
Feature activation+0.521
enjoyed
Token enjoyed
Feature activation+2.571
it
Token it
Feature activation+5.244
,"
Token,"
Feature activation+0.000
Bie
Token Bie
Feature activation+0.000
le
Tokenle
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
said
Token said
Feature activation+0.000
flavour
Token flavour
Feature activation+0.000
as
Token as
Feature activation+0.426
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
nutritional
Token nutritional
Feature activation+0.000
value
Token value
Feature activation+5.182
.
Token.
Feature activation+3.222
Dis
Token Dis
Feature activation+0.000
hes
Tokenhes
Feature activation+0.043
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+2.261
to
Token to
Feature activation+0.533
get
Token get
Feature activation+0.953
done
Token done
Feature activation+3.260
is
Token is
Feature activation+1.123
formidable
Token formidable
Feature activation+5.109
,"
Token,"
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
their
Token their
Feature activation+0.258
children
Token children
Feature activation+3.395
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
see
Token see
Feature activation+0.000
fit
Token fit
Feature activation+5.108
,
Token,
Feature activation+2.559
except
Token except
Feature activation+0.000
when
Token when
Feature activation+0.296
that
Token that
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.738
that
Token that
Feature activation+0.521
's
Token's
Feature activation+0.092
not
Token not
Feature activation+0.552
objectively
Token objectively
Feature activation+0.000
true
Token true
Feature activation+5.102
,"
Token,"
Feature activation+0.811
King
Token King
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
the
Token the
Feature activation+0.613
track
Token track
Feature activation+0.105
record
Token record
Feature activation+1.126
speaks
Token speaks
Feature activation+0.237
for
Token for
Feature activation+0.000
itself
Token itself
Feature activation+4.989
,"
Token,"
Feature activation+0.000
T
Token T
Feature activation+0.000
k
Tokenk
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
her
Token her
Feature activation+0.164
will
Token will
Feature activation+5.544
or
Token or
Feature activation+0.000
question
Token question
Feature activation+0.379
her
Token her
Feature activation+0.313
decisions
Token decisions
Feature activation+4.920
about
Token about
Feature activation+0.000
pregnancy
Token pregnancy
Feature activation+4.125
.
Token.
Feature activation+3.149
We
Token We
Feature activation+0.121
don
Token don
Feature activation+0.000
For
TokenFor
Feature activation+0.000
rest
Tokenrest
Feature activation+0.912
was
Token was
Feature activation+1.691
big
Token big
Feature activation+3.425
back
Token back
Feature activation+2.026
then
Token then
Feature activation+4.906
,
Token,
Feature activation+1.473
for
Token for
Feature activation+0.469
that
Token that
Feature activation+0.000
era
Token era
Feature activation+4.240
,"
Token,"
Feature activation+0.000
organ
Token organ
Feature activation+0.000
ics
Tokenics
Feature activation+3.139
in
Token in
Feature activation+1.276
the
Token the
Feature activation+0.267
processing
Token processing
Feature activation+0.404
facility
Token facility
Feature activation+4.882
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000
rec
Tokenrec
Feature activation+0.000
imagined
Token imagined
Feature activation+2.080
that
Token that
Feature activation+1.570
this
Token this
Feature activation+0.652
would
Token would
Feature activation+2.054
touch
Token touch
Feature activation+2.128
anyone
Token anyone
Feature activation+4.812
high
Token high
Feature activation+1.541
up
Token up
Feature activation+3.007
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Papa
Token Papa
Feature activation+0.000
from
Token from
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
trans
Tokentrans
Feature activation+0.000
gender
Tokengender
Feature activation+0.168
employees
Token employees
Feature activation+4.778
,"
Token,"
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.771
the
Token the
Feature activation+0.346
way
Token way
Feature activation+1.850
the
Token the
Feature activation+0.538
board
Token board
Feature activation+0.880
operates
Token operates
Feature activation+4.771
,"
Token,"
Feature activation+0.012
said
Token said
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
Green
Token Green
Feature activation+0.000
berger
Tokenberger
Feature activation+0.000
the
Token the
Feature activation+0.000
cities
Token cities
Feature activation+1.292
and
Token and
Feature activation+0.450
became
Token became
Feature activation+0.229
very
Token very
Feature activation+0.000
popular
Token popular
Feature activation+4.770
with
Token with
Feature activation+0.903
entrepreneurs
Token entrepreneurs
Feature activation+3.924
.
Token.
Feature activation+3.183
Many
Token Many
Feature activation+0.000
converts
Token converts
Feature activation+0.000
the
Token the
Feature activation+0.000
Papa
Token Papa
Feature activation+0.000
John
Token John
Feature activation+0.812
's
Token's
Feature activation+0.283
corporate
Token corporate
Feature activation+0.444
office
Token office
Feature activation+4.745
,
Token,
Feature activation+2.219
let
Token let
Feature activation+0.000
alone
Token alone
Feature activation+0.261
,
Token,
Feature activation+0.584
John
Token John
Feature activation+0.057
depends
Token depends
Feature activation+3.842
on
Token on
Feature activation+0.869
how
Token how
Feature activation+1.054
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
done
Token done
Feature activation+4.700
,"
Token,"
Feature activation+0.000
Giuliani
Token Giuliani
Feature activation+0.000
said
Token said
Feature activation+0.000
when
Token when
Feature activation+0.000
asked
Token asked
Feature activation+0.000
"
Token"
Feature activation+0.288
They
TokenThey
Feature activation+1.355
liked
Token liked
Feature activation+2.945
what
Token what
Feature activation+2.441
they
Token they
Feature activation+0.000
saw
Token saw
Feature activation+4.678
,"
Token,"
Feature activation+0.000
Robinson
Token Robinson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
end
Token end
Feature activation+1.381
of
Token of
Feature activation+0.545
the
Token the
Feature activation+0.179
National
Token National
Feature activation+0.042
Health
Token Health
Feature activation+0.000
Service
Token Service
Feature activation+4.596
,"
Token,"
Feature activation+0.000
declared
Token declared
Feature activation+0.000
a
Token a
Feature activation+0.000
confidential
Token confidential
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000

Top DFA by src position
MAX = 6.096

in
Token in
Feature activation+0.000
Top resid features:
January
Token January
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
"
Token"
Feature activation+6.092
Top resid features:
I
TokenI
Feature activation+0.005
Top resid features:
haven
Token haven
Feature activation+0.002
Top resid features:
't
Token't
Feature activation-0.002
Top resid features:
looked
Token looked
Feature activation+0.004
Top resid features:
at
Token at
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
bill
Token bill
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
"
Token"
Feature activation+6.096
Top resid features:
We
TokenWe
Feature activation+0.014
Top resid features:
should
Token should
Feature activation+0.005
Top resid features:
never
Token never
Feature activation-0.016
Top resid features:
force
Token force
Feature activation-0.025
Top resid features:
any
Token any
Feature activation+0.004
Top resid features:
Des
Token Des
Feature activation-0.001
Top resid features:
Moines
Token Moines
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
"
Token"
Feature activation+5.779
Top resid features:
A
TokenA
Feature activation+0.011
Top resid features:
lot
Token lot
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
young
Token young
Feature activation-0.001
Top resid features:
people
Token people
Feature activation+0.006
Top resid features:
T
TokenT
Feature activation+0.000
Top resid features:
Stadium
Token Stadium
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
"
Token"
Feature activation+5.777
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
kids
Token kids
Feature activation+0.006
Top resid features:
saw
Token saw
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
uniforms
Token uniforms
Feature activation+0.004
Top resid features:
specifically
Token specifically
Feature activation-0.000
Top resid features:
mentioned
Token mentioned
Feature activation+0.000
Top resid features:
its
Token its
Feature activation-0.000
Top resid features:
vegetarian
Token vegetarian
Feature activation-0.001
Top resid features:
fare
Token fare
Feature activation-0.002
Top resid features:
."
Token."
Feature activation+5.664
Top resid features:
Though
TokenThough
Feature activation+0.007
Top resid features:
meat
Token meat
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
feature
Token feature
Feature activation+0.001
Top resid features:
extend
Token extend
Feature activation+0.001
Top resid features:
further
Token further
Feature activation+0.002
Top resid features:
financial
Token financial
Feature activation+0.001
Top resid features:
support
Token support
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.066
Top resid features:
"
Token "
Feature activation+5.766
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
task
Token task
Feature activation+0.012
Top resid features:
at
Token at
Feature activation-0.006
Top resid features:
hand
Token hand
Feature activation-0.006
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
child
Token child
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
"
Token"
Feature activation+5.607
Top resid features:
Obviously
TokenObviously
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
parents
Token parents
Feature activation+0.038
Top resid features:
are
Token are
Feature activation+0.023
Top resid features:
entitled
Token entitled
Feature activation+0.006
Top resid features:
than
Token than
Feature activation-0.001
Top resid features:
others
Token others
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.252
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.082
Top resid features:
"
Token"
Feature activation+5.394
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
idea
Token idea
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
multicultural
Token multicultural
Feature activation-0.005
Top resid features:
ism
Tokenism
Feature activation-0.003
Top resid features:
Hunter
Token Hunter
Feature activation-0.004
Top resid features:
instead
Token instead
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
"
Token"
Feature activation+5.553
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
talked
Token talked
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
lot
Token lot
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bill
Token bill
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
"
Token"
Feature activation+5.401
Top resid features:
We
TokenWe
Feature activation+0.025
Top resid features:
should
Token should
Feature activation+0.004
Top resid features:
never
Token never
Feature activation+0.006
Top resid features:
force
Token force
Feature activation-0.007
Top resid features:
any
Token any
Feature activation+0.004
Top resid features:
imposing
Token imposing
Feature activation-0.005
Top resid features:
figure
Token figure
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.077
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
"
Token"
Feature activation+5.463
Top resid features:
For
TokenFor
Feature activation+0.003
Top resid features:
rest
Tokenrest
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.031
Top resid features:
big
Token big
Feature activation+0.060
Top resid features:
back
Token back
Feature activation+0.018
Top resid features:
foot
Tokenfoot
Feature activation-0.000
Top resid features:
building
Token building
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
"
Token"
Feature activation+5.306
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
roof
Token roof
Feature activation-0.001
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
hold
Token hold
Feature activation+0.000
Top resid features:
CEO
Token CEO
Feature activation-0.004
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
unexpected
Token unexpected
Feature activation-0.000
Top resid features:
appearance
Token appearance
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+5.356
Top resid features:
We
TokenWe
Feature activation+0.006
Top resid features:
never
Token never
Feature activation+0.002
Top resid features:
once
Token once
Feature activation+0.001
Top resid features:
imagined
Token imagined
Feature activation+0.036
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
law
Token law
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.083
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
"
Token"
Feature activation+5.126
Top resid features:
North
TokenNorth
Feature activation+0.012
Top resid features:
Carolina
Token Carolina
Feature activation+0.014
Top resid features:
does
Token does
Feature activation+0.008
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
treat
Token treat
Feature activation-0.008
Top resid features:
Lam
Token Lam
Feature activation+0.001
Top resid features:
one
Tokenone
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
"
Token"
Feature activation+5.429
Top resid features:
This
TokenThis
Feature activation+0.003
Top resid features:
audit
Token audit
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
an
Token an
Feature activation+0.005
Top resid features:
A
Token A
Feature activation+0.002
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
stairs
Token stairs
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
"
Token"
Feature activation+5.316
Top resid features:
It
TokenIt
Feature activation+0.002
Top resid features:
moved
Token moved
Feature activation+0.002
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
largely
Token largely
Feature activation+0.000
Top resid features:
CEO
Token CEO
Feature activation-0.003
Top resid features:
making
Token making
Feature activation-0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
unexpected
Token unexpected
Feature activation-0.001
Top resid features:
appearance
Token appearance
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+5.268
Top resid features:
We
TokenWe
Feature activation+0.007
Top resid features:
never
Token never
Feature activation-0.000
Top resid features:
once
Token once
Feature activation-0.001
Top resid features:
imagined
Token imagined
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
drowning
Token drowning
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
"
Token"
Feature activation+5.212
Top resid features:
It
TokenIt
Feature activation+0.028
Top resid features:
depends
Token depends
Feature activation+0.024
Top resid features:
on
Token on
Feature activation+0.015
Top resid features:
how
Token how
Feature activation+0.012
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
recent
Token recent
Feature activation-0.004
Top resid features:
development
Token development
Feature activation-0.016
Top resid features:
camp
Token camp
Feature activation-0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
"
Token"
Feature activation+5.470
Top resid features:
They
TokenThey
Feature activation+0.038
Top resid features:
liked
Token liked
Feature activation+0.052
Top resid features:
what
Token what
Feature activation+0.011
Top resid features:
they
Token they
Feature activation+0.018
Top resid features:
saw
Token saw
Feature activation+0.028
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
other
Token other
Feature activation+0.001
Top resid features:
public
Token public
Feature activation-0.000
Top resid features:
services
Token services
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
"
Token "
Feature activation+5.133
Top resid features:
This
TokenThis
Feature activation+0.014
Top resid features:
would
Token would
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
course
Token course
Feature activation-0.007
Top resid features:
mean
Token mean
Feature activation-0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.57

Head 4: 0.03

Head 5: 0.08

Head 6: 0.03

Head 7: 0.05

Head 8: 0.02

Head 9: 0.02

Head 10: 0.09

Head 11: 0.04

Positive logits

,"5.64

),"5.09

.,"4.92

,''4.74

,"4.62

"),4.42

,'"4.19

)",4.08

?",4.00

",3.81

',"3.75

!",3.49

")3.20

","3.02

],"3.01

"],2.85

?"2.84

),2.83

,'2.83

!),2.81

Negative logits

'>-2.91

>.-2.62

••-2.52

ゴン-2.51

].-2.26

NetMessage-2.20

}.-2.17

-2.15

](-2.12

quished-2.06

>>>>>>>>-2.04

].-2.04

Oracle-2.03

================-1.98

?]-1.96

APTER-1.91

***-1.91

.]-1.90

***-1.88

]."-1.87

INTERVAL 5.154 - 5.727
CONTAINS 0.001%

become
Token become
Feature activation+0.263
a
Token a
Feature activation+0.071
parent
Token parent
Feature activation+4.289
against
Token against
Feature activation+0.594
her
Token her
Feature activation+0.164
will
Token will
Feature activation+5.544
or
Token or
Feature activation+0.000
question
Token question
Feature activation+0.379
her
Token her
Feature activation+0.313
decisions
Token decisions
Feature activation+4.920
about
Token about
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+5.308
all
Token all
Feature activation+0.269
the
Token the
Feature activation+0.125
time
Token time
Feature activation+5.727
and
Token and
Feature activation+2.032
flip
Token flip
Feature activation+0.000
to
Token to
Feature activation+0.594
talk
Token talk
Feature activation+0.639
to
Token to
Feature activation+0.304
them
Token them
Feature activation+3.962
about
Token about
Feature activation+0.916
it
Token it
Feature activation+5.606
.
Token.
Feature activation+3.925
Here
Token Here
Feature activation+0.503
's
Token's
Feature activation+0.000
what
Token what
Feature activation+0.318
we
Token we
Feature activation+0.000
flavour
Token flavour
Feature activation+0.000
as
Token as
Feature activation+0.426
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
nutritional
Token nutritional
Feature activation+0.000
value
Token value
Feature activation+5.182
.
Token.
Feature activation+3.222
Dis
Token Dis
Feature activation+0.000
hes
Tokenhes
Feature activation+0.043
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+3.155
and
Token and
Feature activation+1.316
really
Token really
Feature activation+0.521
enjoyed
Token enjoyed
Feature activation+2.571
it
Token it
Feature activation+5.244
,"
Token,"
Feature activation+0.000
Bie
Token Bie
Feature activation+0.000
le
Tokenle
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 4.581 - 5.154
CONTAINS 0.002%

of
Token of
Feature activation+0.771
the
Token the
Feature activation+0.346
way
Token way
Feature activation+1.850
the
Token the
Feature activation+0.538
board
Token board
Feature activation+0.880
operates
Token operates
Feature activation+4.771
,"
Token,"
Feature activation+0.012
said
Token said
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
Green
Token Green
Feature activation+0.000
berger
Tokenberger
Feature activation+0.000
need
Token need
Feature activation+2.261
to
Token to
Feature activation+0.533
get
Token get
Feature activation+0.953
done
Token done
Feature activation+3.260
is
Token is
Feature activation+1.123
formidable
Token formidable
Feature activation+5.109
,"
Token,"
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
Chase
Token Chase
Feature activation+0.000
debit
Token debit
Feature activation+0.000
card
Token card
Feature activation+4.590
,"
Token,"
Feature activation+0.000
Detective
Token Detective
Feature activation+0.000
Joshua
Token Joshua
Feature activation+0.000
Web
Token Web
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
the
Token the
Feature activation+0.000
Papa
Token Papa
Feature activation+0.000
John
Token John
Feature activation+0.812
's
Token's
Feature activation+0.283
corporate
Token corporate
Feature activation+0.444
office
Token office
Feature activation+4.745
,
Token,
Feature activation+2.219
let
Token let
Feature activation+0.000
alone
Token alone
Feature activation+0.261
,
Token,
Feature activation+0.584
John
Token John
Feature activation+0.057
depends
Token depends
Feature activation+3.842
on
Token on
Feature activation+0.869
how
Token how
Feature activation+1.054
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
done
Token done
Feature activation+4.700
,"
Token,"
Feature activation+0.000
Giuliani
Token Giuliani
Feature activation+0.000
said
Token said
Feature activation+0.000
when
Token when
Feature activation+0.000
asked
Token asked
Feature activation+0.000

INTERVAL 4.009 - 4.581
CONTAINS 0.006%

turbines
Token turbines
Feature activation+2.804
and
Token and
Feature activation+0.000
near
Token near
Feature activation+0.000
urban
Token urban
Feature activation+0.000
load
Token load
Feature activation+0.000
centers
Token centers
Feature activation+4.022
like
Token like
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
and
Token and
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+1.299
the
Token the
Feature activation+0.000
things
Token things
Feature activation+0.165
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
fighting
Token fighting
Feature activation+1.236
for
Token for
Feature activation+4.096
.
Token.
Feature activation+2.945
Please
Token Please
Feature activation+0.099
pray
Token pray
Feature activation+0.107
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.869
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
number
Token number
Feature activation+0.463
of
Token of
Feature activation+0.000
civilian
Token civilian
Feature activation+0.000
casualties
Token casualties
Feature activation+4.247
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
have
Token have
Feature activation+0.529
occurred
Token occurred
Feature activation+3.205
at
Token at
Feature activation+0.924
around
Token around
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+4.353
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
Insp
Token Insp
Feature activation+0.000
Alan
Token Alan
Feature activation+0.000
but
Token but
Feature activation+2.361
apparently
Token apparently
Feature activation+0.398
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.069
not
Token not
Feature activation+3.562
.
Token.
Feature activation+4.385
It
Token It
Feature activation+0.737
must
Token must
Feature activation+0.005
have
Token have
Feature activation+0.227
been
Token been
Feature activation+0.164
really
Token really
Feature activation+0.000

INTERVAL 3.436 - 4.009
CONTAINS 0.013%

"
Token"
Feature activation+0.000
These
TokenThese
Feature activation+0.289
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.056
sentient
Token sentient
Feature activation+0.403
beings
Token beings
Feature activation+3.516
.
Token.
Feature activation+2.072
I
Token I
Feature activation+0.166
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.662
want
Token want
Feature activation+0.531
the
Token the
Feature activation+0.260
scenes
Token scenes
Feature activation+2.361
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+1.737
sure
Token sure
Feature activation+3.550
he
Token he
Feature activation+0.000
wanted
Token wanted
Feature activation+1.687
it
Token it
Feature activation+3.933
,"
Token,"
Feature activation+0.000
added
Token added
Feature activation+0.000
I
Token I
Feature activation+0.729
knew
Token knew
Feature activation+1.700
there
Token there
Feature activation+0.293
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
chance
Token chance
Feature activation+3.871
to
Token to
Feature activation+0.000
score
Token score
Feature activation+1.166
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+2.933
of
Token of
Feature activation+0.000
,
Token,
Feature activation+1.895
but
Token but
Feature activation+2.361
apparently
Token apparently
Feature activation+0.398
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.069
not
Token not
Feature activation+3.562
.
Token.
Feature activation+4.385
It
Token It
Feature activation+0.737
must
Token must
Feature activation+0.005
have
Token have
Feature activation+0.227
been
Token been
Feature activation+0.164
a
Token a
Feature activation+0.450
l
Token l
Feature activation+0.000
oo
Tokenoo
Feature activation+0.673
oot
Tokenoot
Feature activation+1.223
of
Token of
Feature activation+0.608
fun
Token fun
Feature activation+3.573
!"
Token!"
Feature activation+0.000
Mend
Token Mend
Feature activation+0.000
o
Tokeno
Feature activation+0.000
za
Tokenza
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000

INTERVAL 2.863 - 3.436
CONTAINS 0.023%

the
Token the
Feature activation+0.000
budget
Token budget
Feature activation+1.745
ed
Tokened
Feature activation+0.000
trend
Token trend
Feature activation+0.729
over
Token over
Feature activation+0.000
time
Token time
Feature activation+2.997
,"
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
a
Token a
Feature activation+0.000
facade
Token facade
Feature activation+3.318
of
Token of
Feature activation+0.000
unity
Token unity
Feature activation+2.948
to
Token to
Feature activation+0.844
their
Token their
Feature activation+0.241
people
Token people
Feature activation+3.257
,"
Token,"
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
al
Tokenal
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
benefited
Token benefited
Feature activation+0.794
enormously
Token enormously
Feature activation+2.402
from
Token from
Feature activation+0.177
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
order
Token order
Feature activation+3.083
that
Token that
Feature activation+0.440
we
Token we
Feature activation+0.000
helped
Token helped
Feature activation+0.000
build
Token build
Feature activation+3.753
together
Token together
Feature activation+2.671
president
Token president
Feature activation+0.795
,
Token,
Feature activation+0.148
could
Token could
Feature activation+0.000
work
Token work
Feature activation+0.456
very
Token very
Feature activation+0.000
well
Token well
Feature activation+3.089
together
Token together
Feature activation+3.076
,
Token,
Feature activation+0.784
providing
Token providing
Feature activation+0.000
much
Token much
Feature activation+0.000
-
Token-
Feature activation+0.000
is
Token is
Feature activation+0.218
how
Token how
Feature activation+0.445
we
Token we
Feature activation+0.476
will
Token will
Feature activation+0.609
be
Token be
Feature activation+0.832
victorious
Token victorious
Feature activation+3.185
!"
Token!"
Feature activation+0.000
screamed
Token screamed
Feature activation+0.000
the
Token the
Feature activation+0.000
tabloid
Token tabloid
Feature activation+0.000
T
Token T
Feature activation+0.000

INTERVAL 2.291 - 2.863
CONTAINS 0.036%

it
Token it
Feature activation+0.714
will
Token will
Feature activation+0.000
always
Token always
Feature activation+0.000
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+2.843
like
Token like
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Dana
Token Dana
Feature activation+0.000
We
TokenWe
Feature activation+0.981
want
Token want
Feature activation+1.166
to
Token to
Feature activation+0.743
decide
Token decide
Feature activation+0.965
our
Token our
Feature activation+0.322
future
Token future
Feature activation+2.603
.
Token.
Feature activation+2.902
We
Token We
Feature activation+1.168
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.601
understand
Token understand
Feature activation+1.069
But
TokenBut
Feature activation+2.837
everybody
Token everybody
Feature activation+1.201
who
Token who
Feature activation+0.268
was
Token was
Feature activation+0.186
there
Token there
Feature activation+1.843
knows
Token knows
Feature activation+2.723
that
Token that
Feature activation+2.623
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.014
an
Token an
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+2.061
Bureau
Token Bureau
Feature activation+0.000
of
Token of
Feature activation+0.000
Pr
Token Pr
Feature activation+0.000
isons
Tokenisons
Feature activation+2.476
because
Token because
Feature activation+1.414
the
Token the
Feature activation+0.088
other
Token other
Feature activation+0.000
convictions
Token convictions
Feature activation+0.865
likely
Token likely
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
f
Token f
Feature activation+0.000
isc
Tokenisc
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
conservative
Token conservative
Feature activation+2.690
,"
Token,"
Feature activation+0.407
Cur
Token Cur
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
o
Tokeno
Feature activation+0.000
explained
Token explained
Feature activation+0.000

INTERVAL 1.718 - 2.291
CONTAINS 0.045%

Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.441
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
belief
Token belief
Feature activation+2.288
,
Token,
Feature activation+0.000
supported
Token supported
Feature activation+0.106
by
Token by
Feature activation+0.467
the
Token the
Feature activation+0.179
medical
Token medical
Feature activation+0.000
to
Token to
Feature activation+0.097
check
Token check
Feature activation+0.116
status
Token status
Feature activation+0.307
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
films
Token films
Feature activation+1.811
online
Token online
Feature activation+1.909
.
Token.
Feature activation+0.814
We
Token We
Feature activation+0.000
also
Token also
Feature activation+0.000
plan
Token plan
Feature activation+0.000
re
Tokenre
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
candid
Token candid
Feature activation+0.000
conversation
Token conversation
Feature activation+1.829
now
Token now
Feature activation+1.557
on
Token on
Feature activation+0.000
why
Token why
Feature activation+0.490
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
visited
Token visited
Feature activation+0.101
this
Token this
Feature activation+0.000
part
Token part
Feature activation+0.768
of
Token of
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.738
.
Token.
Feature activation+1.791
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
fierce
Token fierce
Feature activation+0.251
.
Token.
Feature activation+0.700
They
Token They
Feature activation+0.000
duration
Token duration
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
incident
Token incident
Feature activation+1.951
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
EPA
TokenEPA
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 1.145 - 1.718
CONTAINS 0.087%

time
Token time
Feature activation+2.494
,
Token,
Feature activation+0.296
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
felt
Token felt
Feature activation+0.000
great
Token great
Feature activation+1.218
and
Token and
Feature activation+0.201
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
religion
Token religion
Feature activation+0.586
,
Token,
Feature activation+0.377
came
Token came
Feature activation+0.278
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
cities
Token cities
Feature activation+1.292
and
Token and
Feature activation+0.450
became
Token became
Feature activation+0.229
very
Token very
Feature activation+0.000
popular
Token popular
Feature activation+4.770
with
Token with
Feature activation+0.903
actually
Token actually
Feature activation+0.000
did
Token did
Feature activation+0.835
get
Token get
Feature activation+0.131
through
Token through
Feature activation+0.814
to
Token to
Feature activation+0.424
me
Token me
Feature activation+1.430
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
reason
Token reason
Feature activation+1.426
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.681
have
Token have
Feature activation+0.460
to
Token to
Feature activation+0.413
see
Token see
Feature activation+1.689
the
Token the
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
picture
Token picture
Feature activation+3.449
.
Token.
Feature activation+2.005
And
Token And
Feature activation+1.296
gging
Tokengging
Feature activation+0.000
their
Token their
Feature activation+0.000
shoulders
Token shoulders
Feature activation+1.255
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
point
Token point
Feature activation+1.707
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
T
Token T
Feature activation+0.000
any
Tokenany
Feature activation+0.000
Yao
Token Yao
Feature activation+0.000

INTERVAL 0.573 - 1.145
CONTAINS 0.186%

than
Token than
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+0.000
Euros
Token Euros
Feature activation+0.808
($
Token ($
Feature activation+0.000
A
TokenA
Feature activation+0.000
US
TokenUS
Feature activation+0.000
3
Token 3
Feature activation+0.000
billion
Token billion
Feature activation+0.000
the
Token the
Feature activation+0.000
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.967
's
Token's
Feature activation+0.250
very
Token very
Feature activation+0.000
much
Token much
Feature activation+0.061
in
Token in
Feature activation+0.333
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
real
Token real
Feature activation+0.118
,
Token,
Feature activation+0.321
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
powerful
Token powerful
Feature activation+1.116
,
Token,
Feature activation+0.160
and
Token and
Feature activation+0.143
He
Token He
Feature activation+0.000
answers
Token answers
Feature activation+0.000
prayer
Token prayer
Feature activation+0.410
of
Token of
Feature activation+0.000
recent
Token recent
Feature activation+0.000
generations
Token generations
Feature activation+0.605
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
devastating
Token devastating
Feature activation+0.704
to
Token to
Feature activation+0.000
everyone
Token everyone
Feature activation+0.043
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
ever
Token ever
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.821
died
Token died
Feature activation+1.302
long
Token long
Feature activation+0.293
before
Token before
Feature activation+0.732
you
Token you
Feature activation+0.629
were
Token were
Feature activation+0.083
born
Token born
Feature activation+3.429
.
Token.
Feature activation+1.373
This
Token This
Feature activation+0.000

INTERVAL 0.000 - 0.573
CONTAINS 99.602%

have
Token have
Feature activation+0.000
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
;
Token;
Feature activation+0.000
in
Token in
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
10
Token 10
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
Disclaimer
TokenDisclaimer
Feature activation+0.000
:
Token:
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
can
Token can
Feature activation+0.000
substitute
Token substitute
Feature activation+0.000
for
Token for
Feature activation+0.000
stick
Token stick
Feature activation+0.000
skills
Token skills
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
C
TokenC
Feature activation+0.000
IO
TokenIO
Feature activation+0.000
executive
Token executive
Feature activation+0.000
board
Token board
Feature activation+0.000
has
Token has
Feature activation+0.000
endorsed
Token endorsed
Feature activation+0.000
two
Token two
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
,
Token,
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
certain
Token certain
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
violation
Token violation
Feature activation+0.000
,
Token,
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
Rep
Token Rep
Feature activation+0.000
.
Token.
Feature activation+0.000
John
Token John
Feature activation+0.000
Campbell
Token Campbell
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
CA
TokenCA
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 9 in H9.3: (feature 19868)

TOP ACTIVATIONS
MAX = 4.744

they
Token they
Feature activation+0.000
lied
Token lied
Feature activation+0.000
'
Token '
Feature activation+0.000
with
Tokenwith
Feature activation+1.277
such
Token such
Feature activation+0.975
ease
Token ease
Feature activation+4.744
,
Token,
Feature activation+0.823
it
Token it
Feature activation+1.935
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.258
s
Tokens
Feature activation+0.613
with
Token with
Feature activation+1.238
iron
Token iron
Feature activation+1.567
bars
Token bars
Feature activation+3.764
and
Token and
Feature activation+0.178
hamm
Token hamm
Feature activation+0.000
ers
Tokeners
Feature activation+4.200
,'
Token,'
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
'
Token '
Feature activation+0.000
Make
TokenMake
Feature activation+1.178
America
Token America
Feature activation+0.784
Great
Token Great
Feature activation+4.190
Again
Token Again
Feature activation+3.233
'
Token'
Feature activation+0.021
Merch
Token Merch
Feature activation+0.000
andise
Tokenandise
Feature activation+0.000
Deal
Token Deal
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
'
Token '
Feature activation+0.000
touch
Tokentouch
Feature activation+0.359
and
Token and
Feature activation+0.169
go
Token go
Feature activation+3.985
'
Token'
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
clash
Token clash
Feature activation+0.000
with
Token with
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
use
Token use
Feature activation+0.000
'
Token '
Feature activation+0.000
hot
Tokenhot
Feature activation+3.882
'
Token'
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
starting
Token starting
Feature activation+0.000
point
Token point
Feature activation+0.000
Nine
TokenNine
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
With
Token With
Feature activation+0.000
'
Token '
Feature activation+0.328
H
TokenH
Feature activation+3.318
ands
Tokenands
Feature activation+3.866
'
Token'
Feature activation+0.117
Found
Token Found
Feature activation+0.000
to
Token to
Feature activation+0.000
Be
Token Be
Feature activation+0.000
New
Token New
Feature activation+0.105
some
Token some
Feature activation+0.000
'
Token '
Feature activation+0.000
armed
Tokenarmed
Feature activation+3.666
with
Token with
Feature activation+1.238
iron
Token iron
Feature activation+1.567
bars
Token bars
Feature activation+3.764
and
Token and
Feature activation+0.178
hamm
Token hamm
Feature activation+0.000
ers
Tokeners
Feature activation+4.200
,'
Token,'
Feature activation+0.000
according
Token according
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
'
Token '
Feature activation+0.000
We
TokenWe
Feature activation+1.531
Found
Token Found
Feature activation+0.616
Love
Token Love
Feature activation+3.764
'
Token'
Feature activation+0.000
singer
Token singer
Feature activation+0.000
is
Token is
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
to
Token to
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
really
Token really
Feature activation+0.000
'
Token '
Feature activation+0.000
con
Tokencon
Feature activation+2.569
verse
Tokenverse
Feature activation+3.748
'
Token'
Feature activation+0.000
with
Token with
Feature activation+0.000
my
Token my
Feature activation+0.000
phone
Token phone
Feature activation+0.000
."
Token."
Feature activation+0.000
lun
Token lun
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
from
Token from
Feature activation+0.000
'
Token '
Feature activation+0.000
Info
TokenInfo
Feature activation+0.899
Wars
TokenWars
Feature activation+3.730
'
Token'
Feature activation+0.000
nut
Token nut
Feature activation+0.000
job
Tokenjob
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
'
Token '
Feature activation+0.000
man
Tokenman
Feature activation+2.447
opener
Token opener
Feature activation+3.718
'.
Token'.
Feature activation+0.000
But
Token But
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
FOX
TokenFOX
Feature activation+1.798
News
Token News
Feature activation+1.960
Medical
Token Medical
Feature activation+0.209
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.127
Team
TokenTeam
Feature activation+3.710
'
Token'
Feature activation+0.000
talks
Token talks
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
photo
Token photo
Feature activation+0.000
in
Token in
Feature activation+0.000
Calais
Token Calais
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
'
Token '
Feature activation+0.000
armed
Tokenarmed
Feature activation+3.666
with
Token with
Feature activation+1.238
iron
Token iron
Feature activation+1.567
bars
Token bars
Feature activation+3.764
and
Token and
Feature activation+0.178
hamm
Token hamm
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
'
Token '
Feature activation+0.000
di
Tokendi
Feature activation+1.843
plom
Tokenplom
Feature activation+0.858
acy
Tokenacy
Feature activation+3.636
'
Token'
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
champion
Token champion
Feature activation+0.000
at
Token at
Feature activation+0.000
Chinese
TokenChinese
Feature activation+0.000
'
Token '
Feature activation+0.000
arm
Tokenarm
Feature activation+0.950
-
Token-
Feature activation+0.238
tw
Tokentw
Feature activation+0.086
isting
Tokenisting
Feature activation+3.524
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Senior
TokenSenior
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
that
Token that
Feature activation+0.832
will
Token will
Feature activation+0.868
change
Token change
Feature activation+1.768
your
Token your
Feature activation+0.000
life
Token life
Feature activation+2.767
forever
Token forever
Feature activation+3.524
."
Token."
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+0.000
'
Token '
Feature activation+0.000
An
TokenAn
Feature activation+0.919
arch
Tokenarch
Feature activation+0.189
o
Tokeno
Feature activation+1.175
-
Token-
Feature activation+0.000
capitalist
Tokencapitalist
Feature activation+3.508
'
Token'
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
that
Token that
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.823
it
Token it
Feature activation+1.935
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.258
s
Tokens
Feature activation+0.613
troubling
Token troubling
Feature activation+3.432
.'
Token.'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
had
Token had
Feature activation+0.000
remember
Token remember
Feature activation+0.000
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000
'
Token '
Feature activation+0.000
Star
TokenStar
Feature activation+0.869
Wars
Token Wars
Feature activation+3.425
,'
Token,'
Feature activation+0.000
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
so
Token so
Feature activation+0.000
'
Token '
Feature activation+0.000
blown
Tokenblown
Feature activation+1.713
hugely
Token hugely
Feature activation+2.461
out
Token out
Feature activation+1.600
of
Token of
Feature activation+0.086
proportion
Token proportion
Feature activation+3.416
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000

Top DFA by src position
MAX = 5.096

because
Token because
Feature activation-0.007
Top resid features:
he
Token he
Feature activation-0.005
Top resid features:
believes
Token believes
Feature activation+0.009
Top resid features:
they
Token they
Feature activation-0.008
Top resid features:
lied
Token lied
Feature activation+0.070
Top resid features:
'
Token '
Feature activation+5.096
Top resid features:
with
Tokenwith
Feature activation+0.068
Top resid features:
such
Token such
Feature activation+0.009
Top resid features:
ease
Token ease
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Tunnel
Token Tunnel
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
Calais
Token Calais
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
some
Token some
Feature activation-0.008
Top resid features:
'
Token '
Feature activation+4.568
Top resid features:
armed
Tokenarmed
Feature activation+0.017
Top resid features:
with
Token with
Feature activation+0.088
Top resid features:
iron
Token iron
Feature activation+0.030
Top resid features:
bars
Token bars
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.035
Top resid features:
otes
Tokenotes
Feature activation+0.012
Top resid features:
His
Token His
Feature activation+0.004
Top resid features:
Own
Token Own
Feature activation+0.002
Top resid features:
Black
Token Black
Feature activation+0.013
Top resid features:
Friday
Token Friday
Feature activation-0.012
Top resid features:
'
Token '
Feature activation+4.597
Top resid features:
Make
TokenMake
Feature activation+0.059
Top resid features:
America
Token America
Feature activation-0.030
Top resid features:
Great
Token Great
Feature activation+0.018
Top resid features:
Again
Token Again
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
understood
Token understood
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
be
Token be
Feature activation-0.035
Top resid features:
'
Token '
Feature activation+5.055
Top resid features:
touch
Tokentouch
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
go
Token go
Feature activation+0.003
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
now
Token now
Feature activation-0.019
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.037
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
use
Token use
Feature activation-0.050
Top resid features:
'
Token '
Feature activation+4.566
Top resid features:
hot
Tokenhot
Feature activation+0.001
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
starting
Token starting
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.005
Top resid features:
"
Token "
Feature activation+0.013
Top resid features:
Nine
TokenNine
Feature activation-0.005
Top resid features:
Fish
Token Fish
Feature activation+0.006
Top resid features:
With
Token With
Feature activation+0.075
Top resid features:
'
Token '
Feature activation+4.368
Top resid features:
H
TokenH
Feature activation-0.001
Top resid features:
ands
Tokenands
Feature activation+0.022
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Found
Token Found
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Tunnel
Token Tunnel
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
Calais
Token Calais
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
some
Token some
Feature activation-0.014
Top resid features:
'
Token '
Feature activation+4.183
Top resid features:
armed
Tokenarmed
Feature activation+0.019
Top resid features:
with
Token with
Feature activation+0.106
Top resid features:
iron
Token iron
Feature activation+0.048
Top resid features:
bars
Token bars
Feature activation+0.057
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
activity
Token activity
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.005
Top resid features:
'
Token '
Feature activation+4.250
Top resid features:
We
TokenWe
Feature activation-0.007
Top resid features:
Found
Token Found
Feature activation-0.012
Top resid features:
Love
Token Love
Feature activation-0.008
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
singer
Token singer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
't
Token't
Feature activation-0.013
Top resid features:
really
Token really
Feature activation-0.031
Top resid features:
'
Token '
Feature activation+4.275
Top resid features:
con
Tokencon
Feature activation+0.009
Top resid features:
verse
Tokenverse
Feature activation+0.013
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
utter
Token utter
Feature activation-0.000
Top resid features:
lun
Token lun
Feature activation+0.001
Top resid features:
acy
Tokenacy
Feature activation-0.010
Top resid features:
from
Token from
Feature activation-0.084
Top resid features:
'
Token '
Feature activation+4.339
Top resid features:
Info
TokenInfo
Feature activation-0.015
Top resid features:
Wars
TokenWars
Feature activation+0.019
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
nut
Token nut
Feature activation+0.000
Top resid features:
job
Tokenjob
Feature activation+0.000
Top resid features:
upward
Token upward
Feature activation-0.004
Top resid features:
elbow
Token elbow
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
real
Token real
Feature activation-0.071
Top resid features:
'
Token '
Feature activation+4.475
Top resid features:
man
Tokenman
Feature activation-0.005
Top resid features:
opener
Token opener
Feature activation+0.002
Top resid features:
'.
Token'.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
larger
Token larger
Feature activation-0.000
Top resid features:
arm
Token arm
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.050
Top resid features:
The
TokenThe
Feature activation-0.004
Top resid features:
'
Token '
Feature activation+4.169
Top resid features:
FOX
TokenFOX
Feature activation+0.002
Top resid features:
News
Token News
Feature activation-0.027
Top resid features:
Medical
Token Medical
Feature activation+0.024
Top resid features:
A
Token A
Feature activation+0.017
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
Tunnel
Token Tunnel
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
Calais
Token Calais
Feature activation-0.018
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
some
Token some
Feature activation-0.008
Top resid features:
'
Token '
Feature activation+4.230
Top resid features:
armed
Tokenarmed
Feature activation+0.043
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
iron
Token iron
Feature activation+0.000
Top resid features:
bars
Token bars
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.004
Top resid features:
knows
Token knows
Feature activation-0.009
Top resid features:
what
Token what
Feature activation-0.010
Top resid features:
sort
Token sort
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.020
Top resid features:
'
Token '
Feature activation+4.164
Top resid features:
di
Tokendi
Feature activation+0.007
Top resid features:
plom
Tokenplom
Feature activation-0.015
Top resid features:
acy
Tokenacy
Feature activation+0.021
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
China
Token China
Feature activation-0.026
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.098
Top resid features:
Chinese
TokenChinese
Feature activation+0.016
Top resid features:
'
Token '
Feature activation+4.116
Top resid features:
arm
Tokenarm
Feature activation+0.032
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
tw
Tokentw
Feature activation-0.008
Top resid features:
isting
Tokenisting
Feature activation+0.027
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
am
Token am
Feature activation-0.003
Top resid features:
about
Token about
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
learn
Token learn
Feature activation-0.001
Top resid features:
'
Token '
Feature activation+4.005
Top resid features:
the
Tokenthe
Feature activation+0.006
Top resid features:
one
Token one
Feature activation-0.001
Top resid features:
thing
Token thing
Feature activation+0.038
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
will
Token will
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
terms
Token terms
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
an
Token an
Feature activation+0.017
Top resid features:
'
Token '
Feature activation+3.964
Top resid features:
An
TokenAn
Feature activation+0.017
Top resid features:
arch
Tokenarch
Feature activation-0.002
Top resid features:
o
Tokeno
Feature activation+0.018
Top resid features:
-
Token-
Feature activation+0.098
Top resid features:
capitalist
Tokencapitalist
Feature activation+0.013
Top resid features:
because
Token because
Feature activation-0.010
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
believes
Token believes
Feature activation+0.002
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
lied
Token lied
Feature activation+0.004
Top resid features:
'
Token '
Feature activation+4.219
Top resid features:
with
Tokenwith
Feature activation+0.012
Top resid features:
such
Token such
Feature activation-0.002
Top resid features:
ease
Token ease
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.121
Top resid features:
it
Token it
Feature activation+0.028
Top resid features:
Everybody
TokenEverybody
Feature activation-0.002
Top resid features:
will
Token will
Feature activation-0.001
Top resid features:
remember
Token remember
Feature activation-0.004
Top resid features:
him
Token him
Feature activation-0.006
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
'
Token '
Feature activation+4.149
Top resid features:
Star
TokenStar
Feature activation-0.005
Top resid features:
Wars
Token Wars
Feature activation-0.034
Top resid features:
,'
Token,'
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.009
Top resid features:
Father
Token Father
Feature activation-0.004
Top resid features:
's
Token's
Feature activation-0.004
Top resid features:
Khan
Token Khan
Feature activation-0.000
Top resid features:
remarks
Token remarks
Feature activation+0.003
Top resid features:
'
Token '
Feature activation+4.305
Top resid features:
blown
Tokenblown
Feature activation+0.008
Top resid features:
hugely
Token hugely
Feature activation-0.004
Top resid features:
out
Token out
Feature activation-0.019
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
proportion
Token proportion
Feature activation+0.034
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.03

Head 3: 0.57

Head 4: 0.02

Head 5: 0.05

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.02

Head 10: 0.13

Head 11: 0.04

Positive logits

,'5.57

.'5.08

':5.04

';5.01

?'5.00

!'4.90

'.4.87

',4.77

,'"4.76

',"4.72

',4.54

.'"4.48

').4.43

'."4.37

'?4.37

'),4.32

'.4.22

')4.22

]'4.16

)'3.98

Negative logits

"-2.71

"[-2.69

"…-2.60

—"-2.52

"...-2.42

"--2.13

"#-2.07

"(-2.04

"$-2.03

=""-2.03

esides-2.03

("-2.00

"@-1.99

"_-1.95

"<-1.89

"{-1.84

"+-1.84

"/-1.79

""-1.66

"\-1.60

INTERVAL 4.270 - 4.744
CONTAINS 0.000%

they
Token they
Feature activation+0.000
lied
Token lied
Feature activation+0.000
'
Token '
Feature activation+0.000
with
Tokenwith
Feature activation+1.277
such
Token such
Feature activation+0.975
ease
Token ease
Feature activation+4.744
,
Token,
Feature activation+0.823
it
Token it
Feature activation+1.935
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.258
s
Tokens
Feature activation+0.613

INTERVAL 3.795 - 4.270
CONTAINS 0.001%

to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
'
Token '
Feature activation+0.000
touch
Tokentouch
Feature activation+0.359
and
Token and
Feature activation+0.169
go
Token go
Feature activation+3.985
'
Token'
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
clash
Token clash
Feature activation+0.000
with
Token with
Feature activation+0.000
Nine
TokenNine
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
With
Token With
Feature activation+0.000
'
Token '
Feature activation+0.328
H
TokenH
Feature activation+3.318
ands
Tokenands
Feature activation+3.866
'
Token'
Feature activation+0.117
Found
Token Found
Feature activation+0.000
to
Token to
Feature activation+0.000
Be
Token Be
Feature activation+0.000
New
Token New
Feature activation+0.105
with
Token with
Feature activation+1.238
iron
Token iron
Feature activation+1.567
bars
Token bars
Feature activation+3.764
and
Token and
Feature activation+0.178
hamm
Token hamm
Feature activation+0.000
ers
Tokeners
Feature activation+4.200
,'
Token,'
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
'
Token '
Feature activation+0.000
Make
TokenMake
Feature activation+1.178
America
Token America
Feature activation+0.784
Great
Token Great
Feature activation+4.190
Again
Token Again
Feature activation+3.233
'
Token'
Feature activation+0.021
Merch
Token Merch
Feature activation+0.000
andise
Tokenandise
Feature activation+0.000
Deal
Token Deal
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
use
Token use
Feature activation+0.000
'
Token '
Feature activation+0.000
hot
Tokenhot
Feature activation+3.882
'
Token'
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
starting
Token starting
Feature activation+0.000
point
Token point
Feature activation+0.000

INTERVAL 3.321 - 3.795
CONTAINS 0.002%

lun
Token lun
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
from
Token from
Feature activation+0.000
'
Token '
Feature activation+0.000
Info
TokenInfo
Feature activation+0.899
Wars
TokenWars
Feature activation+3.730
'
Token'
Feature activation+0.000
nut
Token nut
Feature activation+0.000
job
Tokenjob
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
in
Token in
Feature activation+0.000
Calais
Token Calais
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
'
Token '
Feature activation+0.000
armed
Tokenarmed
Feature activation+3.666
with
Token with
Feature activation+1.238
iron
Token iron
Feature activation+1.567
bars
Token bars
Feature activation+3.764
and
Token and
Feature activation+0.178
hamm
Token hamm
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
really
Token really
Feature activation+0.000
'
Token '
Feature activation+0.000
con
Tokencon
Feature activation+2.569
verse
Tokenverse
Feature activation+3.748
'
Token'
Feature activation+0.000
with
Token with
Feature activation+0.000
my
Token my
Feature activation+0.000
phone
Token phone
Feature activation+0.000
."
Token."
Feature activation+0.000
photograph
Token photograph
Feature activation+0.000
'
Token '
Feature activation+0.733
d
Tokend
Feature activation+1.189
aw
Tokenaw
Feature activation+1.172
la
Tokenla
Feature activation+3.042
takeaway
Token takeaway
Feature activation+3.332
w
Token w
Feature activation+0.314
/
Token/
Feature activation+0.488
@
Token @
Feature activation+1.185
um
Tokenum
Feature activation+0.000
_
Token_
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
'
Token '
Feature activation+0.000
We
TokenWe
Feature activation+1.531
Found
Token Found
Feature activation+0.616
Love
Token Love
Feature activation+3.764
'
Token'
Feature activation+0.000
singer
Token singer
Feature activation+0.000
is
Token is
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.847 - 3.321
CONTAINS 0.004%

people
Token people
Feature activation+0.000
critic
Token critic
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
'
Token '
Feature activation+0.000
s
Tokens
Feature activation+0.809
ensitivity
Tokenensitivity
Feature activation+3.025
',
Token',
Feature activation+0.000
as
Token as
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
anne
Tokenanne
Feature activation+0.000
Barr
Token Barr
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
filmed
Token filmed
Feature activation+0.000
'
Token '
Feature activation+0.000
t
Tokent
Feature activation+1.127
ort
Tokenort
Feature activation+1.364
ure
Tokenure
Feature activation+2.893
of
Token of
Feature activation+0.766
a
Token a
Feature activation+0.470
Palestinian
Token Palestinian
Feature activation+1.104
man
Token man
Feature activation+2.482
'.
Token'.
Feature activation+0.000
"
Token "
Feature activation+0.000
Nine
TokenNine
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
With
Token With
Feature activation+0.000
'
Token '
Feature activation+0.328
H
TokenH
Feature activation+3.318
ands
Tokenands
Feature activation+3.866
'
Token'
Feature activation+0.117
Found
Token Found
Feature activation+0.000
to
Token to
Feature activation+0.000
Be
Token Be
Feature activation+0.000
playing
Token playing
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.000
danger
Tokendanger
Feature activation+0.007
ous
Tokenous
Feature activation+1.019
game
Token game
Feature activation+2.936
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
July
Token July
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
'
Token '
Feature activation+0.107
dead
Tokendead
Feature activation+3.263
',
Token',
Feature activation+0.000
they
Token they
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
means
Token means
Feature activation+0.000

INTERVAL 2.372 - 2.847
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+1.387
acy
Tokenacy
Feature activation+1.946
lives
Token lives
Feature activation+1.426
on
Token on
Feature activation+2.537
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
They
TokenThey
Feature activation+0.000
roud
Tokenroud
Feature activation+1.497
Boys
Token Boys
Feature activation+2.588
'
Token'
Feature activation+0.000
holding
Token holding
Feature activation+0.165
'
Token '
Feature activation+0.547
March
TokenMarch
Feature activation+2.715
4
Token 4
Feature activation+3.364
Trump
Token Trump
Feature activation+3.018
'
Token'
Feature activation+0.000
in
Token in
Feature activation+0.000
#
Token #
Feature activation+0.000
world
Tokenworld
Feature activation+1.124
class
Token class
Feature activation+2.318
player
Token player
Feature activation+2.635
and
Token and
Feature activation+0.370
deal
Token deal
Feature activation+0.000
maker
Tokenmaker
Feature activation+2.831
,'
Token,'
Feature activation+0.000
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
these
Token these
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
accept
Token accept
Feature activation+0.000
'
Token '
Feature activation+0.000
b
Tokenb
Feature activation+1.639
og
Tokenog
Feature activation+1.309
us
Tokenus
Feature activation+2.452
'
Token'
Feature activation+0.000
reconciliation
Token reconciliation
Feature activation+0.000
deal
Token deal
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token '
Feature activation+0.000
bear
Tokenbear
Feature activation+2.825
flips
Token flips
Feature activation+1.543
Leo
Token Leo
Feature activation+0.291
over
Token over
Feature activation+0.452
and
Token and
Feature activation+0.361
thrust
Token thrust
Feature activation+0.000

INTERVAL 1.898 - 2.372
CONTAINS 0.009%

?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
'
Token '
Feature activation+0.000
Diamond
TokenDiamond
Feature activation+2.008
s
Tokens
Feature activation+1.661
'
Token'
Feature activation+0.000
singer
Token singer
Feature activation+0.000
is
Token is
Feature activation+0.000
said
Token said
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.000
cher
Tokencher
Feature activation+0.201
ry
Tokenry
Feature activation+0.775
on
Token on
Feature activation+0.159
top
Token top
Feature activation+2.332
'
Token'
Feature activation+0.000
reason
Token reason
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
care
Tokencare
Feature activation+0.000
was
Token was
Feature activation+0.000
'
Token '
Feature activation+0.000
an
Tokenan
Feature activation+0.955
obstacle
Token obstacle
Feature activation+2.114
,'
Token,'
Feature activation+0.000
says
Token says
Feature activation+0.000
First
Token First
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
heard
Token heard
Feature activation+0.000
yelling
Token yelling
Feature activation+0.000
'
Token '
Feature activation+0.000
Black
TokenBlack
Feature activation+1.589
Lives
Token Lives
Feature activation+1.051
Matter
Token Matter
Feature activation+2.342
,'
Token,'
Feature activation+0.000
and
Token and
Feature activation+0.000
'
Token '
Feature activation+0.878
H
TokenH
Feature activation+1.826
ands
Tokenands
Feature activation+0.654
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token '
Feature activation+0.000
Connect
TokenConnect
Feature activation+1.490
icut
Tokenicut
Feature activation+1.841
effect
Token effect
Feature activation+1.957
'
Token'
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.423 - 1.898
CONTAINS 0.016%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
What
TokenWhat
Feature activation+0.812
is
Token is
Feature activation+0.886
needed
Token needed
Feature activation+1.467
is
Token is
Feature activation+0.000
information
Token information
Feature activation+1.531
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
restrictions
Token restrictions
Feature activation+2.180
Who
Token Who
Feature activation+0.000
's
Token's
Feature activation+0.000
'
Token '
Feature activation+0.000
A
TokenA
Feature activation+2.367
Quick
Token Quick
Feature activation+0.797
One
Token One
Feature activation+1.699
,
Token,
Feature activation+0.738
While
Token While
Feature activation+0.755
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.000
Away
Token Away
Feature activation+0.239
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
nothing
Token nothing
Feature activation+0.670
to
Token to
Feature activation+0.000
apologize
Token apologize
Feature activation+0.368
for
Token for
Feature activation+1.792
'
Token'
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
King
Token King
Feature activation+0.000
spins
Token spins
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
Movies
Token Movies
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
X
TokenX
Feature activation+1.472
-
Token-
Feature activation+0.264
Men
TokenMen
Feature activation+1.775
:
Token:
Feature activation+0.202
Days
Token Days
Feature activation+0.000
of
Token of
Feature activation+0.139
Future
Token Future
Feature activation+0.000
Past
Token Past
Feature activation+2.009
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
'
Token '
Feature activation+0.000
too
Tokentoo
Feature activation+1.535
many
Token many
Feature activation+1.559
tweets
Token tweets
Feature activation+1.747
...
Token...
Feature activation+0.909
',"
Token',"
Feature activation+0.000
referencing
Token referencing
Feature activation+0.000
a
Token a
Feature activation+0.000
comment
Token comment
Feature activation+0.000

INTERVAL 0.949 - 1.423
CONTAINS 0.019%

student
Token student
Feature activation+0.000
's
Token's
Feature activation+0.000
subjective
Token subjective
Feature activation+0.000
'
Token '
Feature activation+0.000
internal
Tokeninternal
Feature activation+0.198
sense
Token sense
Feature activation+1.383
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+1.335
.'"
Token.'"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
thought
Token thought
Feature activation+0.440
you
Token you
Feature activation+0.014
wanted
Token wanted
Feature activation+0.227
to
Token to
Feature activation+0.017
do
Token do
Feature activation+0.044
this
Token this
Feature activation+1.322
.
Token.
Feature activation+0.487
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+1.635
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.000
def
Tokendef
Feature activation+1.220
iciency
Tokeniciency
Feature activation+2.459
memo
Token memo
Feature activation+2.263
'
Token'
Feature activation+0.000
on
Token on
Feature activation+0.000
January
Token January
Feature activation+0.000
that
Token that
Feature activation+0.330
violates
Token violates
Feature activation+0.382
the
Token the
Feature activation+0.000
trans
Token trans
Feature activation+0.000
itive
Tokenitive
Feature activation+0.000
inference
Token inference
Feature activation+1.011
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
try
Token try
Feature activation+0.569
to
Token to
Feature activation+0.000
figure
Token figure
Feature activation+0.101
you
Token you
Feature activation+0.481
wanna
Token wanna
Feature activation+0.380
make
Token make
Feature activation+0.089
a
Token a
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Widow
Token Widow
Feature activation+1.363
movie
Token movie
Feature activation+1.628
?'
Token?'
Feature activation+0.000
the
Token the
Feature activation+0.000
answer
Token answer
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 0.474 - 0.949
CONTAINS 0.033%

have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.267
Scottish
Token Scottish
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.156
but
Token but
Feature activation+0.488
I
Token I
Feature activation+0.227
think
Token think
Feature activation+0.250
I
Token I
Feature activation+0.000
swayed
Token swayed
Feature activation+0.071
him
Token him
Feature activation+0.818
protest
Token protest
Feature activation+0.000
"
Token "
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
oliberal
Tokenoliberal
Feature activation+0.000
economic
Token economic
Feature activation+0.000
and
Token and
Feature activation+0.667
labor
Token labor
Feature activation+0.114
policies
Token policies
Feature activation+0.000
"
Token"
Feature activation+0.000
pursued
Token pursued
Feature activation+0.000
by
Token by
Feature activation+0.000
"
Token"
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
Rex
Token Rex
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.509
world
Tokenworld
Feature activation+1.124
class
Token class
Feature activation+2.318
player
Token player
Feature activation+2.635
and
Token and
Feature activation+0.370
deal
Token deal
Feature activation+0.000
old
Token old
Feature activation+0.000
or
Token or
Feature activation+0.000
used
Token used
Feature activation+0.000
'
Token '
Feature activation+0.000
one
Tokenone
Feature activation+1.355
-
Token-
Feature activation+0.846
pot
Tokenpot
Feature activation+2.384
'
Token'
Feature activation+0.000
meth
Token meth
Feature activation+0.000
labs
Token labs
Feature activation+0.000
,
Token,
Feature activation+0.000
walk
Token walk
Feature activation+0.155
in
Token in
Feature activation+0.154
the
Token the
Feature activation+0.000
rain
Token rain
Feature activation+0.889
to
Token to
Feature activation+0.000
hide
Token hide
Feature activation+0.659
my
Token my
Feature activation+0.000
tears
Token tears
Feature activation+1.455
.'
Token.'
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.000 - 0.474
CONTAINS 99.909%

water
Token water
Feature activation+0.000
flux
Token flux
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
applied
Token applied
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
with
Token with
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
thing
Token thing
Feature activation+0.000
but
Token but
Feature activation+0.000
my
Token my
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
white
Tokenwhite
Feature activation+0.000
friends
Token friends
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
The
Token The
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
Finance
Token Finance
Feature activation+0.000
and
Token and
Feature activation+0.000
Accounting
Token Accounting
Feature activation+0.000
Service
Token Service
Feature activation+0.000
(
Token (
Feature activation+0.000
DF
TokenDF
Feature activation+0.000
AS
TokenAS
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Tokens
Feature activation+0.000
simply
Token simply
Feature activation+0.000
a
Token a
Feature activation+0.000
placeholder
Token placeholder
Feature activation+0.000
logo
Token logo
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lake
TokenLake
Feature activation+0.000
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
update
Token update
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