H11.3 top features

Top feature 0 in H11.3: (feature 19038)

TOP ACTIVATIONS
MAX = 4.301

the
Token the
Feature activation+0.072
need
Token need
Feature activation+0.000
for
Token for
Feature activation+1.521
a
Token a
Feature activation+1.900
nationwide
Token nationwide
Feature activation+2.596
Super
Token Super
Feature activation+4.301
charg
Tokencharg
Feature activation+0.000
er
Tokener
Feature activation+0.841
network
Token network
Feature activation+0.896
.
Token.
Feature activation+0.000
Australia
Token Australia
Feature activation+0.359
1974
Token 1974
Feature activation+0.000
Fiat
Token Fiat
Feature activation+0.000
126
Token 126
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.609
Budapest
Token Budapest
Feature activation+4.217
last
Token last
Feature activation+0.021
year
Token year
Feature activation+0.608
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Y
TokenY
Feature activation+0.000
is
Token is
Feature activation+0.057
an
Token an
Feature activation+0.574
Italian
Token Italian
Feature activation+2.528
ground
Token ground
Feature activation+1.717
-
Token-
Feature activation+4.154
attack
Tokenattack
Feature activation+1.770
and
Token and
Feature activation+0.955
reconnaissance
Token reconnaissance
Feature activation+2.635
aircraft
Token aircraft
Feature activation+1.180
which
Token which
Feature activation+0.182
would
Token would
Feature activation+0.229
be
Token be
Feature activation+0.983
cruising
Token cruising
Feature activation+0.000
silently
Token silently
Feature activation+0.664
on
Token on
Feature activation+0.492
German
Token German
Feature activation+3.942
streets
Token streets
Feature activation+0.302
by
Token by
Feature activation+0.000
2020
Token 2020
Feature activation+0.000
,
Token,
Feature activation+0.303
to
Token to
Feature activation+0.000
Ford
Token Ford
Feature activation+2.106
's
Token's
Feature activation+0.554
Dear
Token Dear
Feature activation+0.000
born
Tokenborn
Feature activation+3.570
,
Token,
Feature activation+0.247
Michigan
Token Michigan
Feature activation+3.914
,
Token,
Feature activation+3.228
assembly
Token assembly
Feature activation+1.608
plant
Token plant
Feature activation+0.352
located
Token located
Feature activation+0.000
12
Token 12
Feature activation+1.542
won
Token won
Feature activation+1.015
prizes
Token prizes
Feature activation+0.000
in
Token in
Feature activation+2.487
T
Token T
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
A
TokenA
Feature activation+3.802
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.287
s
Tokens
Feature activation+3.381
signature
Token signature
Feature activation+2.890
writing
Token writing
Feature activation+0.234
Z
Token Z
Feature activation+2.327
d
Tokend
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ien
Tokenien
Feature activation+0.000
ci
Tokenci
Feature activation+0.000
k
Tokenk
Feature activation+3.686
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.555
s
Tokens
Feature activation+3.063
offerings
Token offerings
Feature activation+0.000
.
Token.
Feature activation+0.000
elt
Tokenelt
Feature activation+0.184
aw
Tokenaw
Feature activation+0.000
ing
Tokening
Feature activation+0.000
-
Token-
Feature activation+0.000
That
TokenThat
Feature activation+0.724
-
Token-
Feature activation+3.661
T
TokenT
Feature activation+0.707
otally
Tokenotally
Feature activation+1.725
-
Token-
Feature activation+1.675
Isn
TokenIsn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Spider
Token Spider
Feature activation+0.590
,
Token,
Feature activation+0.831
have
Token have
Feature activation+2.367
won
Token won
Feature activation+1.922
awards
Token awards
Feature activation+0.061
in
Token in
Feature activation+3.653
T
Token T
Feature activation+0.668
AW
TokenAW
Feature activation+2.200
A
TokenA
Feature activation+2.682
's
Token's
Feature activation+2.433
annual
Token annual
Feature activation+3.059
stands
Token stands
Feature activation+0.000
out
Token out
Feature activation+0.000
as
Token as
Feature activation+1.099
a
Token a
Feature activation+1.534
special
Token special
Feature activation+2.984
case
Token case
Feature activation+3.630
of
Token of
Feature activation+2.007
silence
Token silence
Feature activation+2.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.286
Ċ
TokenĊ
Feature activation+0.941
the
Token the
Feature activation+1.571
Hum
Token Hum
Feature activation+0.000
mer
Tokenmer
Feature activation+1.359
will
Token will
Feature activation+1.558
last
Token last
Feature activation+0.271
three
Token three
Feature activation+3.626
times
Token times
Feature activation+1.625
longer
Token longer
Feature activation+3.109
âĢ¦)
TokenâĢ¦)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.105
Ċ
TokenĊ
Feature activation+0.470
not
Token not
Feature activation+0.308
unlike
Token unlike
Feature activation+1.935
an
Token an
Feature activation+1.389
American
Token American
Feature activation+1.660
vice
Token vice
Feature activation+1.728
-
Token-
Feature activation+3.616
president
Tokenpresident
Feature activation+1.532
:
Token:
Feature activation+1.495
be
Token be
Feature activation+0.523
available
Token available
Feature activation+0.284
for
Token for
Feature activation+1.309
1964
Token 1964
Feature activation+1.041
at
Token at
Feature activation+0.000
Ford
Token Ford
Feature activation+2.106
's
Token's
Feature activation+0.554
Dear
Token Dear
Feature activation+0.000
born
Tokenborn
Feature activation+3.570
,
Token,
Feature activation+0.247
Michigan
Token Michigan
Feature activation+3.914
,
Token,
Feature activation+3.228
assembly
Token assembly
Feature activation+1.608
plant
Token plant
Feature activation+0.352
ocking
Tokenocking
Feature activation+0.036
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.341
miles
Token miles
Feature activation+1.353
annually
Token annually
Feature activation+3.552
can
Token can
Feature activation+1.168
save
Token save
Feature activation+0.538
âĤ¬
Token âĤ¬
Feature activation+0.000
6
Token6
Feature activation+0.000
,
Token,
Feature activation+0.000
horse
Tokenhorse
Feature activation+2.443
for
Token for
Feature activation+1.278
sale
Token sale
Feature activation+0.320
by
Token by
Feature activation+1.267
White
Token White
Feature activation+1.308
horse
Tokenhorse
Feature activation+3.539
Motors
Token Motors
Feature activation+0.705
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.201
where
Token where
Feature activation+0.890
this
Token this
Feature activation+0.678
-
Token-
Feature activation+0.000
150
Token150
Feature activation+0.000
being
Token being
Feature activation+1.341
crowned
Token crowned
Feature activation+1.246
T
Token T
Feature activation+0.311
AW
TokenAW
Feature activation+3.523
A
TokenA
Feature activation+1.534
's
Token's
Feature activation+3.329
2014
Token 2014
Feature activation+2.048
"
Token "
Feature activation+2.882
T
TokenT
Feature activation+2.122
of
Token of
Feature activation+1.247
sport
Token sport
Feature activation+0.992
utility
Token utility
Feature activation+1.379
vehicles
Token vehicles
Feature activation+0.000
roaming
Token roaming
Feature activation+2.018
the
Token the
Feature activation+3.439
field
Token field
Feature activation+1.159
.
Token.
Feature activation+0.443
Even
Token Even
Feature activation+0.666
the
Token the
Feature activation+0.633
oddly
Token oddly
Feature activation+1.544
to
Token to
Feature activation+1.237
drive
Token drive
Feature activation+3.128
and
Token and
Feature activation+0.254
simple
Token simple
Feature activation+1.999
to
Token to
Feature activation+1.709
maintain
Token maintain
Feature activation+3.419
street
Token street
Feature activation+2.356
car
Token car
Feature activation+2.589
,
Token,
Feature activation+0.000
featuring
Token featuring
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
optional
Token optional
Feature activation+0.000
Electro
Token Electro
Feature activation+3.017
Gy
Token Gy
Feature activation+0.325
ro
Tokenro
Feature activation+1.512
-
Token-
Feature activation+3.410
C
TokenC
Feature activation+0.863
ator
Tokenator
Feature activation+1.242
(
Token (
Feature activation+0.092
the
Tokenthe
Feature activation+0.744
world
Token world
Feature activation+1.477
Ahead
Token Ahead
Feature activation+1.572
Of
Token Of
Feature activation+1.564
De
Token De
Feature activation+0.452
but
Tokenbut
Feature activation+2.378
At
Token At
Feature activation+2.935
Frankfurt
Token Frankfurt
Feature activation+3.408
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2018
Token2018
Feature activation+0.000
BMW
Token BMW
Feature activation+1.175
6
Token 6
Feature activation+0.000

Top DFA by src position
MAX = 4.010

the
Token the
Feature activation-0.006
Top resid features:
launch
Token launch
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
Model
Token Model
Feature activation+0.132
Top resid features:
S
Token S
Feature activation+1.856
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
Oz
Token Oz
Feature activation+0.010
Top resid features:
comes
Token comes
Feature activation+0.200
Top resid features:
the
Token the
Feature activation+0.129
Top resid features:
need
Token need
Feature activation+0.035
Top resid features:
next
Token next
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
1974
Token 1974
Feature activation+0.054
Top resid features:
Fiat
Token Fiat
Feature activation+0.111
Top resid features:
126
Token 126
Feature activation+0.263
Top resid features:
s
Tokens
Feature activation+3.517
Top resid features:
in
Token in
Feature activation+0.103
Top resid features:
Budapest
Token Budapest
Feature activation+0.025
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
91
Token91
Feature activation+0.389
Top resid features:
Y
TokenY
Feature activation+0.172
Top resid features:
is
Token is
Feature activation+0.118
Top resid features:
an
Token an
Feature activation+0.213
Top resid features:
Italian
Token Italian
Feature activation+0.428
Top resid features:
ground
Token ground
Feature activation+3.001
Top resid features:
-
Token-
Feature activation+0.060
Top resid features:
attack
Tokenattack
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
reconnaissance
Token reconnaissance
Feature activation+0.000
Top resid features:
aircraft
Token aircraft
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.078
Top resid features:
would
Token would
Feature activation-0.003
Top resid features:
be
Token be
Feature activation+0.024
Top resid features:
cruising
Token cruising
Feature activation+2.162
Top resid features:
silently
Token silently
Feature activation+0.166
Top resid features:
on
Token on
Feature activation+2.202
Top resid features:
German
Token German
Feature activation+0.129
Top resid features:
streets
Token streets
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
2020
Token 2020
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
1964
Token 1964
Feature activation+0.118
Top resid features:
at
Token at
Feature activation+0.301
Top resid features:
Ford
Token Ford
Feature activation+0.426
Top resid features:
's
Token's
Feature activation+2.017
Top resid features:
Dear
Token Dear
Feature activation+0.275
Top resid features:
born
Tokenborn
Feature activation+0.214
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
Michigan
Token Michigan
Feature activation+0.216
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
a
Token a
Feature activation+0.053
Top resid features:
business
Token business
Feature activation+0.047
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
restores
Token restores
Feature activation+0.399
Top resid features:
Jeep
Token Jeep
Feature activation+1.740
Top resid features:
Wag
Token Wag
Feature activation+0.281
Top resid features:
one
Tokenone
Feature activation-0.003
Top resid features:
ers
Tokeners
Feature activation+1.199
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
won
Token won
Feature activation-0.010
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
main
Token main
Feature activation+0.075
Top resid features:
stay
Tokenstay
Feature activation+0.517
Top resid features:
of
Token of
Feature activation+1.762
Top resid features:
Z
Token Z
Feature activation+0.032
Top resid features:
d
Tokend
Feature activation-0.005
Top resid features:
ur
Tokenur
Feature activation-0.001
Top resid features:
ien
Tokenien
Feature activation-0.012
Top resid features:
ci
Tokenci
Feature activation-0.013
Top resid features:
D
Token D
Feature activation+0.429
Top resid features:
elt
Tokenelt
Feature activation+0.139
Top resid features:
aw
Tokenaw
Feature activation+0.198
Top resid features:
ing
Tokening
Feature activation+0.657
Top resid features:
-
Token-
Feature activation+0.089
Top resid features:
That
TokenThat
Feature activation+1.165
Top resid features:
-
Token-
Feature activation-0.024
Top resid features:
T
TokenT
Feature activation+0.000
Top resid features:
otally
Tokenotally
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Isn
TokenIsn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
2015
Token 2015
Feature activation+0.020
Top resid features:
Ford
Token Ford
Feature activation+0.119
Top resid features:
F
Token F
Feature activation+0.039
Top resid features:
-
Token-
Feature activation+0.009
Top resid features:
150
Token150
Feature activation+0.967
Top resid features:
being
Token being
Feature activation+0.099
Top resid features:
crowned
Token crowned
Feature activation+0.105
Top resid features:
T
Token T
Feature activation+0.057
Top resid features:
AW
TokenAW
Feature activation+0.035
Top resid features:
A
TokenA
Feature activation+0.022
Top resid features:
around
Token around
Feature activation+0.059
Top resid features:
,
Token,
Feature activation-0.125
Top resid features:
but
Token but
Feature activation-0.044
Top resid features:
said
Token said
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.454
Top resid features:
Volt
Token Volt
Feature activation+2.181
Top resid features:
stands
Token stands
Feature activation-0.000
Top resid features:
out
Token out
Feature activation+0.026
Top resid features:
as
Token as
Feature activation+0.046
Top resid features:
a
Token a
Feature activation+0.686
Top resid features:
special
Token special
Feature activation+0.668
Top resid features:
less
Token less
Feature activation+0.016
Top resid features:
energy
Token energy
Feature activation+0.016
Top resid features:
than
Token than
Feature activation+0.166
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
Pri
Token Pri
Feature activation+0.079
Top resid features:
us
Tokenus
Feature activation+2.951
Top resid features:
.
Token.
Feature activation-0.094
Top resid features:
(
Token (
Feature activation-0.297
Top resid features:
I
Token I
Feature activation-0.036
Top resid features:
am
Token am
Feature activation-0.029
Top resid features:
not
Token not
Feature activation-0.014
Top resid features:
job
Token job
Feature activation+0.012
Top resid features:
not
Token not
Feature activation-0.003
Top resid features:
unlike
Token unlike
Feature activation+0.014
Top resid features:
an
Token an
Feature activation+0.042
Top resid features:
American
Token American
Feature activation+0.784
Top resid features:
vice
Token vice
Feature activation+2.644
Top resid features:
-
Token-
Feature activation+0.028
Top resid features:
president
Tokenpresident
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
available
Token available
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
1964
Token 1964
Feature activation+0.108
Top resid features:
at
Token at
Feature activation+0.536
Top resid features:
Ford
Token Ford
Feature activation+0.363
Top resid features:
's
Token's
Feature activation+1.989
Top resid features:
Dear
Token Dear
Feature activation+0.087
Top resid features:
born
Tokenborn
Feature activation+0.119
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Michigan
Token Michigan
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
can
Token can
Feature activation-0.023
Top resid features:
reduce
Token reduce
Feature activation+0.007
Top resid features:
expenses
Token expenses
Feature activation+0.065
Top resid features:
.
Token.
Feature activation-0.082
Top resid features:
Two
Token Two
Feature activation+0.012
Top resid features:
trucks
Token trucks
Feature activation+4.010
Top resid features:
cl
Token cl
Feature activation-0.075
Top resid features:
ocking
Tokenocking
Feature activation-0.002
Top resid features:
100
Token 100
Feature activation+0.049
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
000
Token000
Feature activation+0.037
Top resid features:
car
Token car
Feature activation+1.171
Top resid features:
in
Token in
Feature activation+0.089
Top resid features:
White
Token White
Feature activation+0.004
Top resid features:
horse
Tokenhorse
Feature activation+0.069
Top resid features:
for
Token for
Feature activation+0.311
Top resid features:
sale
Token sale
Feature activation+1.403
Top resid features:
by
Token by
Feature activation+0.823
Top resid features:
White
Token White
Feature activation-0.003
Top resid features:
horse
Tokenhorse
Feature activation+0.267
Top resid features:
Motors
Token Motors
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ford
Token Ford
Feature activation+0.318
Top resid features:
F
Token F
Feature activation+0.180
Top resid features:
-
Token-
Feature activation+0.044
Top resid features:
150
Token150
Feature activation+0.740
Top resid features:
being
Token being
Feature activation+0.397
Top resid features:
crowned
Token crowned
Feature activation+1.291
Top resid features:
T
Token T
Feature activation+0.241
Top resid features:
AW
TokenAW
Feature activation+0.132
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
2014
Token 2014
Feature activation+0.000
Top resid features:
ering
Tokenering
Feature activation+0.011
Top resid features:
array
Token array
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.192
Top resid features:
sport
Token sport
Feature activation+0.252
Top resid features:
utility
Token utility
Feature activation+0.227
Top resid features:
vehicles
Token vehicles
Feature activation+0.838
Top resid features:
roaming
Token roaming
Feature activation+0.717
Top resid features:
the
Token the
Feature activation+0.163
Top resid features:
field
Token field
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Even
Token Even
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.064
Top resid features:
fun
Token fun
Feature activation+0.530
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
easy
Token easy
Feature activation+0.138
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
drive
Token drive
Feature activation+0.817
Top resid features:
and
Token and
Feature activation+0.062
Top resid features:
simple
Token simple
Feature activation+0.486
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
maintain
Token maintain
Feature activation+0.275
Top resid features:
street
Token street
Feature activation+0.000
Top resid features:
early
Token early
Feature activation+0.070
Top resid features:
models
Token models
Feature activation+0.032
Top resid features:
had
Token had
Feature activation+0.336
Top resid features:
the
Token the
Feature activation+0.124
Top resid features:
optional
Token optional
Feature activation+0.763
Top resid features:
Electro
Token Electro
Feature activation+1.105
Top resid features:
Gy
Token Gy
Feature activation+0.204
Top resid features:
ro
Tokenro
Feature activation+0.839
Top resid features:
-
Token-
Feature activation+0.112
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
ator
Tokenator
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.095
Top resid features:
Ahead
Token Ahead
Feature activation+0.104
Top resid features:
Of
Token Of
Feature activation+0.592
Top resid features:
De
Token De
Feature activation+0.003
Top resid features:
but
Tokenbut
Feature activation+0.608
Top resid features:
At
Token At
Feature activation+1.125
Top resid features:
Frankfurt
Token Frankfurt
Feature activation+0.130
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
2018
Token2018
Feature activation+0.000
Top resid features:
BMW
Token BMW
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.04

Head 3: 0.37

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.05

Head 8: 0.12

Head 9: 0.03

Head 10: 0.05

Head 11: 0.09

Positive logits

cars7.00

Chevrolet6.98

dealership6.97

automotive6.83

Volvo6.70

vehicle6.67

SUV6.67

sedan6.67

automobile6.66

automobiles6.62

Veh6.60

Cars6.59

BMW6.58

driver6.57

vehicles6.56

car6.55

Vehicle6.51

Drivers6.51

motorcycles6.46

Porsche6.45

Negative logits

Psychiat-3.16

Meow-3.07

Hallow-2.99

fec-2.96

Jed-2.95

Osw-2.90

besie-2.85

crochet-2.84

Shattered-2.81

GamerGate-2.66

Bungie-2.65

Timbers-2.63

Solomon-2.62

PNG-2.62

Dumbledore-2.61

Mental-2.60

Patreon-2.60

Uri-2.58

Warcraft-2.57

Hearthstone-2.54

INTERVAL 3.871 - 4.301
CONTAINS 0.001%

Y
TokenY
Feature activation+0.000
is
Token is
Feature activation+0.057
an
Token an
Feature activation+0.574
Italian
Token Italian
Feature activation+2.528
ground
Token ground
Feature activation+1.717
-
Token-
Feature activation+4.154
attack
Tokenattack
Feature activation+1.770
and
Token and
Feature activation+0.955
reconnaissance
Token reconnaissance
Feature activation+2.635
aircraft
Token aircraft
Feature activation+1.180
which
Token which
Feature activation+0.182
1974
Token 1974
Feature activation+0.000
Fiat
Token Fiat
Feature activation+0.000
126
Token 126
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.609
Budapest
Token Budapest
Feature activation+4.217
last
Token last
Feature activation+0.021
year
Token year
Feature activation+0.608
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ford
Token Ford
Feature activation+2.106
's
Token's
Feature activation+0.554
Dear
Token Dear
Feature activation+0.000
born
Tokenborn
Feature activation+3.570
,
Token,
Feature activation+0.247
Michigan
Token Michigan
Feature activation+3.914
,
Token,
Feature activation+3.228
assembly
Token assembly
Feature activation+1.608
plant
Token plant
Feature activation+0.352
located
Token located
Feature activation+0.000
12
Token 12
Feature activation+1.542
would
Token would
Feature activation+0.229
be
Token be
Feature activation+0.983
cruising
Token cruising
Feature activation+0.000
silently
Token silently
Feature activation+0.664
on
Token on
Feature activation+0.492
German
Token German
Feature activation+3.942
streets
Token streets
Feature activation+0.302
by
Token by
Feature activation+0.000
2020
Token 2020
Feature activation+0.000
,
Token,
Feature activation+0.303
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.072
need
Token need
Feature activation+0.000
for
Token for
Feature activation+1.521
a
Token a
Feature activation+1.900
nationwide
Token nationwide
Feature activation+2.596
Super
Token Super
Feature activation+4.301
charg
Tokencharg
Feature activation+0.000
er
Tokener
Feature activation+0.841
network
Token network
Feature activation+0.896
.
Token.
Feature activation+0.000
Australia
Token Australia
Feature activation+0.359

INTERVAL 3.441 - 3.871
CONTAINS 0.001%

-
Token-
Feature activation+0.000
150
Token150
Feature activation+0.000
being
Token being
Feature activation+1.341
crowned
Token crowned
Feature activation+1.246
T
Token T
Feature activation+0.311
AW
TokenAW
Feature activation+3.523
A
TokenA
Feature activation+1.534
's
Token's
Feature activation+3.329
2014
Token 2014
Feature activation+2.048
"
Token "
Feature activation+2.882
T
TokenT
Feature activation+2.122
ocking
Tokenocking
Feature activation+0.036
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.341
miles
Token miles
Feature activation+1.353
annually
Token annually
Feature activation+3.552
can
Token can
Feature activation+1.168
save
Token save
Feature activation+0.538
âĤ¬
Token âĤ¬
Feature activation+0.000
6
Token6
Feature activation+0.000
,
Token,
Feature activation+0.000
elt
Tokenelt
Feature activation+0.184
aw
Tokenaw
Feature activation+0.000
ing
Tokening
Feature activation+0.000
-
Token-
Feature activation+0.000
That
TokenThat
Feature activation+0.724
-
Token-
Feature activation+3.661
T
TokenT
Feature activation+0.707
otally
Tokenotally
Feature activation+1.725
-
Token-
Feature activation+1.675
Isn
TokenIsn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
stands
Token stands
Feature activation+0.000
out
Token out
Feature activation+0.000
as
Token as
Feature activation+1.099
a
Token a
Feature activation+1.534
special
Token special
Feature activation+2.984
case
Token case
Feature activation+3.630
of
Token of
Feature activation+2.007
silence
Token silence
Feature activation+2.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.286
Ċ
TokenĊ
Feature activation+0.941
not
Token not
Feature activation+0.308
unlike
Token unlike
Feature activation+1.935
an
Token an
Feature activation+1.389
American
Token American
Feature activation+1.660
vice
Token vice
Feature activation+1.728
-
Token-
Feature activation+3.616
president
Tokenpresident
Feature activation+1.532
:
Token:
Feature activation+1.495
be
Token be
Feature activation+0.523
available
Token available
Feature activation+0.284
for
Token for
Feature activation+1.309

INTERVAL 3.011 - 3.441
CONTAINS 0.003%

hybrids
Token hybrids
Feature activation+0.456
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.955
on
Token on
Feature activation+1.526
the
Token the
Feature activation+3.324
market
Token market
Feature activation+0.596
long
Token long
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+1.120
A
TokenA
Feature activation+2.682
's
Token's
Feature activation+2.433
annual
Token annual
Feature activation+3.059
Excellence
Token Excellence
Feature activation+2.522
in
Token in
Feature activation+3.306
Craft
Token Craft
Feature activation+3.197
Competition
Token Competition
Feature activation+1.096
.
Token.
Feature activation+0.000
Last
Token Last
Feature activation+1.001
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+1.688
sized
Tokensized
Feature activation+0.000
,
Token,
Feature activation+0.000
six
Token six
Feature activation+0.026
-
Token-
Feature activation+0.248
person
Tokenperson
Feature activation+3.092
interior
Token interior
Feature activation+2.110
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.314
BMW
Token BMW
Feature activation+0.346
X
Token X
Feature activation+0.000
's
Token's
Feature activation+0.554
Dear
Token Dear
Feature activation+0.000
born
Tokenborn
Feature activation+3.570
,
Token,
Feature activation+0.247
Michigan
Token Michigan
Feature activation+3.914
,
Token,
Feature activation+3.228
assembly
Token assembly
Feature activation+1.608
plant
Token plant
Feature activation+0.352
located
Token located
Feature activation+0.000
12
Token 12
Feature activation+1.542
miles
Token miles
Feature activation+0.000
popular
Token popular
Feature activation+0.000
with
Token with
Feature activation+1.063
both
Token both
Feature activation+1.839
the
Token the
Feature activation+1.693
ultra
Token ultra
Feature activation+1.400
-
Token-
Feature activation+3.029
modern
Tokenmodern
Feature activation+1.640
/
Token/
Feature activation+2.892
super
Tokensuper
Feature activation+2.619
-
Token-
Feature activation+3.284
bike
Tokenbike
Feature activation+2.316

INTERVAL 2.581 - 3.011
CONTAINS 0.005%

refreshing
Token refreshing
Feature activation+0.000
ly
Tokenly
Feature activation+0.518
unique
Token unique
Feature activation+0.448
approach
Token approach
Feature activation+0.104
to
Token to
Feature activation+1.171
both
Token both
Feature activation+2.714
motorcycles
Token motorcycles
Feature activation+2.058
and
Token and
Feature activation+1.842
motorcycle
Token motorcycle
Feature activation+3.162
gear
Token gear
Feature activation+0.266
,
Token,
Feature activation+0.089
ed
Tokened
Feature activation+0.000
Ahead
Token Ahead
Feature activation+1.572
Of
Token Of
Feature activation+1.564
De
Token De
Feature activation+0.452
but
Tokenbut
Feature activation+2.378
At
Token At
Feature activation+2.935
Frankfurt
Token Frankfurt
Feature activation+3.408
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2018
Token2018
Feature activation+0.000
BMW
Token BMW
Feature activation+1.175
of
Token of
Feature activation+0.165
W
Token W
Feature activation+0.000
agon
Tokenagon
Feature activation+0.035
master
Tokenmaster
Feature activation+1.172
,
Token,
Feature activation+0.557
a
Token a
Feature activation+2.657
business
Token business
Feature activation+1.722
that
Token that
Feature activation+1.330
restores
Token restores
Feature activation+0.248
Jeep
Token Jeep
Feature activation+0.795
Wag
Token Wag
Feature activation+0.000
assembled
Tokenassembled
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.002
can
Token can
Feature activation+0.751
realistically
Token realistically
Feature activation+1.656
meet
Token meet
Feature activation+1.899
the
Token the
Feature activation+2.842
pact
Token pact
Feature activation+0.376
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.740
rules
Token rules
Feature activation+0.000
been
Token been
Feature activation+0.000
made
Token made
Feature activation+0.056
on
Token on
Feature activation+0.451
Can
Token Can
Feature activation+0.095
ep
Tokenep
Feature activation+1.714
a
Tokena
Feature activation+2.749
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.786
s
Tokens
Feature activation+1.545
ongoing
Token ongoing
Feature activation+2.574
restoration
Token restoration
Feature activation+0.000

INTERVAL 2.151 - 2.581
CONTAINS 0.011%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
car
Token car
Feature activation+0.151
out
Token out
Feature activation+0.000
of
Token of
Feature activation+2.247
the
Token the
Feature activation+3.096
snow
Token snow
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
2
Token2
Feature activation+0.255
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.067
m
Tokenm
Feature activation+2.115
the
Token the
Feature activation+2.395
mayor
Token mayor
Feature activation+0.000
of
Token of
Feature activation+0.381
London
Token London
Feature activation+1.952
claims
Token claims
Feature activation+1.131
it
Token it
Feature activation+1.808
and
Token and
Feature activation+0.000
more
Token more
Feature activation+1.092
young
Token young
Feature activation+1.587
people
Token people
Feature activation+0.000
discover
Token discover
Feature activation+1.137
car
Token car
Feature activation+2.381
culture
Token culture
Feature activation+0.060
through
Token through
Feature activation+2.047
the
Token the
Feature activation+2.331
internet
Token internet
Feature activation+0.579
,
Token,
Feature activation+2.529
are
Token are
Feature activation+0.000
among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.000
stars
Token stars
Feature activation+0.784
said
Token said
Feature activation+0.000
to
Token to
Feature activation+2.581
be
Token be
Feature activation+1.729
in
Token in
Feature activation+0.037
the
Token the
Feature activation+0.187
Avengers
Token Avengers
Feature activation+0.941
:
Token:
Feature activation+0.000
have
Token have
Feature activation+2.367
won
Token won
Feature activation+1.922
awards
Token awards
Feature activation+0.061
in
Token in
Feature activation+3.653
T
Token T
Feature activation+0.668
AW
TokenAW
Feature activation+2.200
A
TokenA
Feature activation+2.682
's
Token's
Feature activation+2.433
annual
Token annual
Feature activation+3.059
Excellence
Token Excellence
Feature activation+2.522
in
Token in
Feature activation+3.306

INTERVAL 1.721 - 2.151
CONTAINS 0.020%

March
Token March
Feature activation+0.000
9
Token 9
Feature activation+1.065
,
Token,
Feature activation+0.000
1964
Token 1964
Feature activation+1.041
at
Token at
Feature activation+0.000
Ford
Token Ford
Feature activation+2.106
's
Token's
Feature activation+0.554
Dear
Token Dear
Feature activation+0.000
born
Tokenborn
Feature activation+3.570
,
Token,
Feature activation+0.247
Michigan
Token Michigan
Feature activation+3.914
ango
Tokenango
Feature activation+0.000
can
Token can
Feature activation+1.436
carry
Token carry
Feature activation+1.478
enough
Token enough
Feature activation+2.199
10
Token 10
Feature activation+0.536
-
Token-
Feature activation+1.975
foot
Tokenfoot
Feature activation+1.617
2
Token 2
Feature activation+0.124
-
Token-
Feature activation+0.763
by
Tokenby
Feature activation+0.076
-
Token-
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
Group
Token Group
Feature activation+0.568
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.359
s
Tokens
Feature activation+0.000
coming
Token coming
Feature activation+1.811
Cent
Token Cent
Feature activation+0.171
enary
Tokenenary
Feature activation+1.594
,
Token,
Feature activation+1.040
as
Token as
Feature activation+0.129
a
Token a
Feature activation+1.271
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
horse
Token horse
Feature activation+0.000
-
Token-
Feature activation+1.846
tr
Tokentr
Feature activation+0.924
ading
Tokenading
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
corrupt
Token corrupt
Feature activation+0.000
keep
Token keep
Feature activation+1.793
oil
Token oil
Feature activation+0.000
surge
Token surge
Feature activation+0.000
under
Token under
Feature activation+0.091
control
Token control
Feature activation+0.000
during
Token during
Feature activation+1.852
hard
Token hard
Feature activation+3.031
corner
Token corner
Feature activation+0.808
ing
Tokening
Feature activation+0.623
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.555

INTERVAL 1.290 - 1.721
CONTAINS 0.044%

Ċ
TokenĊ
Feature activation+0.057
Autom
TokenAutom
Feature activation+0.000
ated
Tokenated
Feature activation+0.394
vehicles
Token vehicles
Feature activation+0.000
are
Token are
Feature activation+0.000
less
Token less
Feature activation+1.384
likely
Token likely
Feature activation+0.532
to
Token to
Feature activation+0.125
suffer
Token suffer
Feature activation+2.104
damage
Token damage
Feature activation+0.000
or
Token or
Feature activation+1.041
BMW
Token BMW
Feature activation+0.346
X
Token X
Feature activation+0.000
7
Token7
Feature activation+0.000
i
Token i
Feature activation+0.119
Performance
TokenPerformance
Feature activation+0.710
Concept
Token Concept
Feature activation+1.606
offers
Token offers
Feature activation+1.898
an
Token an
Feature activation+0.937
interior
Token interior
Feature activation+1.191
with
Token with
Feature activation+0.469
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
diesel
Token diesel
Feature activation+0.425
engine
Token engine
Feature activation+0.148
and
Token and
Feature activation+0.189
a
Token a
Feature activation+0.696
wooden
Token wooden
Feature activation+1.455
ship
Token ship
Feature activation+0.457
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.008
s
Tokens
Feature activation+0.638
wheel
Token wheel
Feature activation+0.000
and
Token and
Feature activation+0.088
the
Token the
Feature activation+0.262
creative
Token creative
Feature activation+0.276
way
Token way
Feature activation+0.902
Baker
Token Baker
Feature activation+2.026
promoted
Token promoted
Feature activation+1.394
the
Token the
Feature activation+1.159
brand
Token brand
Feature activation+0.251
and
Token and
Feature activation+0.710
the
Token the
Feature activation+1.381
vehicles
Token vehicles
Feature activation+1.193
a
Token a
Feature activation+0.456
post
Token post
Feature activation+0.000
telling
Token telling
Feature activation+0.245
of
Token of
Feature activation+0.149
a
Token a
Feature activation+0.614
large
Token large
Feature activation+1.480
collection
Token collection
Feature activation+0.000
of
Token of
Feature activation+0.720
Alf
Token Alf
Feature activation+0.000
as
Tokenas
Feature activation+0.450
for
Token for
Feature activation+0.147

INTERVAL 0.860 - 1.290
CONTAINS 0.084%

Which
Token Which
Feature activation+1.065
means
Token means
Feature activation+0.817
that
Token that
Feature activation+0.606
the
Token the
Feature activation+0.970
Hum
Token Hum
Feature activation+0.000
mer
Tokenmer
Feature activation+1.258
will
Token will
Feature activation+0.476
last
Token last
Feature activation+0.000
three
Token three
Feature activation+1.191
times
Token times
Feature activation+0.525
as
Token as
Feature activation+1.442
EU
Token EU
Feature activation+0.741
âĢĵ
Token âĢĵ
Feature activation+0.000
still
Token still
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
lower
Token lower
Feature activation+0.974
impact
Token impact
Feature activation+0.013
on
Token on
Feature activation+0.888
the
Token the
Feature activation+0.549
climate
Token climate
Feature activation+0.000
than
Token than
Feature activation+0.390
Solo
Token Solo
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
Charg
Token Charg
Feature activation+0.000
er
Tokener
Feature activation+0.252
/
Token /
Feature activation+1.214
Power
Token Power
Feature activation+0.687
Adapter
Token Adapter
Feature activation+0.308
,
Token,
Feature activation+0.590
90
Token 90
Feature activation+0.188
mm
Token mm
Feature activation+0.780
car
Token car
Feature activation+2.589
,
Token,
Feature activation+0.000
featuring
Token featuring
Feature activation+0.000
a
Token a
Feature activation+0.000
completely
Token completely
Feature activation+0.650
pre
Token pre
Feature activation+1.232
-
Token-
Feature activation+2.714
assembled
Tokenassembled
Feature activation+0.309
race
Token race
Feature activation+0.217
car
Token car
Feature activation+0.000
chassis
Token chassis
Feature activation+0.000
and
Token and
Feature activation+1.175
the
Token the
Feature activation+1.352
PT
Token PT
Feature activation+0.240
Cruz
Token Cruz
Feature activation+1.481
er
Tokener
Feature activation+1.990
,
Token,
Feature activation+0.875
to
Token to
Feature activation+0.927
last
Token last
Feature activation+0.812
year
Token year
Feature activation+0.113
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.698

INTERVAL 0.430 - 0.860
CONTAINS 0.176%

-
Token-
Feature activation+0.598
looking
Tokenlooking
Feature activation+2.473
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.215
attract
Token attract
Feature activation+0.737
a
Token a
Feature activation+0.775
younger
Token younger
Feature activation+1.559
crowd
Token crowd
Feature activation+0.334
to
Token to
Feature activation+0.000
auto
Token auto
Feature activation+2.099
racing
Token racing
Feature activation+0.588
transportation
Token transportation
Feature activation+0.000
."
Token."
Feature activation+0.000
S
Token S
Feature activation+0.000
igh
Tokenigh
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.588
Ċ
TokenĊ
Feature activation+0.088
More
TokenMore
Feature activation+0.869
Tree
Token Tree
Feature activation+0.085
Hug
TokenHug
Feature activation+0.000
ger
Tokenger
Feature activation+0.213
even
Token even
Feature activation+0.000
simpler
Token simpler
Feature activation+0.000
.
Token.
Feature activation+0.000
Use
Token Use
Feature activation+0.045
the
Token the
Feature activation+0.132
built
Token built
Feature activation+0.481
-
Token-
Feature activation+0.364
in
Tokenin
Feature activation+0.891
dial
Token dial
Feature activation+0.000
to
Token to
Feature activation+0.000
speed
Token speed
Feature activation+0.239
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
Motor
Token Motor
Feature activation+0.000
Mile
Token Mile
Feature activation+0.706
Speedway
Token Speedway
Feature activation+1.885
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.688
s
Tokens
Feature activation+0.467
rookie
Token rookie
Feature activation+0.553
flying
Token flying
Feature activation+0.536
car
Token car
Feature activation+0.380
,
Token,
Feature activation+0.174
the
Token the
Feature activation+0.184
Aero
Token Aero
Feature activation+0.776
Mobil
TokenMobil
Feature activation+0.500
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
despite
Token despite
Feature activation+0.286

INTERVAL 0.000 - 0.430
CONTAINS 99.655%

active
Token active
Feature activation+0.000
"
Token"
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
execution
Token execution
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
plant
Token plant
Feature activation+0.000
that
Token that
Feature activation+0.000
some
Token some
Feature activation+0.000
people
Token people
Feature activation+0.000
have
Token have
Feature activation+0.000
illegally
Token illegally
Feature activation+0.000
manipulated
Token manipulated
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
higher
Token higher
Feature activation+0.000
levels
Token levels
Feature activation+0.000
caused
Token caused
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
miss
Token miss
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
's
Token's
Feature activation+0.000
final
Token final
Feature activation+0.000
10
Token 10
Feature activation+0.000
games
Token games
Feature activation+0.000
of
Token of
Feature activation+0.000
through
Token through
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
connections
Token connections
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
escaped
Token escaped
Feature activation+0.000
custody
Token custody
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
Britons
Token Britons
Feature activation+0.000
living
Token living
Feature activation+0.000
abroad
Token abroad
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
worried
Token worried
Feature activation+0.000
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
status
Token status
Feature activation+0.000
once
Token once
Feature activation+0.000
Brexit
Token Brexit
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 H11.3: (feature 19818)

TOP ACTIVATIONS
MAX = 5.625

rushed
Token rushed
Feature activation+0.000
to
Token to
Feature activation+0.000
Sinai
Token Sinai
Feature activation+2.346
-
Token-
Feature activation+0.632
Gr
TokenGr
Feature activation+0.000
ace
Tokenace
Feature activation+5.625
Hospital
Token Hospital
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
est
Tokenest
Feature activation+0.623
het
Tokenhet
Feature activation+0.383
ist
Tokenist
Feature activation+0.000
at
Token at
Feature activation+1.008
Oxford
Token Oxford
Feature activation+3.589
University
Token University
Feature activation+5.408
Hosp
Token Hosp
Feature activation+0.000
itals
Tokenitals
Feature activation+0.611
and
Token and
Feature activation+0.540
lead
Token lead
Feature activation+1.444
author
Token author
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
West
Token West
Feature activation+2.039
Sub
Token Sub
Feature activation+0.000
urban
Tokenurban
Feature activation+5.372
Medical
Token Medical
Feature activation+0.000
Center
Token Center
Feature activation+0.000
and
Token and
Feature activation+0.000
transferred
Token transferred
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+1.804
deputy
Token deputy
Feature activation+2.931
chief
Token chief
Feature activation+2.240
executive
Token executive
Feature activation+0.605
of
Token of
Feature activation+1.778
York
Token York
Feature activation+3.860
Teaching
Token Teaching
Feature activation+2.401
Hospital
Token Hospital
Feature activation+2.769
NHS
Token NHS
Feature activation+0.676
Foundation
Token Foundation
Feature activation+0.260
Trust
Token Trust
Feature activation+2.138
care
Token care
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.143
Ali
Token Ali
Feature activation+2.355
For
Token For
Feature activation+1.865
ney
Tokenney
Feature activation+3.728
Center
Token Center
Feature activation+1.391
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
religious
Token religious
Feature activation+0.000
released
Token released
Feature activation+0.000
from
Token from
Feature activation+0.147
a
Token a
Feature activation+0.000
Sc
Token Sc
Feature activation+0.261
rant
Tokenrant
Feature activation+0.000
on
Tokenon
Feature activation+3.603
hospital
Token hospital
Feature activation+0.181
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.681
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
medical
Token medical
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
there
Token there
Feature activation+3.594
was
Token was
Feature activation+0.000
where
Token where
Feature activation+0.381
I
Token I
Feature activation+1.090
sought
Token sought
Feature activation+1.127
care
Token care
Feature activation+0.000
an
Token an
Feature activation+0.000
est
Tokenest
Feature activation+0.623
het
Tokenhet
Feature activation+0.383
ist
Tokenist
Feature activation+0.000
at
Token at
Feature activation+1.008
Oxford
Token Oxford
Feature activation+3.589
University
Token University
Feature activation+5.408
Hosp
Token Hosp
Feature activation+0.000
itals
Tokenitals
Feature activation+0.611
and
Token and
Feature activation+0.540
lead
Token lead
Feature activation+1.444
gastro
Token gastro
Feature activation+0.291
enter
Tokenenter
Feature activation+0.470
ologist
Tokenologist
Feature activation+0.278
in
Token in
Feature activation+0.257
Cork
Token Cork
Feature activation+1.682
University
Token University
Feature activation+3.537
Hospital
Token Hospital
Feature activation+1.786
,
Token,
Feature activation+1.715
warned
Token warned
Feature activation+0.666
Ms
Token Ms
Feature activation+0.000
T
Token T
Feature activation+0.000
support
Token support
Feature activation+0.000
and
Token and
Feature activation+0.000
later
Token later
Feature activation+0.000
died
Token died
Feature activation+0.000
at
Token at
Feature activation+1.452
the
Token the
Feature activation+3.534
hospital
Token hospital
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Johnson
TokenJohnson
Feature activation+0.221
founder
Token founder
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
chain
Token chain
Feature activation+1.621
Columbia
Token Columbia
Feature activation+3.451
/
Token/
Feature activation+0.783
H
TokenH
Feature activation+2.041
CA
TokenCA
Feature activation+3.212
,
Token,
Feature activation+0.210
spent
Token spent
Feature activation+0.000
and
Token and
Feature activation+0.000
intensive
Token intensive
Feature activation+1.419
care
Token care
Feature activation+0.040
at
Token at
Feature activation+0.507
the
Token the
Feature activation+1.733
University
Token University
Feature activation+3.415
Medical
Token Medical
Feature activation+3.059
Center
Token Center
Feature activation+1.145
in
Token in
Feature activation+0.286
Tucson
Token Tucson
Feature activation+1.796
in
Token in
Feature activation+0.000
officer
Token officer
Feature activation+0.091
of
Token of
Feature activation+2.053
the
Token the
Feature activation+1.554
North
Token North
Feature activation+0.948
West
Token West
Feature activation+3.061
London
Token London
Feature activation+3.293
collaboration
Token collaboration
Feature activation+2.046
of
Token of
Feature activation+2.599
clinical
Token clinical
Feature activation+1.075
commission
Token commission
Feature activation+0.803
ing
Tokening
Feature activation+1.161
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
in
Token in
Feature activation+0.003
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.021
festival
Token festival
Feature activation+3.243
's
Token's
Feature activation+1.527
medical
Token medical
Feature activation+0.467
tent
Token tent
Feature activation+0.870
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
chain
Token chain
Feature activation+1.621
Columbia
Token Columbia
Feature activation+3.451
/
Token/
Feature activation+0.783
H
TokenH
Feature activation+2.041
CA
TokenCA
Feature activation+3.212
,
Token,
Feature activation+0.210
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.000
73
Token73
Feature activation+0.000
million
Token million
Feature activation+0.000
dead
Token dead
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.426
scene
Token scene
Feature activation+0.000
by
Token by
Feature activation+0.233
Cherokee
Token Cherokee
Feature activation+3.157
County
Token County
Feature activation+1.378
Cor
Token Cor
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
Jeremy
Token Jeremy
Feature activation+0.000
De
Token De
Feature activation+0.000
chief
Token chief
Feature activation+2.086
officer
Token officer
Feature activation+0.091
of
Token of
Feature activation+2.053
the
Token the
Feature activation+1.554
North
Token North
Feature activation+0.948
West
Token West
Feature activation+3.061
London
Token London
Feature activation+3.293
collaboration
Token collaboration
Feature activation+2.046
of
Token of
Feature activation+2.599
clinical
Token clinical
Feature activation+1.075
commission
Token commission
Feature activation+0.803
intensive
Token intensive
Feature activation+1.419
care
Token care
Feature activation+0.040
at
Token at
Feature activation+0.507
the
Token the
Feature activation+1.733
University
Token University
Feature activation+3.415
Medical
Token Medical
Feature activation+3.059
Center
Token Center
Feature activation+1.145
in
Token in
Feature activation+0.286
Tucson
Token Tucson
Feature activation+1.796
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.133
lecturer
Token lecturer
Feature activation+0.813
at
Token at
Feature activation+0.915
the
Token the
Feature activation+1.362
University
Token University
Feature activation+1.423
of
Token of
Feature activation+0.000
Sheffield
Token Sheffield
Feature activation+3.058
said
Token said
Feature activation+0.189
:
Token:
Feature activation+0.054
"
Token "
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.221
Wichita
Token Wichita
Feature activation+2.385
Re
Token Re
Feature activation+0.617
formation
Tokenformation
Feature activation+2.853
Lutheran
Token Lutheran
Feature activation+2.989
Church
Token Church
Feature activation+1.636
in
Token in
Feature activation+0.000
Kansas
Token Kansas
Feature activation+0.224
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 5.549

-
Token-
Feature activation+0.001
Top resid features:
old
Tokenold
Feature activation+0.025
Top resid features:
boy
Token boy
Feature activation+0.052
Top resid features:
was
Token was
Feature activation+0.044
Top resid features:
rushed
Token rushed
Feature activation+0.478
Top resid features:
to
Token to
Feature activation+4.799
Top resid features:
Sinai
Token Sinai
Feature activation+0.772
Top resid features:
-
Token-
Feature activation+0.162
Top resid features:
Gr
TokenGr
Feature activation+0.013
Top resid features:
ace
Tokenace
Feature activation+0.200
Top resid features:
Hospital
Token Hospital
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
consultant
Token consultant
Feature activation+0.635
Top resid features:
an
Token an
Feature activation+0.066
Top resid features:
est
Tokenest
Feature activation+0.059
Top resid features:
het
Tokenhet
Feature activation+0.139
Top resid features:
ist
Tokenist
Feature activation+3.095
Top resid features:
at
Token at
Feature activation+1.049
Top resid features:
Oxford
Token Oxford
Feature activation+0.500
Top resid features:
University
Token University
Feature activation+0.135
Top resid features:
Hosp
Token Hosp
Feature activation+0.000
Top resid features:
itals
Tokenitals
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
The
Token The
Feature activation-0.011
Top resid features:
boy
Token boy
Feature activation+0.009
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
taken
Token taken
Feature activation+0.571
Top resid features:
to
Token to
Feature activation+5.549
Top resid features:
West
Token West
Feature activation+0.021
Top resid features:
Sub
Token Sub
Feature activation+0.006
Top resid features:
urban
Tokenurban
Feature activation+0.179
Top resid features:
Medical
Token Medical
Feature activation+0.000
Top resid features:
Center
Token Center
Feature activation+0.000
Top resid features:
ctor
Tokenctor
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.199
Top resid features:
deputy
Token deputy
Feature activation+0.100
Top resid features:
chief
Token chief
Feature activation+0.266
Top resid features:
executive
Token executive
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+2.410
Top resid features:
York
Token York
Feature activation+0.412
Top resid features:
Teaching
Token Teaching
Feature activation+0.000
Top resid features:
Hospital
Token Hospital
Feature activation+0.000
Top resid features:
NHS
Token NHS
Feature activation+0.000
Top resid features:
Foundation
Token Foundation
Feature activation+0.000
Top resid features:
young
Token young
Feature activation-0.018
Top resid features:
people
Token people
Feature activation-0.029
Top resid features:
who
Token who
Feature activation-0.001
Top resid features:
receive
Token receive
Feature activation+0.029
Top resid features:
care
Token care
Feature activation+1.010
Top resid features:
at
Token at
Feature activation+1.590
Top resid features:
the
Token the
Feature activation+1.196
Top resid features:
Ali
Token Ali
Feature activation+0.154
Top resid features:
For
Token For
Feature activation-0.003
Top resid features:
ney
Tokenney
Feature activation+0.819
Top resid features:
Center
Token Center
Feature activation+0.000
Top resid features:
rehabilitation
Token rehabilitation
Feature activation+0.042
Top resid features:
facility
Token facility
Feature activation+0.035
Top resid features:
after
Token after
Feature activation+0.044
Top resid features:
being
Token being
Feature activation+0.138
Top resid features:
released
Token released
Feature activation+0.056
Top resid features:
from
Token from
Feature activation+1.525
Top resid features:
a
Token a
Feature activation+1.247
Top resid features:
Sc
Token Sc
Feature activation+0.011
Top resid features:
rant
Tokenrant
Feature activation+0.011
Top resid features:
on
Tokenon
Feature activation+0.076
Top resid features:
hospital
Token hospital
Feature activation+0.000
Top resid features:
minor
Token minor
Feature activation-0.000
Top resid features:
medical
Token medical
Feature activation+0.041
Top resid features:
emergency
Token emergency
Feature activation+0.419
Top resid features:
,
Token,
Feature activation-0.031
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
hospital
Token hospital
Feature activation+4.510
Top resid features:
there
Token there
Feature activation+0.689
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
sought
Token sought
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
consultant
Token consultant
Feature activation+0.335
Top resid features:
an
Token an
Feature activation+0.133
Top resid features:
est
Tokenest
Feature activation+0.086
Top resid features:
het
Tokenhet
Feature activation+0.215
Top resid features:
ist
Tokenist
Feature activation+1.555
Top resid features:
at
Token at
Feature activation+1.197
Top resid features:
Oxford
Token Oxford
Feature activation+0.209
Top resid features:
University
Token University
Feature activation+0.000
Top resid features:
Hosp
Token Hosp
Feature activation+0.000
Top resid features:
itals
Tokenitals
Feature activation+0.000
Top resid features:
bie
Tokenbie
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.336
Top resid features:
a
Token a
Feature activation+0.354
Top resid features:
gastro
Token gastro
Feature activation+0.167
Top resid features:
enter
Tokenenter
Feature activation+0.079
Top resid features:
ologist
Tokenologist
Feature activation+2.220
Top resid features:
in
Token in
Feature activation+0.309
Top resid features:
Cork
Token Cork
Feature activation+0.190
Top resid features:
University
Token University
Feature activation+0.223
Top resid features:
Hospital
Token Hospital
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
girl
Token girl
Feature activation+0.011
Top resid features:
was
Token was
Feature activation+0.146
Top resid features:
placed
Token placed
Feature activation+0.875
Top resid features:
on
Token on
Feature activation+0.045
Top resid features:
life
Token life
Feature activation+0.008
Top resid features:
support
Token support
Feature activation+1.563
Top resid features:
and
Token and
Feature activation+0.214
Top resid features:
later
Token later
Feature activation+0.123
Top resid features:
died
Token died
Feature activation+0.495
Top resid features:
at
Token at
Feature activation+0.849
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
founder
Token founder
Feature activation+0.065
Top resid features:
of
Token of
Feature activation+0.136
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
hospital
Token hospital
Feature activation+1.299
Top resid features:
chain
Token chain
Feature activation+2.274
Top resid features:
Columbia
Token Columbia
Feature activation+0.208
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
CA
TokenCA
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
saving
Tokensaving
Feature activation+0.122
Top resid features:
surgery
Token surgery
Feature activation+0.467
Top resid features:
and
Token and
Feature activation+0.068
Top resid features:
intensive
Token intensive
Feature activation+0.089
Top resid features:
care
Token care
Feature activation+0.582
Top resid features:
at
Token at
Feature activation+1.587
Top resid features:
the
Token the
Feature activation+0.666
Top resid features:
University
Token University
Feature activation+0.114
Top resid features:
Medical
Token Medical
Feature activation+0.000
Top resid features:
Center
Token Center
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.150
Top resid features:
the
Token the
Feature activation+0.308
Top resid features:
chief
Token chief
Feature activation+0.049
Top resid features:
executive
Token executive
Feature activation+0.025
Top resid features:
of
Token of
Feature activation+0.209
Top resid features:
the
Token the
Feature activation+0.591
Top resid features:
trust
Token trust
Feature activation+0.092
Top resid features:
which
Token which
Feature activation+0.029
Top resid features:
runs
Token runs
Feature activation+0.167
Top resid features:
the
Token the
Feature activation+0.369
Top resid features:
hospital
Token hospital
Feature activation+0.112
Top resid features:
midday
Token midday
Feature activation+0.013
Top resid features:
he
Token he
Feature activation+0.065
Top resid features:
was
Token was
Feature activation+0.050
Top resid features:
taken
Token taken
Feature activation+0.803
Top resid features:
in
Token in
Feature activation+1.071
Top resid features:
to
Token to
Feature activation+1.188
Top resid features:
the
Token the
Feature activation+0.470
Top resid features:
festival
Token festival
Feature activation+0.186
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
medical
Token medical
Feature activation+0.000
Top resid features:
tent
Token tent
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
founder
Token founder
Feature activation+0.068
Top resid features:
of
Token of
Feature activation+0.100
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
hospital
Token hospital
Feature activation+0.886
Top resid features:
chain
Token chain
Feature activation+1.460
Top resid features:
Columbia
Token Columbia
Feature activation+0.507
Top resid features:
/
Token/
Feature activation+0.410
Top resid features:
H
TokenH
Feature activation+0.059
Top resid features:
CA
TokenCA
Feature activation+0.185
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
pronounced
Token pronounced
Feature activation+0.093
Top resid features:
dead
Token dead
Feature activation+0.357
Top resid features:
at
Token at
Feature activation+0.816
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
scene
Token scene
Feature activation+0.067
Top resid features:
by
Token by
Feature activation+2.266
Top resid features:
Cherokee
Token Cherokee
Feature activation+0.100
Top resid features:
County
Token County
Feature activation+0.000
Top resid features:
Cor
Token Cor
Feature activation+0.000
Top resid features:
oner
Tokenoner
Feature activation+0.000
Top resid features:
Jeremy
Token Jeremy
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.150
Top resid features:
the
Token the
Feature activation+0.220
Top resid features:
chief
Token chief
Feature activation+0.033
Top resid features:
executive
Token executive
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+0.273
Top resid features:
the
Token the
Feature activation+0.388
Top resid features:
trust
Token trust
Feature activation+0.108
Top resid features:
which
Token which
Feature activation+0.028
Top resid features:
runs
Token runs
Feature activation+0.190
Top resid features:
the
Token the
Feature activation+0.310
Top resid features:
hospital
Token hospital
Feature activation+0.254
Top resid features:
saving
Tokensaving
Feature activation+0.091
Top resid features:
surgery
Token surgery
Feature activation+0.122
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
intensive
Token intensive
Feature activation+0.087
Top resid features:
care
Token care
Feature activation+0.159
Top resid features:
at
Token at
Feature activation+1.022
Top resid features:
the
Token the
Feature activation+0.903
Top resid features:
University
Token University
Feature activation+0.542
Top resid features:
Medical
Token Medical
Feature activation+0.147
Top resid features:
Center
Token Center
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation+0.007
Top resid features:
ico
Tokenico
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.391
Top resid features:
senior
Token senior
Feature activation+0.153
Top resid features:
clinical
Token clinical
Feature activation+0.239
Top resid features:
lecturer
Token lecturer
Feature activation+0.804
Top resid features:
at
Token at
Feature activation+0.409
Top resid features:
the
Token the
Feature activation+0.433
Top resid features:
University
Token University
Feature activation+0.227
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
Sheffield
Token Sheffield
Feature activation+0.264
Top resid features:
while
Token while
Feature activation+0.008
Top resid features:
he
Token he
Feature activation+0.032
Top resid features:
attended
Token attended
Feature activation+0.210
Top resid features:
services
Token services
Feature activation+0.191
Top resid features:
at
Token at
Feature activation+1.139
Top resid features:
his
Token his
Feature activation+1.285
Top resid features:
Wichita
Token Wichita
Feature activation+0.164
Top resid features:
Re
Token Re
Feature activation+0.004
Top resid features:
formation
Tokenformation
Feature activation+0.379
Top resid features:
Lutheran
Token Lutheran
Feature activation+0.178
Top resid features:
Church
Token Church
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.03

Head 3: 0.35

Head 4: 0.04

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.18

Head 9: 0.03

Head 10: 0.06

Head 11: 0.09

Positive logits

Doctors7.90

Medical7.22

Patients7.17

patient7.15

physicians7.05

patients7.05

medical6.98

doctors6.94

hospital6.87

Doctors6.73

patient6.68

physician6.68

medical6.66

Medical6.65

Surgery6.62

Hospital6.49

Patient6.45

surgeons6.41

clinic6.36

hospitals6.35

Negative logits

piracy-2.82

Luffy-2.69

ocre-2.66

anarchy-2.64

Strongh-2.59

spo-2.53

sab-2.53

=-=--2.50

Riy-2.37

selector-2.35

insurrection-2.31

secession-2.30

IGN-2.28

trolling-2.28

espionage-2.26

rebell-2.25

rivalry-2.25

pirates-2.24

spoil-2.21

Fishing-2.20

INTERVAL 5.063 - 5.625
CONTAINS 0.000%

est
Tokenest
Feature activation+0.623
het
Tokenhet
Feature activation+0.383
ist
Tokenist
Feature activation+0.000
at
Token at
Feature activation+1.008
Oxford
Token Oxford
Feature activation+3.589
University
Token University
Feature activation+5.408
Hosp
Token Hosp
Feature activation+0.000
itals
Tokenitals
Feature activation+0.611
and
Token and
Feature activation+0.540
lead
Token lead
Feature activation+1.444
author
Token author
Feature activation+0.000
rushed
Token rushed
Feature activation+0.000
to
Token to
Feature activation+0.000
Sinai
Token Sinai
Feature activation+2.346
-
Token-
Feature activation+0.632
Gr
TokenGr
Feature activation+0.000
ace
Tokenace
Feature activation+5.625
Hospital
Token Hospital
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
West
Token West
Feature activation+2.039
Sub
Token Sub
Feature activation+0.000
urban
Tokenurban
Feature activation+5.372
Medical
Token Medical
Feature activation+0.000
Center
Token Center
Feature activation+0.000
and
Token and
Feature activation+0.000
transferred
Token transferred
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 4.500 - 5.063
CONTAINS 0.000%

INTERVAL 3.938 - 4.500
CONTAINS 0.000%

INTERVAL 3.375 - 3.938
CONTAINS 0.001%

founder
Token founder
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
chain
Token chain
Feature activation+1.621
Columbia
Token Columbia
Feature activation+3.451
/
Token/
Feature activation+0.783
H
TokenH
Feature activation+2.041
CA
TokenCA
Feature activation+3.212
,
Token,
Feature activation+0.210
spent
Token spent
Feature activation+0.000
,
Token,
Feature activation+1.804
deputy
Token deputy
Feature activation+2.931
chief
Token chief
Feature activation+2.240
executive
Token executive
Feature activation+0.605
of
Token of
Feature activation+1.778
York
Token York
Feature activation+3.860
Teaching
Token Teaching
Feature activation+2.401
Hospital
Token Hospital
Feature activation+2.769
NHS
Token NHS
Feature activation+0.676
Foundation
Token Foundation
Feature activation+0.260
Trust
Token Trust
Feature activation+2.138
gastro
Token gastro
Feature activation+0.291
enter
Tokenenter
Feature activation+0.470
ologist
Tokenologist
Feature activation+0.278
in
Token in
Feature activation+0.257
Cork
Token Cork
Feature activation+1.682
University
Token University
Feature activation+3.537
Hospital
Token Hospital
Feature activation+1.786
,
Token,
Feature activation+1.715
warned
Token warned
Feature activation+0.666
Ms
Token Ms
Feature activation+0.000
T
Token T
Feature activation+0.000
support
Token support
Feature activation+0.000
and
Token and
Feature activation+0.000
later
Token later
Feature activation+0.000
died
Token died
Feature activation+0.000
at
Token at
Feature activation+1.452
the
Token the
Feature activation+3.534
hospital
Token hospital
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Johnson
TokenJohnson
Feature activation+0.221
medical
Token medical
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
there
Token there
Feature activation+3.594
was
Token was
Feature activation+0.000
where
Token where
Feature activation+0.381
I
Token I
Feature activation+1.090
sought
Token sought
Feature activation+1.127
care
Token care
Feature activation+0.000

INTERVAL 2.813 - 3.375
CONTAINS 0.001%

,
Token,
Feature activation+0.399
the
Token the
Feature activation+0.339
college
Token college
Feature activation+1.615
's
Token's
Feature activation+1.390
associate
Token associate
Feature activation+2.796
vice
Token vice
Feature activation+2.847
president
Token president
Feature activation+1.584
of
Token of
Feature activation+1.960
Student
Token Student
Feature activation+0.709
Health
Token Health
Feature activation+0.659
,
Token,
Feature activation+1.432
chief
Token chief
Feature activation+2.086
officer
Token officer
Feature activation+0.091
of
Token of
Feature activation+2.053
the
Token the
Feature activation+1.554
North
Token North
Feature activation+0.948
West
Token West
Feature activation+3.061
London
Token London
Feature activation+3.293
collaboration
Token collaboration
Feature activation+2.046
of
Token of
Feature activation+2.599
clinical
Token clinical
Feature activation+1.075
commission
Token commission
Feature activation+0.803
intensive
Token intensive
Feature activation+1.419
care
Token care
Feature activation+0.040
at
Token at
Feature activation+0.507
the
Token the
Feature activation+1.733
University
Token University
Feature activation+3.415
Medical
Token Medical
Feature activation+3.059
Center
Token Center
Feature activation+1.145
in
Token in
Feature activation+0.286
Tucson
Token Tucson
Feature activation+1.796
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.133
dead
Token dead
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.426
scene
Token scene
Feature activation+0.000
by
Token by
Feature activation+0.233
Cherokee
Token Cherokee
Feature activation+3.157
County
Token County
Feature activation+1.378
Cor
Token Cor
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
Jeremy
Token Jeremy
Feature activation+0.000
De
Token De
Feature activation+0.000
lecturer
Token lecturer
Feature activation+0.813
at
Token at
Feature activation+0.915
the
Token the
Feature activation+1.362
University
Token University
Feature activation+1.423
of
Token of
Feature activation+0.000
Sheffield
Token Sheffield
Feature activation+3.058
said
Token said
Feature activation+0.189
:
Token:
Feature activation+0.054
"
Token "
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 2.250 - 2.813
CONTAINS 0.004%

bard
Tokenbard
Feature activation+0.000
,
Token,
Feature activation+0.399
the
Token the
Feature activation+0.339
college
Token college
Feature activation+1.615
's
Token's
Feature activation+1.390
associate
Token associate
Feature activation+2.796
vice
Token vice
Feature activation+2.847
president
Token president
Feature activation+1.584
of
Token of
Feature activation+1.960
Student
Token Student
Feature activation+0.709
Health
Token Health
Feature activation+0.659
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
specialty
Token specialty
Feature activation+0.000
in
Token in
Feature activation+1.652
either
Token either
Feature activation+2.040
child
Token child
Feature activation+2.410
abuse
Token abuse
Feature activation+2.249
,
Token,
Feature activation+2.110
ped
Token ped
Feature activation+0.646
iatrics
Tokeniatrics
Feature activation+0.389
,
Token,
Feature activation+2.862
care
Token care
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
toward
Token toward
Feature activation+0.000
accountable
Token accountable
Feature activation+0.000
-
Token-
Feature activation+2.460
care
Tokencare
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
which
Token which
Feature activation+0.000
board
Token board
Feature activation+1.192
member
Token member
Feature activation+0.988
of
Token of
Feature activation+1.776
Hosp
Token Hosp
Feature activation+0.000
ice
Tokenice
Feature activation+1.413
Halifax
Token Halifax
Feature activation+2.307
âĢĶ
Token âĢĶ
Feature activation+0.786
the
Token the
Feature activation+0.840
group
Token group
Feature activation+0.776
behind
Token behind
Feature activation+0.000
the
Token the
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.452
charity
Token charity
Feature activation+0.542
's
Token's
Feature activation+0.225
Old
Token Old
Feature activation+1.345
Windsor
Token Windsor
Feature activation+2.444
centre
Token centre
Feature activation+0.557
in
Token in
Feature activation+0.000
Berkshire
Token Berkshire
Feature activation+0.674
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000

INTERVAL 1.688 - 2.250
CONTAINS 0.012%

secret
Token secret
Feature activation+1.040
surgery
Token surgery
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.724
se
Token se
Feature activation+0.441
cluded
Tokencluded
Feature activation+1.722
ch
Token ch
Feature activation+0.118
ate
Tokenate
Feature activation+0.000
au
Tokenau
Feature activation+0.494
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Teaching
Token Teaching
Feature activation+2.401
Hospital
Token Hospital
Feature activation+2.769
NHS
Token NHS
Feature activation+0.676
Foundation
Token Foundation
Feature activation+0.260
Trust
Token Trust
Feature activation+2.138
which
Token which
Feature activation+2.173
runs
Token runs
Feature activation+1.723
Scarborough
Token Scarborough
Feature activation+2.307
Hospital
Token Hospital
Feature activation+2.030
,
Token,
Feature activation+0.841
said
Token said
Feature activation+1.930
the
Token the
Feature activation+0.790
1
Token 1
Feature activation+0.196
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.263
billion
Token billion
Feature activation+1.798
dollars
Token dollars
Feature activation+1.698
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.326
a
Token a
Feature activation+0.909
single
Token single
Feature activation+0.893
Mike
TokenMike
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
ctor
Tokenctor
Feature activation+2.336
,
Token,
Feature activation+1.804
deputy
Token deputy
Feature activation+2.931
chief
Token chief
Feature activation+2.240
executive
Token executive
Feature activation+0.605
of
Token of
Feature activation+1.778
York
Token York
Feature activation+3.860
Teaching
Token Teaching
Feature activation+2.401
Hospital
Token Hospital
Feature activation+2.769
Cow
Token Cow
Feature activation+0.000
an
Tokenan
Feature activation+1.085
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.090
criticised
Token criticised
Feature activation+0.000
by
Token by
Feature activation+2.139
the
Token the
Feature activation+1.598
chief
Token chief
Feature activation+1.604
executive
Token executive
Feature activation+0.000
of
Token of
Feature activation+2.182
the
Token the
Feature activation+1.381

INTERVAL 1.125 - 1.688
CONTAINS 0.041%

urs
Tokenurs
Feature activation+0.000
ing
Tokening
Feature activation+0.126
shortages
Token shortages
Feature activation+0.000
and
Token and
Feature activation+0.571
spir
Token spir
Feature activation+0.000
alling
Tokenalling
Feature activation+1.354
agency
Token agency
Feature activation+0.154
costs
Token costs
Feature activation+0.000
have
Token have
Feature activation+0.000
generated
Token generated
Feature activation+0.000
intense
Token intense
Feature activation+0.000
Harvard
Token Harvard
Feature activation+1.344
graduate
Token graduate
Feature activation+1.576
who
Token who
Feature activation+0.953
has
Token has
Feature activation+1.021
done
Token done
Feature activation+0.622
extensive
Token extensive
Feature activation+1.448
post
Token post
Feature activation+2.205
-
Token-
Feature activation+2.403
grad
Tokengrad
Feature activation+1.677
education
Token education
Feature activation+0.390
in
Token in
Feature activation+1.708
ating
Tokenating
Feature activation+0.628
required
Token required
Feature activation+0.000
surgery
Token surgery
Feature activation+0.000
and
Token and
Feature activation+0.030
about
Token about
Feature activation+0.000
12
Token 12
Feature activation+1.273
weeks
Token weeks
Feature activation+0.421
of
Token of
Feature activation+0.237
recovery
Token recovery
Feature activation+0.047
.
Token.
Feature activation+0.000
Baylor
Token Baylor
Feature activation+1.267
London
Token London
Feature activation+3.293
collaboration
Token collaboration
Feature activation+2.046
of
Token of
Feature activation+2.599
clinical
Token clinical
Feature activation+1.075
commission
Token commission
Feature activation+0.803
ing
Tokening
Feature activation+1.161
groups
Token groups
Feature activation+1.676
(
Token (
Feature activation+0.583
CC
TokenCC
Feature activation+0.000
G
TokenG
Feature activation+0.000
),
Token),
Feature activation+1.641
or
Tokenor
Feature activation+1.454
HC
Token HC
Feature activation+0.000
)
Token)
Feature activation+0.888
and
Token and
Feature activation+0.790
in
Token in
Feature activation+1.495
house
Token house
Feature activation+1.408
laboratory
Token laboratory
Feature activation+1.240
tests
Token tests
Feature activation+0.000
captured
Token captured
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.563 - 1.125
CONTAINS 0.130%

that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
his
Token his
Feature activation+0.000
six
Token six
Feature activation+0.101
-
Token-
Feature activation+0.989
month
Tokenmonth
Feature activation+0.000
MRI
Token MRI
Feature activation+0.000
on
Token on
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
health
Token health
Feature activation+0.000
start
Token start
Feature activation+0.000
-
Token-
Feature activation+0.750
up
Tokenup
Feature activation+0.960
from
Token from
Feature activation+0.686
a
Token a
Feature activation+0.404
former
Token former
Feature activation+0.538
Wired
Token Wired
Feature activation+0.415
editor
Token editor
Feature activation+0.000
underground
Token underground
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.786
keep
Token keep
Feature activation+0.418
patients
Token patients
Feature activation+0.713
safe
Token safe
Feature activation+0.278
from
Token from
Feature activation+0.678
aerial
Token aerial
Feature activation+0.000
families
Token families
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.319
Ċ
TokenĊ
Feature activation+0.000
Will
TokenWill
Feature activation+0.476
Williams
Token Williams
Feature activation+0.907
return
Token return
Feature activation+0.201
to
Token to
Feature activation+0.508
professional
Token professional
Feature activation+0.392
tennis
Token tennis
Feature activation+0.000
?
Token?
Feature activation+0.000
]
Token]
Feature activation+0.175
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.926
was
Token was
Feature activation+0.295
appointed
Token appointed
Feature activation+0.578
Phys
Token Phys
Feature activation+0.000
ician
Tokenician
Feature activation+0.321
to
Token to
Feature activation+0.598
the
Token the
Feature activation+0.868
President
Token President
Feature activation+0.000

INTERVAL 0.000 - 0.563
CONTAINS 99.810%

)
Token)
Feature activation+0.000
president
Token president
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
network
Token network
Feature activation+0.000
with
Token with
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.000
transactions
Token transactions
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
activated
Token activated
Feature activation+0.000
2
Token 2
Feature activation+0.000
MB
Token MB
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
Technology
Token Technology
Feature activation+0.000
can
Token can
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.000
making
Token making
Feature activation+0.000
cities
Token cities
Feature activation+0.000
more
Token more
Feature activation+0.000
live
Token live
Feature activation+0.000
able
Tokenable
Feature activation+0.000
foremost
Token foremost
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
other
Token other
Feature activation+0.000
players
Token players
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ond
Tokenond
Feature activation+0.000
sche
Tokensche
Feature activation+0.000
in
Tokenin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Son
Token Son
Feature activation+0.000
ata
Tokenata
Feature activation+0.000
Op
Token Op
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H11.3: (feature 2455)

TOP ACTIVATIONS
MAX = 4.678

ust
Tokenust
Feature activation+0.333
-
Token-
Feature activation+0.717
p
Tokenp
Feature activation+0.000
izza
Tokenizza
Feature activation+1.269
.
Token.
Feature activation+2.077
html
Tokenhtml
Feature activation+4.678
©
Token ©
Feature activation+1.668
Pl
TokenPl
Feature activation+0.000
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
five
Token five
Feature activation+0.713
-
Token-
Feature activation+2.146
a
Tokena
Feature activation+0.285
-
Token-
Feature activation+1.622
side
Tokenside
Feature activation+2.791
indoor
Token indoor
Feature activation+4.358
football
Token football
Feature activation+2.764
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Club
TokenClub
Feature activation+0.321
Pl
TokenPl
Feature activation+0.000
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
Inc
Token Inc
Feature activation+4.048
.
Token.
Feature activation+4.061
Ċ
TokenĊ
Feature activation+1.876
Ċ
TokenĊ
Feature activation+0.800
This
TokenThis
Feature activation+0.878
pizza
Token pizza
Feature activation+0.000
is
Token is
Feature activation+0.000
©
Token ©
Feature activation+1.668
Pl
TokenPl
Feature activation+0.000
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
Inc
Token Inc
Feature activation+4.048
.
Token.
Feature activation+4.061
Ċ
TokenĊ
Feature activation+1.876
Ċ
TokenĊ
Feature activation+0.800
This
TokenThis
Feature activation+0.878
pizza
Token pizza
Feature activation+0.000
Ra
Token Ra
Feature activation+0.300
is
Token is
Feature activation+1.227
a
Token a
Feature activation+2.096
taste
Token taste
Feature activation+0.700
of
Token of
Feature activation+1.049
Africa
Token Africa
Feature activation+4.014
with
Token with
Feature activation+0.663
salads
Token salads
Feature activation+0.000
and
Token and
Feature activation+0.174
dips
Token dips
Feature activation+0.797
served
Token served
Feature activation+0.566
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
extra
Token extra
Feature activation+0.000
kick
Token kick
Feature activation+2.647
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.000
Ċ
TokenĊ
Feature activation+1.674
Al
TokenAl
Feature activation+0.164
cohol
Tokencohol
Feature activation+0.774
ic
Tokenic
Feature activation+0.459
Bob
Token Bob
Feature activation+0.224
;
Token;
Feature activation+0.470
Bro
Token Bro
Feature activation+0.000
dy
Tokendy
Feature activation+2.037
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.074
s
Tokens
Feature activation+3.915
Br
Token Br
Feature activation+0.129
ats
Tokenats
Feature activation+2.222
,
Token,
Feature activation+0.000
grilled
Token grilled
Feature activation+0.000
br
Token br
Feature activation+0.075
salad
Token salad
Feature activation+0.000
competed
Token competed
Feature activation+0.000
in
Token in
Feature activation+1.179
the
Token the
Feature activation+1.764
Vegan
Token Vegan
Feature activation+3.673
Miscellaneous
Token Miscellaneous
Feature activation+3.900
division
Token division
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.158
awarded
Token awarded
Feature activation+0.000
extra
Token extra
Feature activation+0.702
ese
Tokenese
Feature activation+0.000
fond
Token fond
Feature activation+0.904
ue
Tokenue
Feature activation+1.249
;
Token;
Feature activation+0.921
Rolling
Token Rolling
Feature activation+1.474
Boulder
Token Boulder
Feature activation+3.733
Sl
Token Sl
Feature activation+0.327
iders
Tokeniders
Feature activation+1.909
,
Token,
Feature activation+0.593
three
Token three
Feature activation+0.790
spicy
Token spicy
Feature activation+0.000
rice
Token rice
Feature activation+0.000
salad
Token salad
Feature activation+0.000
competed
Token competed
Feature activation+0.000
in
Token in
Feature activation+1.179
the
Token the
Feature activation+1.764
Vegan
Token Vegan
Feature activation+3.673
Miscellaneous
Token Miscellaneous
Feature activation+3.900
division
Token division
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.158
awarded
Token awarded
Feature activation+0.000
to
Token to
Feature activation+0.000
Lose
Token Lose
Feature activation+0.000
Weight
Token Weight
Feature activation+1.029
with
Token with
Feature activation+0.000
Amazing
Token Amazing
Feature activation+0.621
Speed
Token Speed
Feature activation+3.626
Ċ
TokenĊ
Feature activation+0.965
Ċ
TokenĊ
Feature activation+0.324
30
Token30
Feature activation+0.506
Healthy
Token Healthy
Feature activation+1.783
Dinner
Token Dinner
Feature activation+0.363
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.898
Now
TokenNow
Feature activation+2.940
just
Token just
Feature activation+3.262
to
Token to
Feature activation+0.761
remind
Token remind
Feature activation+3.616
you
Token you
Feature activation+0.949
of
Token of
Feature activation+2.078
a
Token a
Feature activation+2.601
great
Token great
Feature activation+1.257
pant
Token pant
Feature activation+0.340
India
Token India
Feature activation+1.371
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.949
s
Tokens
Feature activation+1.348
instant
Token instant
Feature activation+0.629
-
Token-
Feature activation+3.595
n
Tokenn
Feature activation+1.128
oodle
Tokenoodle
Feature activation+0.000
market
Token market
Feature activation+0.229
and
Token and
Feature activation+0.631
is
Token is
Feature activation+0.000
dessert
Token dessert
Feature activation+2.285
overall
Token overall
Feature activation+1.695
in
Token in
Feature activation+0.516
the
Token the
Feature activation+0.565
Raw
Token Raw
Feature activation+0.918
Vegan
Token Vegan
Feature activation+3.525
category
Token category
Feature activation+0.508
,
Token,
Feature activation+0.375
and
Token and
Feature activation+0.045
dishes
Token dishes
Feature activation+0.000
such
Token such
Feature activation+0.000
German
Token German
Feature activation+2.408
Miche
Token Miche
Feature activation+0.000
lin
Tokenlin
Feature activation+1.168
-
Token-
Feature activation+0.000
star
Tokenstar
Feature activation+1.406
red
Tokenred
Feature activation+3.519
chef
Token chef
Feature activation+0.082
Ger
Token Ger
Feature activation+0.000
hard
Tokenhard
Feature activation+0.008
Sch
Token Sch
Feature activation+0.000
wa
Tokenwa
Feature activation+0.727
until
Token until
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
tender
Token tender
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.475
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
Add
Token Add
Feature activation+0.000
noodles
Token noodles
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Tokenyou
Feature activation+1.003
-
Token-
Feature activation+1.120
up
Tokenup
Feature activation+1.169
protein
Token protein
Feature activation+0.096
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.361
Ċ
TokenĊ
Feature activation+0.991
But
TokenBut
Feature activation+0.000
quite
Token quite
Feature activation+0.581
honestly
Token honestly
Feature activation+2.289
,
Token,
Feature activation+0.086
.
Token.
Feature activation+1.579
plain
Tokenplain
Feature activation+1.342
ch
Tokench
Feature activation+0.000
icken
Tokenicken
Feature activation+0.780
.
Token.
Feature activation+1.092
com
Tokencom
Feature activation+3.334
/
Token/
Feature activation+3.052
2012
Token2012
Feature activation+1.780
/
Token/
Feature activation+2.826
03
Token03
Feature activation+0.000
/
Token/
Feature activation+1.558
(
Token (
Feature activation+0.973
M
TokenM
Feature activation+0.000
RE
TokenRE
Feature activation+0.095
s
Tokens
Feature activation+0.230
)
Token)
Feature activation+0.758
armies
Token armies
Feature activation+3.293
are
Token are
Feature activation+1.402
equipped
Token equipped
Feature activation+0.114
with
Token with
Feature activation+0.544
while
Token while
Feature activation+0.221
on
Token on
Feature activation+0.137
soft
Token soft
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.480
my
Token my
Feature activation+0.958
post
Token post
Feature activation+3.280
Salt
Token Salt
Feature activation+0.000
Will
Token Will
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
Your
Token Your
Feature activation+2.068
Beans
Token Beans
Feature activation+1.027

Top DFA by src position
MAX = 4.126

,
Token,
Feature activation+0.536
Top resid features:
until
Token until
Feature activation+0.097
Top resid features:
cheese
Token cheese
Feature activation+0.038
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
melted
Token melted
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.771
Top resid features:
http
Token http
Feature activation+0.027
Top resid features:
://
Token://
Feature activation+0.026
Top resid features:
www
Tokenwww
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
plain
Tokenplain
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.748
Top resid features:
five
Token five
Feature activation+0.188
Top resid features:
-
Token-
Feature activation+0.068
Top resid features:
a
Tokena
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
side
Tokenside
Feature activation+3.374
Top resid features:
indoor
Token indoor
Feature activation+0.477
Top resid features:
football
Token football
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:
.
Token.
Feature activation+0.025
Top resid features:
html
Tokenhtml
Feature activation+0.220
Top resid features:
©
Token ©
Feature activation+0.300
Top resid features:
Pl
TokenPl
Feature activation+0.153
Top resid features:
ain
Tokenain
Feature activation+0.126
Top resid features:
Chicken
Token Chicken
Feature activation+0.518
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
Inc
Token Inc
Feature activation+0.135
Top resid features:
.
Token.
Feature activation+0.060
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
html
Tokenhtml
Feature activation+0.229
Top resid features:
©
Token ©
Feature activation+0.405
Top resid features:
Pl
TokenPl
Feature activation+0.045
Top resid features:
ain
Tokenain
Feature activation+0.153
Top resid features:
Chicken
Token Chicken
Feature activation+0.450
Top resid features:
,
Token,
Feature activation+0.115
Top resid features:
Inc
Token Inc
Feature activation+0.136
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:
;
Token;
Feature activation+0.398
Top resid features:
Sn
Token Sn
Feature activation+0.023
Top resid features:
ack
Tokenack
Feature activation+0.535
Top resid features:
of
Token of
Feature activation+0.530
Top resid features:
Ra
Token Ra
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.666
Top resid features:
a
Token a
Feature activation+0.437
Top resid features:
taste
Token taste
Feature activation+0.222
Top resid features:
of
Token of
Feature activation+0.569
Top resid features:
Africa
Token Africa
Feature activation+0.613
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.201
Top resid features:
pick
Token pick
Feature activation+0.070
Top resid features:
led
Tokenled
Feature activation+0.114
Top resid features:
mustard
Token mustard
Feature activation+0.155
Top resid features:
greens
Token greens
Feature activation+0.315
Top resid features:
.
Token.
Feature activation+0.691
Top resid features:
Add
Token Add
Feature activation+0.194
Top resid features:
chili
Token chili
Feature activation+0.206
Top resid features:
sauce
Token sauce
Feature activation+0.238
Top resid features:
for
Token for
Feature activation+0.122
Top resid features:
an
Token an
Feature activation+0.034
Top resid features:
with
Token with
Feature activation+0.074
Top resid features:
yogurt
Token yogurt
Feature activation+0.014
Top resid features:
sauce
Token sauce
Feature activation+0.008
Top resid features:
;
Token;
Feature activation+0.546
Top resid features:
Bro
Token Bro
Feature activation+0.172
Top resid features:
dy
Tokendy
Feature activation+1.209
Top resid features:
âĢ
TokenâĢ
Feature activation-0.055
Top resid features:
Ļ
TokenĻ
Feature activation+0.317
Top resid features:
s
Tokens
Feature activation+0.516
Top resid features:
Br
Token Br
Feature activation+0.000
Top resid features:
ats
Tokenats
Feature activation+0.000
Top resid features:
rice
Token rice
Feature activation+0.340
Top resid features:
salad
Token salad
Feature activation+0.136
Top resid features:
competed
Token competed
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.150
Top resid features:
Vegan
Token Vegan
Feature activation+0.564
Top resid features:
Miscellaneous
Token Miscellaneous
Feature activation+0.302
Top resid features:
division
Token division
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
awarded
Token awarded
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
che
Tokenche
Feature activation-0.004
Top resid features:
ese
Tokenese
Feature activation+0.039
Top resid features:
fond
Token fond
Feature activation+0.070
Top resid features:
ue
Tokenue
Feature activation+0.111
Top resid features:
;
Token;
Feature activation+0.821
Top resid features:
Rolling
Token Rolling
Feature activation+0.350
Top resid features:
Boulder
Token Boulder
Feature activation+0.614
Top resid features:
Sl
Token Sl
Feature activation+0.000
Top resid features:
iders
Tokeniders
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
corn
Token corn
Feature activation+0.195
Top resid features:
ch
Token ch
Feature activation+0.024
Top resid features:
owder
Tokenowder
Feature activation+0.499
Top resid features:
and
Token and
Feature activation+0.172
Top resid features:
wild
Token wild
Feature activation+0.090
Top resid features:
rice
Token rice
Feature activation+0.575
Top resid features:
salad
Token salad
Feature activation+0.294
Top resid features:
competed
Token competed
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.202
Top resid features:
Vegan
Token Vegan
Feature activation+0.209
Top resid features:
Healthy
Token Healthy
Feature activation+0.244
Top resid features:
Recipes
Token Recipes
Feature activation+0.971
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
Lose
Token Lose
Feature activation+0.060
Top resid features:
Weight
Token Weight
Feature activation+0.173
Top resid features:
with
Token with
Feature activation+1.753
Top resid features:
Amazing
Token Amazing
Feature activation+0.962
Top resid features:
Speed
Token Speed
Feature activation+0.276
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
30
Token30
Feature activation+0.000
Top resid features:
Fantastic
Token Fantastic
Feature activation+0.061
Top resid features:
St
Token St
Feature activation+0.050
Top resid features:
uffed
Tokenuffed
Feature activation+0.064
Top resid features:
Mush
Token Mush
Feature activation+0.239
Top resid features:
rooms
Tokenrooms
Feature activation+0.221
Top resid features:
!
Token!
Feature activation+1.136
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+1.003
Top resid features:
Now
TokenNow
Feature activation-0.181
Top resid features:
just
Token just
Feature activation-0.200
Top resid features:
to
Token to
Feature activation-0.154
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
India
Token India
Feature activation+0.107
Top resid features:
âĢ
TokenâĢ
Feature activation-0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.047
Top resid features:
instant
Token instant
Feature activation+4.126
Top resid features:
-
Token-
Feature activation+0.025
Top resid features:
n
Tokenn
Feature activation+0.000
Top resid features:
oodle
Tokenoodle
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
one
Tokenone
Feature activation+0.388
Top resid features:
dessert
Token dessert
Feature activation+0.061
Top resid features:
overall
Token overall
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.113
Top resid features:
the
Token the
Feature activation+0.246
Top resid features:
Raw
Token Raw
Feature activation+1.302
Top resid features:
Vegan
Token Vegan
Feature activation+0.205
Top resid features:
category
Token category
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:
dishes
Token dishes
Feature activation+0.000
Top resid features:
passion
Token passion
Feature activation+0.245
Top resid features:
fruit
Token fruit
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
all
Token all
Feature activation+0.141
Top resid features:
prepared
Token prepared
Feature activation+0.452
Top resid features:
by
Token by
Feature activation+0.882
Top resid features:
German
Token German
Feature activation+0.222
Top resid features:
Miche
Token Miche
Feature activation+0.027
Top resid features:
lin
Tokenlin
Feature activation+0.069
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
star
Tokenstar
Feature activation+0.046
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
add
Token add
Feature activation+0.025
Top resid features:
garlic
Token garlic
Feature activation+0.075
Top resid features:
and
Token and
Feature activation+0.132
Top resid features:
carrot
Token carrot
Feature activation+0.078
Top resid features:
.
Token.
Feature activation+0.525
Top resid features:
Sa
Token Sa
Feature activation+0.021
Top resid features:
ute
Tokenute
Feature activation+0.126
Top resid features:
until
Token until
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
garlic
Token garlic
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.014
Top resid features:
you
Tokenyou
Feature activation+0.012
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
up
Tokenup
Feature activation+0.030
Top resid features:
protein
Token protein
Feature activation+1.287
Top resid features:
.
Token.
Feature activation+2.121
Top resid features:
Ċ
TokenĊ
Feature activation+0.229
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation+0.000
Top resid features:
quite
Token quite
Feature activation+0.000
Top resid features:
honestly
Token honestly
Feature activation+0.000
Top resid features:
Bake
Token Bake
Feature activation+0.150
Top resid features:
8
Token 8
Feature activation+0.113
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
10
Token10
Feature activation+0.033
Top resid features:
minutes
Token minutes
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.484
Top resid features:
until
Token until
Feature activation+0.131
Top resid features:
cheese
Token cheese
Feature activation+0.048
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
melted
Token melted
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.375
Top resid features:
ready
Token ready
Feature activation+0.077
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
to
Tokento
Feature activation-0.020
Top resid features:
-
Token-
Feature activation-0.023
Top resid features:
eat
Tokeneat
Feature activation+0.184
Top resid features:
meals
Token meals
Feature activation+2.651
Top resid features:
(
Token (
Feature activation+0.053
Top resid features:
M
TokenM
Feature activation+0.010
Top resid features:
RE
TokenRE
Feature activation+0.040
Top resid features:
s
Tokens
Feature activation+0.021
Top resid features:
)
Token)
Feature activation+0.909
Top resid features:
I
TokenI
Feature activation-0.004
Top resid features:
never
Token never
Feature activation-0.006
Top resid features:
add
Token add
Feature activation-0.047
Top resid features:
salt
Token salt
Feature activation+0.054
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
beans
Token beans
Feature activation+0.772
Top resid features:
until
Token until
Feature activation+0.111
Top resid features:
they
Token they
Feature activation+0.137
Top resid features:
are
Token are
Feature activation+0.046
Top resid features:
almost
Token almost
Feature activation+0.001
Top resid features:
done
Token done
Feature activation+0.025
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.05

Head 2: 0.05

Head 3: 0.35

Head 4: 0.04

Head 5: 0.04

Head 6: 0.04

Head 7: 0.05

Head 8: 0.15

Head 9: 0.03

Head 10: 0.04

Head 11: 0.08

Positive logits

recipes6.51

food6.49

chefs6.45

culinary6.44

pastry6.39

chef6.37

Recipes6.36

cook6.26

Recipe6.24

Food6.12

meal6.11

delicious6.09

cooks6.08

foods6.04

sauces6.03

cooking6.01

Chef6.00

recipe5.99

cuisine5.99

desserts5.91

Negative logits

Limbaugh-2.95

yrights-2.87

Arkham-2.80

Assange-2.79

Lockheed-2.68

DACA-2.66

Gamergate-2.64

Weld-2.63

Reeves-2.62

seism-2.61

Activision-2.56

Fundamental-2.56

acknow-2.53

MLG-2.52

Engineers-2.50

Mehran-2.49

Moff-2.46

paramilitary-2.45

Spectre-2.44

BLM-2.44

INTERVAL 4.210 - 4.678
CONTAINS 0.000%

ust
Tokenust
Feature activation+0.333
-
Token-
Feature activation+0.717
p
Tokenp
Feature activation+0.000
izza
Tokenizza
Feature activation+1.269
.
Token.
Feature activation+2.077
html
Tokenhtml
Feature activation+4.678
©
Token ©
Feature activation+1.668
Pl
TokenPl
Feature activation+0.000
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
five
Token five
Feature activation+0.713
-
Token-
Feature activation+2.146
a
Tokena
Feature activation+0.285
-
Token-
Feature activation+1.622
side
Tokenside
Feature activation+2.791
indoor
Token indoor
Feature activation+4.358
football
Token football
Feature activation+2.764
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Club
TokenClub
Feature activation+0.321

INTERVAL 3.742 - 4.210
CONTAINS 0.001%

salad
Token salad
Feature activation+0.000
competed
Token competed
Feature activation+0.000
in
Token in
Feature activation+1.179
the
Token the
Feature activation+1.764
Vegan
Token Vegan
Feature activation+3.673
Miscellaneous
Token Miscellaneous
Feature activation+3.900
division
Token division
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.158
awarded
Token awarded
Feature activation+0.000
extra
Token extra
Feature activation+0.702
Ra
Token Ra
Feature activation+0.300
is
Token is
Feature activation+1.227
a
Token a
Feature activation+2.096
taste
Token taste
Feature activation+0.700
of
Token of
Feature activation+1.049
Africa
Token Africa
Feature activation+4.014
with
Token with
Feature activation+0.663
salads
Token salads
Feature activation+0.000
and
Token and
Feature activation+0.174
dips
Token dips
Feature activation+0.797
served
Token served
Feature activation+0.566
;
Token;
Feature activation+0.470
Bro
Token Bro
Feature activation+0.000
dy
Tokendy
Feature activation+2.037
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.074
s
Tokens
Feature activation+3.915
Br
Token Br
Feature activation+0.129
ats
Tokenats
Feature activation+2.222
,
Token,
Feature activation+0.000
grilled
Token grilled
Feature activation+0.000
br
Token br
Feature activation+0.075
Pl
TokenPl
Feature activation+0.000
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
Inc
Token Inc
Feature activation+4.048
.
Token.
Feature activation+4.061
Ċ
TokenĊ
Feature activation+1.876
Ċ
TokenĊ
Feature activation+0.800
This
TokenThis
Feature activation+0.878
pizza
Token pizza
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
extra
Token extra
Feature activation+0.000
kick
Token kick
Feature activation+2.647
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.000
Ċ
TokenĊ
Feature activation+1.674
Al
TokenAl
Feature activation+0.164
cohol
Tokencohol
Feature activation+0.774
ic
Tokenic
Feature activation+0.459
Bob
Token Bob
Feature activation+0.224

INTERVAL 3.274 - 3.742
CONTAINS 0.001%

you
Tokenyou
Feature activation+1.003
-
Token-
Feature activation+1.120
up
Tokenup
Feature activation+1.169
protein
Token protein
Feature activation+0.096
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.361
Ċ
TokenĊ
Feature activation+0.991
But
TokenBut
Feature activation+0.000
quite
Token quite
Feature activation+0.581
honestly
Token honestly
Feature activation+2.289
,
Token,
Feature activation+0.086
India
Token India
Feature activation+1.371
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.949
s
Tokens
Feature activation+1.348
instant
Token instant
Feature activation+0.629
-
Token-
Feature activation+3.595
n
Tokenn
Feature activation+1.128
oodle
Tokenoodle
Feature activation+0.000
market
Token market
Feature activation+0.229
and
Token and
Feature activation+0.631
is
Token is
Feature activation+0.000
soft
Token soft
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.480
my
Token my
Feature activation+0.958
post
Token post
Feature activation+3.280
Salt
Token Salt
Feature activation+0.000
Will
Token Will
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
Your
Token Your
Feature activation+2.068
Beans
Token Beans
Feature activation+1.027
.
Token.
Feature activation+1.579
plain
Tokenplain
Feature activation+1.342
ch
Tokench
Feature activation+0.000
icken
Tokenicken
Feature activation+0.780
.
Token.
Feature activation+1.092
com
Tokencom
Feature activation+3.334
/
Token/
Feature activation+3.052
2012
Token2012
Feature activation+1.780
/
Token/
Feature activation+2.826
03
Token03
Feature activation+0.000
/
Token/
Feature activation+1.558
rice
Token rice
Feature activation+0.000
salad
Token salad
Feature activation+0.000
competed
Token competed
Feature activation+0.000
in
Token in
Feature activation+1.179
the
Token the
Feature activation+1.764
Vegan
Token Vegan
Feature activation+3.673
Miscellaneous
Token Miscellaneous
Feature activation+3.900
division
Token division
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.158
awarded
Token awarded
Feature activation+0.000

INTERVAL 2.807 - 3.274
CONTAINS 0.003%

for
Token for
Feature activation+0.557
the
Token the
Feature activation+0.713
V
Token V
Feature activation+0.036
ibr
Tokenibr
Feature activation+0.607
ant
Tokenant
Feature activation+1.411
Vegan
Token Vegan
Feature activation+2.824
category
Token category
Feature activation+0.000
,
Token,
Feature activation+0.519
a
Token a
Feature activation+2.145
No
Token No
Feature activation+0.519
Bake
Token Bake
Feature activation+1.615
lingu
Token lingu
Feature activation+0.000
ine
Tokenine
Feature activation+1.077
or
Token or
Feature activation+0.000
pasta
Token pasta
Feature activation+0.553
of
Token of
Feature activation+0.000
choice
Token choice
Feature activation+2.894
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.223
deep
Token deep
Feature activation+0.000
skillet
Token skillet
Feature activation+0.000
add
Token add
Feature activation+0.000
Bulgar
Token Bulgar
Feature activation+0.245
Salad
Token Salad
Feature activation+0.229
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.169
I
Token I
Feature activation+1.154
never
Token never
Feature activation+2.847
know
Token know
Feature activation+0.100
how
Token how
Feature activation+1.409
to
Token to
Feature activation+0.557
pronounce
Token pronounce
Feature activation+1.129
bul
Token bul
Feature activation+0.000
icken
Tokenicken
Feature activation+0.780
.
Token.
Feature activation+1.092
com
Tokencom
Feature activation+3.334
/
Token/
Feature activation+3.052
2012
Token2012
Feature activation+1.780
/
Token/
Feature activation+2.826
03
Token03
Feature activation+0.000
/
Token/
Feature activation+1.558
whe
Tokenwhe
Feature activation+0.000
res
Tokenres
Feature activation+0.328
-
Token-
Feature activation+0.400
,
Token,
Feature activation+0.229
and
Token and
Feature activation+0.044
shopping
Token shopping
Feature activation+0.849
for
Token for
Feature activation+2.397
their
Token their
Feature activation+2.403
first
Token first
Feature activation+3.122
cooker
Token cooker
Feature activation+1.456
often
Token often
Feature activation+0.000
ask
Token ask
Feature activation+1.412
me
Token me
Feature activation+1.726
if
Token if
Feature activation+1.231

INTERVAL 2.339 - 2.807
CONTAINS 0.006%

T
Token T
Feature activation+0.000
-
Token-
Feature activation+0.000
Loc
TokenLoc
Feature activation+0.052
's
Token's
Feature activation+1.213
Son
Token Son
Feature activation+0.000
ora
Tokenora
Feature activation+2.646
Hot
Token Hot
Feature activation+0.000
Dogs
Token Dogs
Feature activation+1.215
(
Token (
Feature activation+0.000
T
TokenT
Feature activation+0.000
LS
TokenLS
Feature activation+0.285
and
Token and
Feature activation+0.000
cheese
Token cheese
Feature activation+0.000
bisc
Token bisc
Feature activation+0.000
uit
Tokenuit
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+2.780
of
Token of
Feature activation+3.131
those
Token those
Feature activation+2.342
fast
Token fast
Feature activation+0.000
food
Token food
Feature activation+0.426
places
Token places
Feature activation+0.472
cooking
Token cooking
Feature activation+0.113
,
Token,
Feature activation+0.229
and
Token and
Feature activation+0.044
shopping
Token shopping
Feature activation+0.849
for
Token for
Feature activation+2.397
their
Token their
Feature activation+2.403
first
Token first
Feature activation+3.122
cooker
Token cooker
Feature activation+1.456
often
Token often
Feature activation+0.000
ask
Token ask
Feature activation+1.412
me
Token me
Feature activation+1.726
won
Token won
Feature activation+0.609
big
Token big
Feature activation+1.090
at
Token at
Feature activation+0.581
the
Token the
Feature activation+0.493
Iowa
Token Iowa
Feature activation+1.762
State
Token State
Feature activation+2.386
Fair
Token Fair
Feature activation+1.644
!
Token!
Feature activation+0.000
Anna
Token Anna
Feature activation+0.000
Star
Token Star
Feature activation+0.089
ost
Tokenost
Feature activation+0.000
agus
Tokenagus
Feature activation+0.974
soup
Token soup
Feature activation+0.009
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
many
Token many
Feature activation+1.656
of
Token of
Feature activation+2.654
my
Token my
Feature activation+2.423
favorite
Token favorite
Feature activation+2.239
foods
Token foods
Feature activation+0.000
,
Token,
Feature activation+0.000
uses
Token uses
Feature activation+0.000

INTERVAL 1.871 - 2.339
CONTAINS 0.012%

sweetness
Token sweetness
Feature activation+0.000
.
Token.
Feature activation+0.461
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.497
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.944
My
TokenMy
Feature activation+1.632
goal
Token goal
Feature activation+0.832
for
Token for
Feature activation+2.499
this
Token this
Feature activation+2.315
project
Token project
Feature activation+0.424
$
Token $
Feature activation+0.000
0
Token0
Feature activation+0.000
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.587
Ċ
TokenĊ
Feature activation+1.908
It
TokenIt
Feature activation+0.993
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.449
s
Tokens
Feature activation+0.336
pretty
Token pretty
Feature activation+1.213
ain
Tokenain
Feature activation+0.101
Chicken
Token Chicken
Feature activation+1.634
,
Token,
Feature activation+2.211
Inc
Token Inc
Feature activation+4.048
.
Token.
Feature activation+4.061
Ċ
TokenĊ
Feature activation+1.876
Ċ
TokenĊ
Feature activation+0.800
This
TokenThis
Feature activation+0.878
pizza
Token pizza
Feature activation+0.000
is
Token is
Feature activation+0.000
low
Token low
Feature activation+0.305
project
Token project
Feature activation+0.424
from
Token from
Feature activation+2.770
the
Token the
Feature activation+2.787
very
Token very
Feature activation+2.295
beginning
Token beginning
Feature activation+0.188
was
Token was
Feature activation+1.899
to
Token to
Feature activation+0.341
take
Token take
Feature activation+1.840
an
Token an
Feature activation+1.993
exp
Token exp
Feature activation+0.623
ository
Tokenository
Feature activation+2.044
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
mes
Tokenmes
Feature activation+0.000
an
Tokenan
Feature activation+0.000
cheese
Token cheese
Feature activation+0.289
.
Token.
Feature activation+0.288
Ċ
TokenĊ
Feature activation+1.957
Ċ
TokenĊ
Feature activation+1.220
The
TokenThe
Feature activation+1.106
Best
Token Best
Feature activation+2.596
Cream
Token Cream
Feature activation+1.606
y
Tokeny
Feature activation+1.874

INTERVAL 1.403 - 1.871
CONTAINS 0.030%

day
Token day
Feature activation+1.187
courtesy
Token courtesy
Feature activation+0.776
of
Token of
Feature activation+0.968
Geek
Token Geek
Feature activation+1.642
Feed
TokenFeed
Feature activation+1.230
er
Tokener
Feature activation+1.595
and
Token and
Feature activation+0.900
our
Token our
Feature activation+0.974
fabulous
Token fabulous
Feature activation+0.728
sponsors
Token sponsors
Feature activation+1.752
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.402
)
Token)
Feature activation+1.385
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.352
For
TokenFor
Feature activation+0.219
more
Token more
Feature activation+1.752
recipes
Token recipes
Feature activation+0.000
follow
Token follow
Feature activation+1.423
me
Token me
Feature activation+1.601
on
Token on
Feature activation+1.850
Pinterest
Token Pinterest
Feature activation+1.120
with
Token with
Feature activation+0.000
infinite
Token infinite
Feature activation+1.009
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.906
variations
Token variations
Feature activation+0.080
and
Token and
Feature activation+1.488
flavor
Token flavor
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
,
Token,
Feature activation+0.474
but
Token but
Feature activation+0.000
few
Token few
Feature activation+2.061
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+1.060
want
Token want
Feature activation+0.448
my
Token my
Feature activation+2.301
mom
Token mom
Feature activation+0.478
my
Tokenmy
Feature activation+1.416
now
Token now
Feature activation+0.574
.
Token.
Feature activation+0.318
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Can
TokenCan
Feature activation+0.000
and
Token and
Feature activation+0.634
flavour
Token flavour
Feature activation+0.000
ful
Tokenful
Feature activation+0.967
,
Token,
Feature activation+0.255
the
Token the
Feature activation+0.915
rural
Token rural
Feature activation+1.597
Thai
Token Thai
Feature activation+2.422
approach
Token approach
Feature activation+1.663
to
Token to
Feature activation+1.842
cooking
Token cooking
Feature activation+1.164
pays
Token pays
Feature activation+0.823

INTERVAL 0.936 - 1.403
CONTAINS 0.065%

areas
Token areas
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.005
to
Token to
Feature activation+0.518
wide
Token wide
Feature activation+1.104
ranges
Token ranges
Feature activation+0.252
of
Token of
Feature activation+1.377
chees
Token chees
Feature activation+0.000
es
Tokenes
Feature activation+0.000
,
Token,
Feature activation+0.617
meats
Token meats
Feature activation+0.000
,
Token,
Feature activation+1.122
!
Token!
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.174
how
Token how
Feature activation+1.594
could
Token could
Feature activation+0.995
I
Token I
Feature activation+1.390
possibly
Token possibly
Feature activation+1.036
go
Token go
Feature activation+0.513
so
Token so
Feature activation+2.215
long
Token long
Feature activation+0.263
without
Token without
Feature activation+0.506
well
Token well
Feature activation+0.548
and
Token and
Feature activation+0.000
can
Token can
Feature activation+0.000
make
Token make
Feature activation+0.000
morning
Token morning
Feature activation+0.000
hours
Token hours
Feature activation+0.943
food
Token food
Feature activation+0.000
more
Token more
Feature activation+0.377
filling
Token filling
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
jar
Token jar
Feature activation+0.586
/
Token/
Feature activation+1.050
v
Tokenv
Feature activation+0.000
otive
Tokenotive
Feature activation+1.253
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.147
working
Token working
Feature activation+0.000
your
Token your
Feature activation+0.408
mouth
Token mouth
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
carrots
Token carrots
Feature activation+0.000
lend
Token lend
Feature activation+1.022
a
Token a
Feature activation+0.516
gorgeous
Token gorgeous
Feature activation+1.336
pop
Token pop
Feature activation+1.084
of
Token of
Feature activation+2.019
colour
Token colour
Feature activation+0.000

INTERVAL 0.468 - 0.936
CONTAINS 0.143%

city
Token city
Feature activation+1.488
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.074
s
Tokens
Feature activation+0.569
meal
Token meal
Feature activation+0.000
program
Token program
Feature activation+0.716
.
Token.
Feature activation+0.000
Since
Token Since
Feature activation+0.000
then
Token then
Feature activation+0.493
,
Token,
Feature activation+0.095
one
Token one
Feature activation+0.000
meal
Token meal
Feature activation+0.274
on
Token on
Feature activation+0.710
Wednesday
Token Wednesday
Feature activation+1.601
evening
Token evening
Feature activation+1.190
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.846
it
Token it
Feature activation+0.000
emerged
Token emerged
Feature activation+0.226
doctors
Token doctors
Feature activation+0.000
battled
Token battled
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+0.000
Stir
Token Stir
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.846
Ċ
TokenĊ
Feature activation+0.500
|
Token|
Feature activation+0.977
If
Token If
Feature activation+0.288
you
Token you
Feature activation+0.128
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
taste
Token taste
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.238
daily
Token daily
Feature activation+0.610
commute
Token commute
Feature activation+0.595
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
C
Token C
Feature activation+0.000
resp
Tokenresp
Feature activation+0.000
the
Token the
Feature activation+0.317
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.926
a
Token a
Feature activation+1.292
mobile
Token mobile
Feature activation+1.440
phone
Token phone
Feature activation+0.916
application
Token application
Feature activation+0.316
(
Token (
Feature activation+0.046
Figure
TokenFigure
Feature activation+0.000
1
Token 1
Feature activation+0.000
).
Token).
Feature activation+0.000

INTERVAL 0.000 - 0.468
CONTAINS 99.740%

,
Token,
Feature activation+0.000
Metro
Token Metro
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
x
Tokenx
Feature activation+0.000
says
Token says
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
brand
Token brand
Feature activation+0.000
new
Token new
Feature activation+0.000
generation
Token generation
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
standard
Token standard
Feature activation+0.000
cos
Token cos
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
loan
Token loan
Feature activation+0.000
striker
Token striker
Feature activation+0.000
Jay
Token Jay
Feature activation+0.000
Emmanuel
Token Emmanuel
Feature activation+0.000
-
Token-
Feature activation+0.000
Thomas
TokenThomas
Feature activation+0.000
Picture
Token Picture
Feature activation+0.000
=
Token=
Feature activation+0.000
3
Token3
Feature activation+0.000
D
TokenD
Feature activation+0.000
"
Token"
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
to
Tokento
Feature activation+0.000
:
Token:
Feature activation+0.000
john
Tokenjohn
Feature activation+0.000
.
Token.
Feature activation+0.000
pod
Tokenpod
Feature activation+0.000
esta
Tokenesta
Feature activation+0.000
4
Token 4
Feature activation+0.000
2
Token 2
Feature activation+0.000
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
41
Token41
Feature activation+0.000
Ole
Token Ole
Feature activation+0.000
Miss
Token Miss
Feature activation+0.000
7
Token 7
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
4
Token 4
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 H11.3: (feature 12657)

TOP ACTIVATIONS
MAX = 4.276

conducting
Token conducting
Feature activation+1.898
an
Token an
Feature activation+1.804
internal
Token internal
Feature activation+2.330
review
Token review
Feature activation+0.000
after
Token after
Feature activation+1.782
one
Token one
Feature activation+4.276
of
Token of
Feature activation+1.634
its
Token its
Feature activation+1.732
white
Token white
Feature activation+2.296
police
Token police
Feature activation+1.259
officers
Token officers
Feature activation+0.719
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
University
Token University
Feature activation+0.986
of
Token of
Feature activation+0.315
Wag
Token Wag
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
en
Tokenen
Feature activation+3.674
at
Token at
Feature activation+0.114
the
Token the
Feature activation+0.326
request
Token request
Feature activation+0.000
of
Token of
Feature activation+1.453
the
Token the
Feature activation+1.579
oyer
Tokenoyer
Feature activation+0.539
of
Token of
Feature activation+0.675
the
Token the
Feature activation+1.402
School
Token School
Feature activation+1.328
Without
Token Without
Feature activation+0.754
Walls
Token Walls
Feature activation+3.557
in
Token in
Feature activation+0.703
the
Token the
Feature activation+1.182
District
Token District
Feature activation+1.805
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+1.211
istic
Tokenistic
Feature activation+0.093
tuition
Token tuition
Feature activation+0.206
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.377
Bond
Token Bond
Feature activation+2.456
Street
Token Street
Feature activation+3.458
rooms
Token rooms
Feature activation+1.154
of
Token of
Feature activation+0.645
former
Token former
Feature activation+0.972
pri
Token pri
Feature activation+0.000
z
Tokenz
Feature activation+0.000
West
Token West
Feature activation+0.712
O
Token O
Feature activation+0.331
ahu
Tokenahu
Feature activation+1.581
and
Token and
Feature activation+0.755
U
Token U
Feature activation+0.300
H
TokenH
Feature activation+3.386
H
Token H
Feature activation+1.226
ilo
Tokenilo
Feature activation+3.069
,
Token,
Feature activation+1.298
but
Token but
Feature activation+1.767
several
Token several
Feature activation+2.301
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
students
Token students
Feature activation+0.000
at
Token at
Feature activation+0.558
Bethlehem
Token Bethlehem
Feature activation+2.722
Central
Token Central
Feature activation+3.384
High
Token High
Feature activation+0.842
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
class
Token class
Feature activation+0.000
at
Token at
Feature activation+0.000
John
Token John
Feature activation+0.501
F
Token F
Feature activation+0.738
.
Token.
Feature activation+1.956
Kennedy
Token Kennedy
Feature activation+3.369
High
Token High
Feature activation+0.569
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
decided
Token decided
Feature activation+0.000
its
Token its
Feature activation+1.732
white
Token white
Feature activation+2.296
police
Token police
Feature activation+1.259
officers
Token officers
Feature activation+0.719
handcuffed
Token handcuffed
Feature activation+2.243
a
Token a
Feature activation+3.349
black
Token black
Feature activation+2.965
man
Token man
Feature activation+1.184
who
Token who
Feature activation+0.927
had
Token had
Feature activation+0.000
just
Token just
Feature activation+0.000
and
Token and
Feature activation+1.064
Sciences
Token Sciences
Feature activation+1.836
Registrar
Token Registrar
Feature activation+0.554
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.395
s
Tokens
Feature activation+3.304
Office
Token Office
Feature activation+0.371
on
Token on
Feature activation+0.525
Wednesday
Token Wednesday
Feature activation+0.309
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.780
The
TokenThe
Feature activation+1.244
February
Token February
Feature activation+2.013
issue
Token issue
Feature activation+1.316
of
Token of
Feature activation+3.264
Hawaii
Token Hawaii
Feature activation+2.668
Business
Token Business
Feature activation+0.413
had
Token had
Feature activation+0.541
an
Token an
Feature activation+0.202
article
Token article
Feature activation+0.000
physics
Token physics
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
at
Token at
Feature activation+0.185
Ross
Token Ross
Feature activation+0.220
She
Token She
Feature activation+0.000
ppard
Tokenppard
Feature activation+3.223
High
Token High
Feature activation+1.441
School
Token School
Feature activation+1.132
,
Token,
Feature activation+0.245
was
Token was
Feature activation+0.164
suspended
Token suspended
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.672
University
Token University
Feature activation+0.624
of
Token of
Feature activation+0.000
Reading
Token Reading
Feature activation+3.220
grew
Token grew
Feature activation+0.935
a
Token a
Feature activation+1.714
similar
Token similar
Feature activation+1.565
culture
Token culture
Feature activation+0.106
that
Token that
Feature activation+0.000
transferred
Token transferred
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+1.148
Old
Token Old
Feature activation+1.175
Or
Token Or
Feature activation+0.473
chard
Tokenchard
Feature activation+3.193
Beach
Token Beach
Feature activation+2.586
-
Token-
Feature activation+0.898
S
TokenS
Feature activation+0.078
aco
Tokenaco
Feature activation+2.495
alternative
Token alternative
Feature activation+2.450
course
Token course
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.118
s
Tokens
Feature activation+1.156
30
Token 30
Feature activation+1.672
-
Token-
Feature activation+3.152
year
Tokenyear
Feature activation+1.881
history
Token history
Feature activation+0.102
and
Token and
Feature activation+0.313
the
Token the
Feature activation+0.586
largest
Token largest
Feature activation+0.000
ordered
Token ordered
Feature activation+1.825
Pi
Token Pi
Feature activation+0.000
Kappa
Token Kappa
Feature activation+0.000
Alpha
Token Alpha
Feature activation+1.572
to
Token to
Feature activation+0.201
cease
Token cease
Feature activation+3.143
and
Token and
Feature activation+0.157
des
Token des
Feature activation+0.000
ist
Tokenist
Feature activation+2.588
all
Token all
Feature activation+2.535
fraternity
Token fraternity
Feature activation+1.040
students
Token students
Feature activation+0.000
she
Token she
Feature activation+1.260
studied
Token studied
Feature activation+1.257
alongside
Token alongside
Feature activation+0.926
in
Token in
Feature activation+0.390
Austria
Token Austria
Feature activation+3.115
had
Token had
Feature activation+0.628
ended
Token ended
Feature activation+0.799
up
Token up
Feature activation+0.676
serious
Token serious
Feature activation+0.725
conduct
Token conduct
Feature activation+0.000
The
TokenThe
Feature activation+0.031
principal
Token principal
Feature activation+0.000
of
Token of
Feature activation+0.188
William
Token William
Feature activation+0.307
Cullen
Token Cullen
Feature activation+2.845
Bryant
Token Bryant
Feature activation+3.070
HS
Token HS
Feature activation+1.667
in
Token in
Feature activation+0.000
Long
Token Long
Feature activation+0.000
Island
Token Island
Feature activation+0.369
City
Token City
Feature activation+1.151
ahu
Tokenahu
Feature activation+1.581
and
Token and
Feature activation+0.755
U
Token U
Feature activation+0.300
H
TokenH
Feature activation+3.386
H
Token H
Feature activation+1.226
ilo
Tokenilo
Feature activation+3.069
,
Token,
Feature activation+1.298
but
Token but
Feature activation+1.767
several
Token several
Feature activation+2.301
community
Token community
Feature activation+2.611
colleges
Token colleges
Feature activation+0.000
to
Token to
Feature activation+0.644
the
Token the
Feature activation+1.082
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.457
S
TokenS
Feature activation+2.574
.
Token.
Feature activation+3.040
attorney
Token attorney
Feature activation+0.680
for
Token for
Feature activation+0.000
Vermont
Token Vermont
Feature activation+0.000
and
Token and
Feature activation+1.040
the
Token the
Feature activation+2.240
at
Token at
Feature activation+0.000
Jesse
Token Jesse
Feature activation+0.280
J
Token J
Feature activation+0.244
.
Token.
Feature activation+0.671
McC
Token McC
Feature activation+0.189
rary
Tokenrary
Feature activation+3.031
Jr
Token Jr
Feature activation+2.940
.
Token.
Feature activation+2.685
Elementary
Token Elementary
Feature activation+1.547
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 3.783

.
Token.
Feature activation-0.004
Top resid features:
--
Token --
Feature activation-0.005
Top resid features:
A
Token A
Feature activation-0.003
Top resid features:
North
Token North
Feature activation+0.040
Top resid features:
Carolina
Token Carolina
Feature activation+0.094
Top resid features:
university
Token university
Feature activation+3.783
Top resid features:
is
Token is
Feature activation+0.025
Top resid features:
conducting
Token conducting
Feature activation+0.066
Top resid features:
an
Token an
Feature activation+0.014
Top resid features:
internal
Token internal
Feature activation+0.009
Top resid features:
review
Token review
Feature activation+0.026
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.071
Top resid features:
University
Token University
Feature activation+2.903
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
Wag
Token Wag
Feature activation-0.092
Top resid features:
ening
Tokenening
Feature activation+0.033
Top resid features:
en
Tokenen
Feature activation+1.604
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.165
Top resid features:
f
Token f
Feature activation+0.001
Top resid features:
oyer
Tokenoyer
Feature activation+0.166
Top resid features:
of
Token of
Feature activation+0.279
Top resid features:
the
Token the
Feature activation+0.464
Top resid features:
School
Token School
Feature activation+1.208
Top resid features:
Without
Token Without
Feature activation-0.006
Top resid features:
Walls
Token Walls
Feature activation+0.917
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
District
Token District
Feature activation+0.000
Top resid features:
p
Token p
Feature activation-0.051
Top resid features:
ug
Tokenug
Feature activation-0.019
Top resid features:
il
Tokenil
Feature activation+0.014
Top resid features:
istic
Tokenistic
Feature activation+0.232
Top resid features:
tuition
Token tuition
Feature activation+0.862
Top resid features:
at
Token at
Feature activation+1.645
Top resid features:
the
Token the
Feature activation+1.032
Top resid features:
Bond
Token Bond
Feature activation-0.014
Top resid features:
Street
Token Street
Feature activation+0.263
Top resid features:
rooms
Token rooms
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
only
Token only
Feature activation+0.169
Top resid features:
such
Token such
Feature activation+0.013
Top resid features:
colleges
Token colleges
Feature activation+0.149
Top resid features:
such
Token such
Feature activation+0.017
Top resid features:
as
Token as
Feature activation+1.434
Top resid features:
U
Token U
Feature activation+0.091
Top resid features:
H
TokenH
Feature activation+0.238
Top resid features:
West
Token West
Feature activation+0.209
Top resid features:
O
Token O
Feature activation+0.173
Top resid features:
ahu
Tokenahu
Feature activation+0.490
Top resid features:
ad
Tokenad
Feature activation-0.004
Top resid features:
one
Tokenone
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
other
Token other
Feature activation+0.054
Top resid features:
students
Token students
Feature activation+0.603
Top resid features:
at
Token at
Feature activation+2.754
Top resid features:
Bethlehem
Token Bethlehem
Feature activation+0.464
Top resid features:
Central
Token Central
Feature activation+0.172
Top resid features:
High
Token High
Feature activation+0.000
Top resid features:
School
Token School
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+0.072
Top resid features:
her
Token her
Feature activation+0.010
Top resid features:
math
Token math
Feature activation+0.183
Top resid features:
class
Token class
Feature activation+0.189
Top resid features:
at
Token at
Feature activation+3.010
Top resid features:
John
Token John
Feature activation+0.050
Top resid features:
F
Token F
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Kennedy
Token Kennedy
Feature activation+0.209
Top resid features:
High
Token High
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
--
Token --
Feature activation-0.013
Top resid features:
A
Token A
Feature activation-0.019
Top resid features:
North
Token North
Feature activation+0.003
Top resid features:
Carolina
Token Carolina
Feature activation+0.045
Top resid features:
university
Token university
Feature activation+1.941
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
conducting
Token conducting
Feature activation+0.024
Top resid features:
an
Token an
Feature activation-0.002
Top resid features:
internal
Token internal
Feature activation+0.008
Top resid features:
review
Token review
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
enrolled
Token enrolled
Feature activation+0.080
Top resid features:
in
Token in
Feature activation+0.077
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
single
Token single
Feature activation+0.043
Top resid features:
course
Token course
Feature activation+0.975
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
according
Token according
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.263
Top resid features:
data
Token data
Feature activation+0.064
Top resid features:
released
Token released
Feature activation+0.017
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
includes
Token includes
Feature activation+0.100
Top resid features:
not
Token not
Feature activation-0.008
Top resid features:
only
Token only
Feature activation+0.034
Top resid features:
such
Token such
Feature activation+0.017
Top resid features:
colleges
Token colleges
Feature activation+0.368
Top resid features:
such
Token such
Feature activation+0.012
Top resid features:
as
Token as
Feature activation+0.118
Top resid features:
U
Token U
Feature activation+0.047
Top resid features:
H
TokenH
Feature activation+0.150
Top resid features:
West
Token West
Feature activation+0.017
Top resid features:
val
Tokenval
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
physics
Token physics
Feature activation+0.731
Top resid features:
teacher
Token teacher
Feature activation+0.943
Top resid features:
at
Token at
Feature activation+1.565
Top resid features:
Ross
Token Ross
Feature activation+0.078
Top resid features:
She
Token She
Feature activation-0.086
Top resid features:
ppard
Tokenppard
Feature activation+0.681
Top resid features:
High
Token High
Feature activation+0.000
Top resid features:
School
Token School
Feature activation+0.000
Top resid features:
And
Token And
Feature activation-0.061
Top resid features:
in
Token in
Feature activation-0.048
Top resid features:
2008
Token 2008
Feature activation+0.204
Top resid features:
,
Token,
Feature activation+0.174
Top resid features:
the
Token the
Feature activation+0.080
Top resid features:
University
Token University
Feature activation+2.770
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
Reading
Token Reading
Feature activation+0.877
Top resid features:
grew
Token grew
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
similar
Token similar
Feature activation+0.000
Top resid features:
school
Token school
Feature activation+0.196
Top resid features:
entirely
Token entirely
Feature activation+0.007
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
Morrow
Token Morrow
Feature activation-0.000
Top resid features:
transferred
Token transferred
Feature activation+0.197
Top resid features:
to
Token to
Feature activation+0.841
Top resid features:
the
Token the
Feature activation+0.801
Top resid features:
Old
Token Old
Feature activation+0.219
Top resid features:
Or
Token Or
Feature activation-0.014
Top resid features:
chard
Tokenchard
Feature activation+0.424
Top resid features:
Beach
Token Beach
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.099
Top resid features:
course
Token course
Feature activation+0.211
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
s
Tokens
Feature activation+0.136
Top resid features:
30
Token 30
Feature activation+1.221
Top resid features:
-
Token-
Feature activation+0.138
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
history
Token history
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
ordered
Token ordered
Feature activation+0.105
Top resid features:
Pi
Token Pi
Feature activation+0.058
Top resid features:
Kappa
Token Kappa
Feature activation+0.126
Top resid features:
Alpha
Token Alpha
Feature activation+0.788
Top resid features:
to
Token to
Feature activation+0.416
Top resid features:
cease
Token cease
Feature activation+0.375
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
des
Token des
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.053
Top resid features:
more
Token more
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.011
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
male
Token male
Feature activation+0.009
Top resid features:
students
Token students
Feature activation+3.365
Top resid features:
she
Token she
Feature activation+0.220
Top resid features:
studied
Token studied
Feature activation+0.284
Top resid features:
alongside
Token alongside
Feature activation+0.023
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
Austria
Token Austria
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.143
Top resid features:
The
TokenThe
Feature activation+0.136
Top resid features:
principal
Token principal
Feature activation+0.427
Top resid features:
of
Token of
Feature activation+1.998
Top resid features:
William
Token William
Feature activation+0.121
Top resid features:
Cullen
Token Cullen
Feature activation+0.372
Top resid features:
Bryant
Token Bryant
Feature activation+0.173
Top resid features:
HS
Token HS
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.017
Top resid features:
only
Token only
Feature activation+0.051
Top resid features:
such
Token such
Feature activation+0.009
Top resid features:
colleges
Token colleges
Feature activation+0.289
Top resid features:
such
Token such
Feature activation-0.005
Top resid features:
as
Token as
Feature activation+0.906
Top resid features:
U
Token U
Feature activation+0.065
Top resid features:
H
TokenH
Feature activation+0.480
Top resid features:
West
Token West
Feature activation+0.227
Top resid features:
O
Token O
Feature activation+0.028
Top resid features:
ahu
Tokenahu
Feature activation+0.311
Top resid features:
He
Token He
Feature activation-0.005
Top resid features:
wrote
Token wrote
Feature activation+0.033
Top resid features:
letters
Token letters
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
2016
Token 2016
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+1.760
Top resid features:
the
Token the
Feature activation+0.752
Top resid features:
U
Token U
Feature activation+0.206
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
S
TokenS
Feature activation+0.027
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
distributing
Token distributing
Feature activation-0.000
Top resid features:
supplies
Token supplies
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
students
Token students
Feature activation+0.921
Top resid features:
at
Token at
Feature activation+2.634
Top resid features:
Jesse
Token Jesse
Feature activation+0.109
Top resid features:
J
Token J
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
McC
Token McC
Feature activation+0.003
Top resid features:
rary
Tokenrary
Feature activation+0.339
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.04

Head 2: 0.04

Head 3: 0.35

Head 4: 0.06

Head 5: 0.04

Head 6: 0.03

Head 7: 0.05

Head 8: 0.14

Head 9: 0.03

Head 10: 0.06

Head 11: 0.05

Positive logits

Students7.76

campus7.24

faculty7.23

students7.14

student7.12

tuition7.11

campus7.10

Students7.09

Student7.08

student7.07

university6.96

Colleges6.96

Faculty6.88

undergraduate6.80

Student6.73

undergrad6.72

professors6.70

campuses6.66

Campus6.64

colleges6.55

Negative logits

Armageddon-2.72

bandits-2.66

landfall-2.55

Predator-2.42

caravan-2.42

WATCHED-2.39

usercontent-2.36

Geral-2.35

GoPro-2.34

dwarves-2.30

tac-2.27

Witcher-2.27

desper-2.26

corrid-2.25

Godzilla-2.17

spoilers-2.16

cockpit-2.15

Shogun-2.13

Mafia-2.13

armoured-2.13

INTERVAL 3.849 - 4.276
CONTAINS 0.000%

conducting
Token conducting
Feature activation+1.898
an
Token an
Feature activation+1.804
internal
Token internal
Feature activation+2.330
review
Token review
Feature activation+0.000
after
Token after
Feature activation+1.782
one
Token one
Feature activation+4.276
of
Token of
Feature activation+1.634
its
Token its
Feature activation+1.732
white
Token white
Feature activation+2.296
police
Token police
Feature activation+1.259
officers
Token officers
Feature activation+0.719

INTERVAL 3.421 - 3.849
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
University
Token University
Feature activation+0.986
of
Token of
Feature activation+0.315
Wag
Token Wag
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
en
Tokenen
Feature activation+3.674
at
Token at
Feature activation+0.114
the
Token the
Feature activation+0.326
request
Token request
Feature activation+0.000
of
Token of
Feature activation+1.453
the
Token the
Feature activation+1.579
istic
Tokenistic
Feature activation+0.093
tuition
Token tuition
Feature activation+0.206
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.377
Bond
Token Bond
Feature activation+2.456
Street
Token Street
Feature activation+3.458
rooms
Token rooms
Feature activation+1.154
of
Token of
Feature activation+0.645
former
Token former
Feature activation+0.972
pri
Token pri
Feature activation+0.000
z
Tokenz
Feature activation+0.000
oyer
Tokenoyer
Feature activation+0.539
of
Token of
Feature activation+0.675
the
Token the
Feature activation+1.402
School
Token School
Feature activation+1.328
Without
Token Without
Feature activation+0.754
Walls
Token Walls
Feature activation+3.557
in
Token in
Feature activation+0.703
the
Token the
Feature activation+1.182
District
Token District
Feature activation+1.805
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+1.211

INTERVAL 2.993 - 3.421
CONTAINS 0.002%

at
Token at
Feature activation+0.000
Jesse
Token Jesse
Feature activation+0.280
J
Token J
Feature activation+0.244
.
Token.
Feature activation+0.671
McC
Token McC
Feature activation+0.189
rary
Tokenrary
Feature activation+3.031
Jr
Token Jr
Feature activation+2.940
.
Token.
Feature activation+2.685
Elementary
Token Elementary
Feature activation+1.547
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.780
The
TokenThe
Feature activation+1.244
February
Token February
Feature activation+2.013
issue
Token issue
Feature activation+1.316
of
Token of
Feature activation+3.264
Hawaii
Token Hawaii
Feature activation+2.668
Business
Token Business
Feature activation+0.413
had
Token had
Feature activation+0.541
an
Token an
Feature activation+0.202
article
Token article
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.672
University
Token University
Feature activation+0.624
of
Token of
Feature activation+0.000
Reading
Token Reading
Feature activation+3.220
grew
Token grew
Feature activation+0.935
a
Token a
Feature activation+1.714
similar
Token similar
Feature activation+1.565
culture
Token culture
Feature activation+0.106
that
Token that
Feature activation+0.000
The
TokenThe
Feature activation+0.031
principal
Token principal
Feature activation+0.000
of
Token of
Feature activation+0.188
William
Token William
Feature activation+0.307
Cullen
Token Cullen
Feature activation+2.845
Bryant
Token Bryant
Feature activation+3.070
HS
Token HS
Feature activation+1.667
in
Token in
Feature activation+0.000
Long
Token Long
Feature activation+0.000
Island
Token Island
Feature activation+0.369
City
Token City
Feature activation+1.151
its
Token its
Feature activation+1.732
white
Token white
Feature activation+2.296
police
Token police
Feature activation+1.259
officers
Token officers
Feature activation+0.719
handcuffed
Token handcuffed
Feature activation+2.243
a
Token a
Feature activation+3.349
black
Token black
Feature activation+2.965
man
Token man
Feature activation+1.184
who
Token who
Feature activation+0.927
had
Token had
Feature activation+0.000
just
Token just
Feature activation+0.000

INTERVAL 2.566 - 2.993
CONTAINS 0.002%

one
Tokenone
Feature activation+0.000
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
students
Token students
Feature activation+0.000
at
Token at
Feature activation+0.558
Bethlehem
Token Bethlehem
Feature activation+2.722
Central
Token Central
Feature activation+3.384
High
Token High
Feature activation+0.842
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
from
Token from
Feature activation+0.000
various
Token various
Feature activation+1.069
schools
Token schools
Feature activation+1.437
across
Token across
Feature activation+0.427
the
Token the
Feature activation+0.677
island
Token island
Feature activation+2.744
were
Token were
Feature activation+0.155
on
Token on
Feature activation+0.719
hand
Token hand
Feature activation+0.144
to
Token to
Feature activation+0.522
witness
Token witness
Feature activation+0.000
ed
Tokened
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+1.022
LV
TokenLV
Feature activation+1.649
School
Token School
Feature activation+1.331
of
Token of
Feature activation+2.863
Medicine
Token Medicine
Feature activation+1.855
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.678
s
Tokens
Feature activation+1.368
planned
Token planned
Feature activation+1.779
system
Token system
Feature activation+1.032
that
Token that
Feature activation+1.211
includes
Token includes
Feature activation+0.887
not
Token not
Feature activation+1.433
only
Token only
Feature activation+1.725
such
Token such
Feature activation+2.793
colleges
Token colleges
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
U
Token U
Feature activation+0.264
H
TokenH
Feature activation+1.537
a
Token a
Feature activation+0.000
student
Token student
Feature activation+0.000
at
Token at
Feature activation+0.000
Paradise
Token Paradise
Feature activation+1.619
Valley
Token Valley
Feature activation+1.446
Community
Token Community
Feature activation+2.784
College
Token College
Feature activation+0.095
,
Token,
Feature activation+0.000
filed
Token filed
Feature activation+0.000
suit
Token suit
Feature activation+0.000
against
Token against
Feature activation+0.000

INTERVAL 2.138 - 2.566
CONTAINS 0.007%

Carolina
Token Carolina
Feature activation+0.000
university
Token university
Feature activation+0.785
is
Token is
Feature activation+0.964
conducting
Token conducting
Feature activation+1.898
an
Token an
Feature activation+1.804
internal
Token internal
Feature activation+2.330
review
Token review
Feature activation+0.000
after
Token after
Feature activation+1.782
one
Token one
Feature activation+4.276
of
Token of
Feature activation+1.634
its
Token its
Feature activation+1.732
were
Token were
Feature activation+0.080
available
Token available
Feature activation+0.073
at
Token at
Feature activation+0.412
the
Token the
Feature activation+1.353
all
Token all
Feature activation+1.329
-
Token-
Feature activation+2.219
black
Tokenblack
Feature activation+1.690
college
Token college
Feature activation+0.214
four
Token four
Feature activation+1.814
hours
Token hours
Feature activation+0.000
away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
college
Token college
Feature activation+0.000
's
Token's
Feature activation+0.375
associate
Token associate
Feature activation+2.541
vice
Token vice
Feature activation+2.565
president
Token president
Feature activation+1.233
of
Token of
Feature activation+1.134
Student
Token Student
Feature activation+0.530
Health
Token Health
Feature activation+0.824
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.868
he
Token he
Feature activation+0.000
and
Token and
Feature activation+1.001
Tracy
Token Tracy
Feature activation+0.000
Lawson
Token Lawson
Feature activation+0.000
talk
Token talk
Feature activation+2.282
about
Token about
Feature activation+0.170
Tracy
Token Tracy
Feature activation+0.000
's
Token's
Feature activation+0.232
new
Token new
Feature activation+1.314
release
Token release
Feature activation+0.337
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
university
Token university
Feature activation+0.434
plans
Token plans
Feature activation+1.450
to
Token to
Feature activation+1.232
acquire
Token acquire
Feature activation+2.465
the
Token the
Feature activation+2.253
properties
Token properties
Feature activation+0.346
through
Token through
Feature activation+1.679
eminent
Token eminent
Feature activation+0.000
domain
Token domain
Feature activation+0.000

INTERVAL 1.711 - 2.138
CONTAINS 0.017%

board
Token board
Feature activation+0.931
of
Token of
Feature activation+1.817
reg
Token reg
Feature activation+0.831
ents
Tokenents
Feature activation+1.464
held
Token held
Feature activation+0.915
a
Token a
Feature activation+1.744
special
Token special
Feature activation+1.411
meeting
Token meeting
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
a
Token a
Feature activation+1.092
the
Token the
Feature activation+1.445
Philippine
Token Philippine
Feature activation+1.523
National
Token National
Feature activation+2.514
Agriculture
Token Agriculture
Feature activation+2.227
and
Token and
Feature activation+1.100
Fisheries
Token Fisheries
Feature activation+2.125
(
Token (
Feature activation+0.000
N
TokenN
Feature activation+0.000
U
TokenU
Feature activation+0.000
CA
TokenCA
Feature activation+0.000
F
TokenF
Feature activation+1.319
for
Token for
Feature activation+0.966
instance
Token instance
Feature activation+1.310
,
Token,
Feature activation+1.427
reports
Token reports
Feature activation+1.894
that
Token that
Feature activation+1.242
it
Token it
Feature activation+1.952
is
Token is
Feature activation+1.508
getting
Token getting
Feature activation+0.940
more
Token more
Feature activation+0.702
applicants
Token applicants
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.149
Gordon
Token Gordon
Feature activation+0.727
College
Token College
Feature activation+0.835
of
Token of
Feature activation+0.058
Arts
Token Arts
Feature activation+0.898
and
Token and
Feature activation+0.387
Sciences
Token Sciences
Feature activation+2.069
.
Token.
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
um
Tokenum
Feature activation+0.000
berg
Tokenberg
Feature activation+0.428
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Whenever
Token Whenever
Feature activation+0.214
he
Token he
Feature activation+0.000
told
Token told
Feature activation+1.178
friends
Token friends
Feature activation+0.000
and
Token and
Feature activation+1.745
colleagues
Token colleagues
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
gig
Token gig
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.283 - 1.711
CONTAINS 0.034%

allow
Token allow
Feature activation+0.000
students
Token students
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.090
genders
Token genders
Feature activation+0.969
to
Token to
Feature activation+1.331
be
Token be
Feature activation+1.164
comfortable
Token comfortable
Feature activation+0.870
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
USC
Token USC
Feature activation+0.994
Price
Token Price
Feature activation+0.270
School
Token School
Feature activation+1.251
of
Token of
Feature activation+1.213
Public
Token Public
Feature activation+1.334
Policy
Token Policy
Feature activation+1.598
Professor
Token Professor
Feature activation+0.141
and
Token and
Feature activation+0.853
the
Token the
Feature activation+0.603
newly
Token newly
Feature activation+0.000
appointed
Token appointed
Feature activation+0.312
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
National
Token National
Feature activation+0.896
University
Token University
Feature activation+0.682
/
Token /
Feature activation+0.129
College
Token College
Feature activation+1.503
of
Token of
Feature activation+0.715
Agriculture
Token Agriculture
Feature activation+1.593
/
Token /
Feature activation+0.666
Fisheries
Token Fisheries
Feature activation+2.253
(
Token (
Feature activation+0.000
Va
TokenVa
Feature activation+0.041
.
Token.
Feature activation+1.607
student
Token student
Feature activation+0.000
whose
Token whose
Feature activation+0.332
allegations
Token allegations
Feature activation+0.000
of
Token of
Feature activation+1.419
a
Token a
Feature activation+1.497
2012
Token 2012
Feature activation+1.160
gang
Token gang
Feature activation+0.026
rape
Token rape
Feature activation+0.000
at
Token at
Feature activation+0.337
as
Token as
Feature activation+0.000
U
Token U
Feature activation+0.264
H
TokenH
Feature activation+1.537
West
Token West
Feature activation+0.712
O
Token O
Feature activation+0.331
ahu
Tokenahu
Feature activation+1.581
and
Token and
Feature activation+0.755
U
Token U
Feature activation+0.300
H
TokenH
Feature activation+3.386
H
Token H
Feature activation+1.226
ilo
Tokenilo
Feature activation+3.069

INTERVAL 0.855 - 1.283
CONTAINS 0.078%

ction
Tokenction
Feature activation+0.000
ed
Tokened
Feature activation+0.000
events
Token events
Feature activation+0.000
for
Token for
Feature activation+0.351
CN
Token CN
Feature activation+0.000
U
TokenU
Feature activation+1.108
attendees
Token attendees
Feature activation+0.000
each
Token each
Feature activation+1.076
year
Token year
Feature activation+0.000
(
Token (
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
ocate
Tokenocate
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
Milo
Token Milo
Feature activation+0.000
Yiannopoulos
Token Yiannopoulos
Feature activation+0.000
on
Token on
Feature activation+0.838
Halloween
Token Halloween
Feature activation+1.010
,
Token,
Feature activation+0.389
prompting
Token prompting
Feature activation+0.767
the
Token the
Feature activation+0.842
CS
Token CS
Feature activation+0.000
UF
TokenUF
Feature activation+0.532
-
Token-
Feature activation+0.817
old
Tokenold
Feature activation+1.528
est
Tokenest
Feature activation+1.638
continuously
Token continuously
Feature activation+1.724
public
Token public
Feature activation+2.372
high
Token high
Feature activation+1.104
school
Token school
Feature activation+0.801
in
Token in
Feature activation+0.891
the
Token the
Feature activation+1.365
United
Token United
Feature activation+0.000
States
Token States
Feature activation+1.228
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
graduating
Token graduating
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+1.214
college
Token college
Feature activation+0.000
that
Token that
Feature activation+0.000
stands
Token stands
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.085
the
Token the
Feature activation+0.000
male
Token male
Feature activation+0.000
students
Token students
Feature activation+0.000
she
Token she
Feature activation+1.260
studied
Token studied
Feature activation+1.257
alongside
Token alongside
Feature activation+0.926
in
Token in
Feature activation+0.390
Austria
Token Austria
Feature activation+3.115
had
Token had
Feature activation+0.628
ended
Token ended
Feature activation+0.799

INTERVAL 0.428 - 0.855
CONTAINS 0.165%

,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
24
Token 24
Feature activation+0.972
%
Token%
Feature activation+1.344
say
Token say
Feature activation+0.207
they
Token they
Feature activation+0.615
can
Token can
Feature activation+1.509
help
Token help
Feature activation+0.423
disabled
Token disabled
Feature activation+1.175
students
Token students
Feature activation+1.379
"
Token "
Feature activation+0.594
the
Token the
Feature activation+0.527
giveaway
Token giveaway
Feature activation+0.130
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.449
Lincoln
Token Lincoln
Feature activation+0.524
High
Token High
Feature activation+0.437
School
Token School
Feature activation+1.093
was
Token was
Feature activation+1.344
the
Token the
Feature activation+2.127
African
Token African
Feature activation+1.503
-
Token-
Feature activation+0.939
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
composition
Token composition
Feature activation+0.000
of
Token of
Feature activation+0.000
major
Token major
Feature activation+0.000
-
Token-
Feature activation+0.546
related
Tokenrelated
Feature activation+0.000
classes
Token classes
Feature activation+0.000
affects
Token affects
Feature activation+0.000
major
Token major
Feature activation+0.000
changes
Token changes
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
why
Token why
Feature activation+0.000
a
Token a
Feature activation+0.000
growing
Token growing
Feature activation+0.000
number
Token number
Feature activation+0.630
of
Token of
Feature activation+0.382
short
Token short
Feature activation+0.717
-
Token-
Feature activation+1.215
term
Tokenterm
Feature activation+0.567
opportunities
Token opportunities
Feature activation+0.000
,
Token,
Feature activation+0.539
the
Token the
Feature activation+1.040
parents
Token parents
Feature activation+0.000
claim
Token claim
Feature activation+0.790
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.713
not
Token not
Feature activation+0.148
racism
Token racism
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
desire
Token desire
Feature activation+0.000

INTERVAL 0.000 - 0.428
CONTAINS 99.694%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.000
Court
Token Court
Feature activation+0.000
of
Token of
Feature activation+0.000
Appeals
Token Appeals
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Second
Token Second
Feature activation+0.000
Circuit
Token Circuit
Feature activation+0.000
decision
Token decision
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
warts
Tokenwarts
Feature activation+0.000
who
Token who
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
election
Token election
Feature activation+0.000
are
Token are
Feature activation+0.000
lists
Token lists
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Virtual
TokenVirtual
Feature activation+0.000
servers
Token servers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
NS
TokenNS
Feature activation+0.000
caching
Token caching
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
wrest
Token wrest
Feature activation+0.000
led
Tokenled
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Amazing
TokenAmazing
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
Police
Token Police
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
technique
Token technique
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000
proven
Token proven
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
successful
Token successful
Feature activation+0.000
as
Token as
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 H11.3: (feature 4284)

TOP ACTIVATIONS
MAX = 4.417

spent
Token spent
Feature activation+0.309
years
Token years
Feature activation+0.869
in
Token in
Feature activation+2.853
American
Token American
Feature activation+4.162
and
Token and
Feature activation+1.463
Canadian
Token Canadian
Feature activation+4.417
courts
Token courts
Feature activation+2.769
trying
Token trying
Feature activation+0.175
to
Token to
Feature activation+0.754
collect
Token collect
Feature activation+1.203
from
Token from
Feature activation+0.878
but
Token but
Feature activation+0.257
then
Token then
Feature activation+0.644
spent
Token spent
Feature activation+0.309
years
Token years
Feature activation+0.869
in
Token in
Feature activation+2.853
American
Token American
Feature activation+4.162
and
Token and
Feature activation+1.463
Canadian
Token Canadian
Feature activation+4.417
courts
Token courts
Feature activation+2.769
trying
Token trying
Feature activation+0.175
to
Token to
Feature activation+0.754
federal
Token federal
Feature activation+1.596
judge
Token judge
Feature activation+0.292
,
Token,
Feature activation+0.443
in
Token in
Feature activation+0.090
a
Token a
Feature activation+1.406
Florida
Token Florida
Feature activation+4.002
court
Token court
Feature activation+0.350
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.033
For
TokenFor
Feature activation+1.053
as
Token as
Feature activation+0.000
witnesses
Token witnesses
Feature activation+0.000
in
Token in
Feature activation+0.186
Bru
Token Bru
Feature activation+0.000
yne
Tokenyne
Feature activation+0.000
el
Tokenel
Feature activation+3.974
case
Token case
Feature activation+1.954
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Arm
TokenArm
Feature activation+0.000
strong
Tokenstrong
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.000
of
Token of
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
in
Token in
Feature activation+0.000
Riyadh
Token Riyadh
Feature activation+3.850
approved
Token approved
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
handed
Token handed
Feature activation+0.000
sell
Tokensell
Feature activation+1.162
,
Token,
Feature activation+0.895
a
Token a
Feature activation+2.473
University
Token University
Feature activation+2.583
of
Token of
Feature activation+0.357
Utah
Token Utah
Feature activation+3.695
law
Token law
Feature activation+0.379
professor
Token professor
Feature activation+0.654
and
Token and
Feature activation+2.303
a
Token a
Feature activation+2.273
former
Token former
Feature activation+2.356
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
State
Token State
Feature activation+0.127
Bar
Token Bar
Feature activation+1.232
of
Token of
Feature activation+0.000
Texas
Token Texas
Feature activation+3.335
dis
Token dis
Feature activation+0.934
bar
Tokenbar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.669
county
Token county
Feature activation+0.868
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.577
s
Tokens
Feature activation+1.761
chief
Token chief
Feature activation+1.537
public
Token public
Feature activation+3.264
defender
Token defender
Feature activation+0.000
,
Token,
Feature activation+0.364
Mary
Token Mary
Feature activation+0.000
Mori
Token Mori
Feature activation+0.000
arty
Tokenarty
Feature activation+0.574
Z
Token Z
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
ide
Tokenide
Feature activation+0.762
h
Tokenh
Feature activation+1.578
of
Token of
Feature activation+0.000
Kemp
Token Kemp
Feature activation+3.177
Klein
Token Klein
Feature activation+2.696
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.608
case
Token case
Feature activation+0.000
leaves
Token leaves
Feature activation+0.353
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
federal
Token federal
Feature activation+0.028
and
Token and
Feature activation+0.000
state
Token state
Feature activation+0.796
sex
Token sex
Feature activation+3.107
crimes
Token crimes
Feature activation+1.472
to
Token to
Feature activation+0.000
two
Token two
Feature activation+0.000
state
Token state
Feature activation+0.484
charges
Token charges
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
was
Token was
Feature activation+0.000
filed
Token filed
Feature activation+0.000
in
Token in
Feature activation+0.020
the
Token the
Feature activation+0.741
state
Token state
Feature activation+3.044
superior
Token superior
Feature activation+1.355
court
Token court
Feature activation+0.228
in
Token in
Feature activation+0.000
San
Token San
Feature activation+1.066
Francisco
Token Francisco
Feature activation+1.769
Allen
Token Allen
Feature activation+2.811
,
Token,
Feature activation+0.040
Crow
Token Crow
Feature activation+0.668
,
Token,
Feature activation+0.440
Meth
Token Meth
Feature activation+0.000
vin
Tokenvin
Feature activation+3.033
,
Token,
Feature activation+0.155
Port
Token Port
Feature activation+0.000
is
Tokenis
Feature activation+1.026
&
Token &
Feature activation+0.000
Miles
Token Miles
Feature activation+2.812
wait
Token wait
Feature activation+0.271
states
Token states
Feature activation+0.758
ide
Tokenide
Feature activation+1.863
for
Token for
Feature activation+1.317
their
Token their
Feature activation+2.404
next
Token next
Feature activation+3.005
court
Token court
Feature activation+0.419
appearance
Token appearance
Feature activation+0.000
,
Token,
Feature activation+0.895
but
Token but
Feature activation+1.225
there
Token there
Feature activation+0.000
team
Token team
Feature activation+0.000
to
Token to
Feature activation+0.088
federal
Token federal
Feature activation+0.726
court
Token court
Feature activation+0.168
in
Token in
Feature activation+0.106
Charlottesville
Token Charlottesville
Feature activation+2.945
,
Token,
Feature activation+0.513
Va
Token Va
Feature activation+1.809
.,
Token.,
Feature activation+1.078
on
Token on
Feature activation+0.877
Tuesday
Token Tuesday
Feature activation+1.396
1
Token 1
Feature activation+0.020
and
Token and
Feature activation+0.000
2
Token 2
Feature activation+0.857
,
Token,
Feature activation+1.271
in
Token in
Feature activation+2.057
a
Token a
Feature activation+2.942
civil
Token civil
Feature activation+2.674
lawsuit
Token lawsuit
Feature activation+0.000
against
Token against
Feature activation+1.169
the
Token the
Feature activation+1.302
U
Token U
Feature activation+0.200
sell
Tokensell
Feature activation+1.727
and
Token and
Feature activation+0.774
Florida
Token Florida
Feature activation+1.943
attorney
Token attorney
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
Edwards
Token Edwards
Feature activation+2.940
have
Token have
Feature activation+2.846
represented
Token represented
Feature activation+0.734
two
Token two
Feature activation+1.657
women
Token women
Feature activation+1.212
,
Token,
Feature activation+0.000
.,
Token.,
Feature activation+0.000
defense
Token defense
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
were
Token were
Feature activation+0.967
in
Token in
Feature activation+1.690
the
Token the
Feature activation+2.917
courtroom
Token courtroom
Feature activation+2.593
awaiting
Token awaiting
Feature activation+0.696
the
Token the
Feature activation+0.486
judge
Token judge
Feature activation+0.000
.
Token.
Feature activation+0.037
,
Token,
Feature activation+0.197
but
Token but
Feature activation+0.257
then
Token then
Feature activation+0.644
spent
Token spent
Feature activation+0.309
years
Token years
Feature activation+0.869
in
Token in
Feature activation+2.853
American
Token American
Feature activation+4.162
and
Token and
Feature activation+1.463
Canadian
Token Canadian
Feature activation+4.417
courts
Token courts
Feature activation+2.769
trying
Token trying
Feature activation+0.175
and
Token and
Feature activation+0.774
Florida
Token Florida
Feature activation+1.943
attorney
Token attorney
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
Edwards
Token Edwards
Feature activation+2.940
have
Token have
Feature activation+2.846
represented
Token represented
Feature activation+0.734
two
Token two
Feature activation+1.657
women
Token women
Feature activation+1.212
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.612
in
Tokenin
Feature activation+1.527
County
Token County
Feature activation+2.237
judges
Token judges
Feature activation+0.000
and
Token and
Feature activation+0.670
the
Token the
Feature activation+1.262
Minneapolis
Token Minneapolis
Feature activation+2.820
city
Token city
Feature activation+2.233
attorney
Token attorney
Feature activation+0.362
,
Token,
Feature activation+1.267
who
Token who
Feature activation+0.606
said
Token said
Feature activation+1.411

Top DFA by src position
MAX = 4.091

,
Token,
Feature activation-0.025
Top resid features:
but
Token but
Feature activation+0.004
Top resid features:
then
Token then
Feature activation+0.026
Top resid features:
spent
Token spent
Feature activation+0.024
Top resid features:
years
Token years
Feature activation+0.902
Top resid features:
in
Token in
Feature activation+3.030
Top resid features:
American
Token American
Feature activation+0.748
Top resid features:
and
Token and
Feature activation-0.008
Top resid features:
Canadian
Token Canadian
Feature activation+0.208
Top resid features:
courts
Token courts
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
but
Token but
Feature activation+0.012
Top resid features:
then
Token then
Feature activation+0.033
Top resid features:
spent
Token spent
Feature activation+0.021
Top resid features:
years
Token years
Feature activation+0.516
Top resid features:
in
Token in
Feature activation+4.005
Top resid features:
American
Token American
Feature activation+0.181
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Canadian
Token Canadian
Feature activation+0.000
Top resid features:
courts
Token courts
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.098
Top resid features:
federal
Token federal
Feature activation+0.039
Top resid features:
judge
Token judge
Feature activation+0.100
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.639
Top resid features:
a
Token a
Feature activation+2.609
Top resid features:
Florida
Token Florida
Feature activation+0.339
Top resid features:
court
Token court
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:
Hamilton
Token Hamilton
Feature activation-0.025
Top resid features:
and
Token and
Feature activation-0.098
Top resid features:
others
Token others
Feature activation+0.017
Top resid features:
as
Token as
Feature activation+0.017
Top resid features:
witnesses
Token witnesses
Feature activation+0.234
Top resid features:
in
Token in
Feature activation+3.594
Top resid features:
Bru
Token Bru
Feature activation+0.021
Top resid features:
yne
Tokenyne
Feature activation-0.018
Top resid features:
el
Tokenel
Feature activation+1.111
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
court
Token court
Feature activation+0.760
Top resid features:
of
Token of
Feature activation+0.047
Top resid features:
appeal
Token appeal
Feature activation+4.091
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Riyadh
Token Riyadh
Feature activation+0.159
Top resid features:
approved
Token approved
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.134
Top resid features:
Paul
Token Paul
Feature activation+0.008
Top resid features:
Cas
Token Cas
Feature activation+0.006
Top resid features:
sell
Tokensell
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.252
Top resid features:
a
Token a
Feature activation+3.246
Top resid features:
University
Token University
Feature activation+0.101
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Utah
Token Utah
Feature activation+0.182
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
professor
Token professor
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
family
Token family
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
The
Token The
Feature activation+0.027
Top resid features:
State
Token State
Feature activation+0.575
Top resid features:
Bar
Token Bar
Feature activation+2.198
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
Texas
Token Texas
Feature activation+0.747
Top resid features:
dis
Token dis
Feature activation+0.000
Top resid features:
bar
Tokenbar
Feature activation+0.000
Top resid features:
red
Tokenred
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
county
Token county
Feature activation+0.313
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.060
Top resid features:
s
Tokens
Feature activation+0.278
Top resid features:
chief
Token chief
Feature activation+2.561
Top resid features:
public
Token public
Feature activation+0.306
Top resid features:
defender
Token defender
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Mary
Token Mary
Feature activation+0.000
Top resid features:
Mori
Token Mori
Feature activation+0.000
Top resid features:
Robert
Token Robert
Feature activation+0.017
Top resid features:
Z
Token Z
Feature activation+0.049
Top resid features:
aw
Tokenaw
Feature activation+0.023
Top resid features:
ide
Tokenide
Feature activation+0.049
Top resid features:
h
Tokenh
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+2.286
Top resid features:
Kemp
Token Kemp
Feature activation+0.192
Top resid features:
Klein
Token Klein
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.010
Top resid features:
amounted
Token amounted
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
hundreds
Token hundreds
Feature activation+0.058
Top resid features:
of
Token of
Feature activation+0.061
Top resid features:
federal
Token federal
Feature activation+1.701
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
state
Token state
Feature activation+0.243
Top resid features:
sex
Token sex
Feature activation+0.093
Top resid features:
crimes
Token crimes
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
The
Token The
Feature activation+0.169
Top resid features:
lawsuit
Token lawsuit
Feature activation+0.209
Top resid features:
was
Token was
Feature activation+0.158
Top resid features:
filed
Token filed
Feature activation+0.337
Top resid features:
in
Token in
Feature activation+1.462
Top resid features:
the
Token the
Feature activation+0.671
Top resid features:
state
Token state
Feature activation+0.191
Top resid features:
superior
Token superior
Feature activation+0.000
Top resid features:
court
Token court
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.023
Top resid features:
Al
Token Al
Feature activation-0.007
Top resid features:
ab
Tokenab
Feature activation+0.008
Top resid features:
aman
Tokenaman
Feature activation-0.005
Top resid features:
law
Token law
Feature activation+0.070
Top resid features:
firm
Token firm
Feature activation+2.054
Top resid features:
Be
Token Be
Feature activation-0.003
Top resid features:
asley
Tokenasley
Feature activation+0.358
Top resid features:
,
Token,
Feature activation+0.925
Top resid features:
Allen
Token Allen
Feature activation+0.323
Top resid features:
,
Token,
Feature activation+0.206
Top resid features:
to
Token to
Feature activation+0.157
Top resid features:
wait
Token wait
Feature activation+0.216
Top resid features:
states
Token states
Feature activation+0.109
Top resid features:
ide
Tokenide
Feature activation+0.229
Top resid features:
for
Token for
Feature activation+0.848
Top resid features:
their
Token their
Feature activation+0.891
Top resid features:
next
Token next
Feature activation+0.329
Top resid features:
court
Token court
Feature activation+0.000
Top resid features:
appearance
Token appearance
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:
their
Token their
Feature activation-0.006
Top resid features:
legal
Token legal
Feature activation+0.068
Top resid features:
team
Token team
Feature activation+0.598
Top resid features:
to
Token to
Feature activation+0.198
Top resid features:
federal
Token federal
Feature activation+0.188
Top resid features:
court
Token court
Feature activation+2.350
Top resid features:
in
Token in
Feature activation+0.359
Top resid features:
Charlottesville
Token Charlottesville
Feature activation+0.135
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Va
Token Va
Feature activation+0.000
Top resid features:
.,
Token.,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
1
Token 1
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
2
Token 2
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.158
Top resid features:
in
Token in
Feature activation+1.166
Top resid features:
a
Token a
Feature activation+0.248
Top resid features:
civil
Token civil
Feature activation+0.000
Top resid features:
lawsuit
Token lawsuit
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
For
TokenFor
Feature activation-0.007
Top resid features:
six
Token six
Feature activation+0.096
Top resid features:
years
Token years
Feature activation+0.176
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
Cas
Token Cas
Feature activation+0.003
Top resid features:
sell
Tokensell
Feature activation+1.923
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
Florida
Token Florida
Feature activation+0.151
Top resid features:
attorney
Token attorney
Feature activation+0.473
Top resid features:
Brad
Token Brad
Feature activation+0.013
Top resid features:
Edwards
Token Edwards
Feature activation+0.182
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
m
Tokenm
Feature activation+0.011
Top resid features:
.,
Token.,
Feature activation-0.044
Top resid features:
defense
Token defense
Feature activation+0.079
Top resid features:
attorneys
Token attorneys
Feature activation+2.150
Top resid features:
were
Token were
Feature activation+1.313
Top resid features:
in
Token in
Feature activation+0.394
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
courtroom
Token courtroom
Feature activation+0.000
Top resid features:
awaiting
Token awaiting
Feature activation+0.000
Top resid features:
Tehran
Token Tehran
Feature activation-0.036
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
but
Token but
Feature activation+0.050
Top resid features:
then
Token then
Feature activation+0.114
Top resid features:
spent
Token spent
Feature activation+0.027
Top resid features:
years
Token years
Feature activation+1.699
Top resid features:
in
Token in
Feature activation+0.109
Top resid features:
American
Token American
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Canadian
Token Canadian
Feature activation+0.000
Top resid features:
courts
Token courts
Feature activation+0.000
Top resid features:
For
TokenFor
Feature activation-0.002
Top resid features:
six
Token six
Feature activation+0.010
Top resid features:
years
Token years
Feature activation+0.060
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
Cas
Token Cas
Feature activation+0.005
Top resid features:
sell
Tokensell
Feature activation+2.019
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
Florida
Token Florida
Feature activation+0.028
Top resid features:
attorney
Token attorney
Feature activation+0.106
Top resid features:
Brad
Token Brad
Feature activation+0.002
Top resid features:
Edwards
Token Edwards
Feature activation+0.441
Top resid features:
enn
Tokenenn
Feature activation-0.001
Top resid features:
ep
Tokenep
Feature activation-0.001
Top resid features:
in
Tokenin
Feature activation+0.068
Top resid features:
County
Token County
Feature activation+0.245
Top resid features:
judges
Token judges
Feature activation+0.457
Top resid features:
and
Token and
Feature activation+0.656
Top resid features:
the
Token the
Feature activation+0.441
Top resid features:
Minneapolis
Token Minneapolis
Feature activation+0.238
Top resid features:
city
Token city
Feature activation+0.000
Top resid features:
attorney
Token attorney
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.05

Head 2: 0.03

Head 3: 0.34

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.04

Head 8: 0.15

Head 9: 0.03

Head 10: 0.06

Head 11: 0.09

Positive logits

courtroom7.07

attorneys6.96

Judge6.76

lawyers6.60

court6.57

Court6.54

Lawyers6.36

lawy6.35

defendants6.35

litigation6.32

courthouse6.26

judicial6.25

appellate6.22

Prosecut6.18

Prosecutors6.14

Judicial6.14

prosecutors6.12

defendant6.02

Prosecutors6.01

Judge5.98

Negative logits

perture-2.63

Achievements-2.60

Missions-2.36

icro-2.33

Quantity-2.26

addon-2.25

mop-2.24

ombies-2.24

UNESCO-2.20

indo-2.18

Essential-2.18

linem-2.16

chieve-2.16

edes-2.13

nutrit-2.13

astronaut-2.12

Eco-2.11

zombies-2.10

buffs-2.10

rients-2.10

INTERVAL 3.975 - 4.417
CONTAINS 0.000%

but
Token but
Feature activation+0.257
then
Token then
Feature activation+0.644
spent
Token spent
Feature activation+0.309
years
Token years
Feature activation+0.869
in
Token in
Feature activation+2.853
American
Token American
Feature activation+4.162
and
Token and
Feature activation+1.463
Canadian
Token Canadian
Feature activation+4.417
courts
Token courts
Feature activation+2.769
trying
Token trying
Feature activation+0.175
to
Token to
Feature activation+0.754
spent
Token spent
Feature activation+0.309
years
Token years
Feature activation+0.869
in
Token in
Feature activation+2.853
American
Token American
Feature activation+4.162
and
Token and
Feature activation+1.463
Canadian
Token Canadian
Feature activation+4.417
courts
Token courts
Feature activation+2.769
trying
Token trying
Feature activation+0.175
to
Token to
Feature activation+0.754
collect
Token collect
Feature activation+1.203
from
Token from
Feature activation+0.878
federal
Token federal
Feature activation+1.596
judge
Token judge
Feature activation+0.292
,
Token,
Feature activation+0.443
in
Token in
Feature activation+0.090
a
Token a
Feature activation+1.406
Florida
Token Florida
Feature activation+4.002
court
Token court
Feature activation+0.350
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.033
For
TokenFor
Feature activation+1.053

INTERVAL 3.533 - 3.975
CONTAINS 0.000%

as
Token as
Feature activation+0.000
witnesses
Token witnesses
Feature activation+0.000
in
Token in
Feature activation+0.186
Bru
Token Bru
Feature activation+0.000
yne
Tokenyne
Feature activation+0.000
el
Tokenel
Feature activation+3.974
case
Token case
Feature activation+1.954
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Arm
TokenArm
Feature activation+0.000
strong
Tokenstrong
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.000
of
Token of
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
in
Token in
Feature activation+0.000
Riyadh
Token Riyadh
Feature activation+3.850
approved
Token approved
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
handed
Token handed
Feature activation+0.000
sell
Tokensell
Feature activation+1.162
,
Token,
Feature activation+0.895
a
Token a
Feature activation+2.473
University
Token University
Feature activation+2.583
of
Token of
Feature activation+0.357
Utah
Token Utah
Feature activation+3.695
law
Token law
Feature activation+0.379
professor
Token professor
Feature activation+0.654
and
Token and
Feature activation+2.303
a
Token a
Feature activation+2.273
former
Token former
Feature activation+2.356

INTERVAL 3.092 - 3.533
CONTAINS 0.000%

Z
Token Z
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
ide
Tokenide
Feature activation+0.762
h
Tokenh
Feature activation+1.578
of
Token of
Feature activation+0.000
Kemp
Token Kemp
Feature activation+3.177
Klein
Token Klein
Feature activation+2.696
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.608
case
Token case
Feature activation+0.000
leaves
Token leaves
Feature activation+0.353
county
Token county
Feature activation+0.868
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.577
s
Tokens
Feature activation+1.761
chief
Token chief
Feature activation+1.537
public
Token public
Feature activation+3.264
defender
Token defender
Feature activation+0.000
,
Token,
Feature activation+0.364
Mary
Token Mary
Feature activation+0.000
Mori
Token Mori
Feature activation+0.000
arty
Tokenarty
Feature activation+0.574
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
federal
Token federal
Feature activation+0.028
and
Token and
Feature activation+0.000
state
Token state
Feature activation+0.796
sex
Token sex
Feature activation+3.107
crimes
Token crimes
Feature activation+1.472
to
Token to
Feature activation+0.000
two
Token two
Feature activation+0.000
state
Token state
Feature activation+0.484
charges
Token charges
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
State
Token State
Feature activation+0.127
Bar
Token Bar
Feature activation+1.232
of
Token of
Feature activation+0.000
Texas
Token Texas
Feature activation+3.335
dis
Token dis
Feature activation+0.934
bar
Tokenbar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.669

INTERVAL 2.650 - 3.092
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
Athens
Token Athens
Feature activation+0.000
court
Token court
Feature activation+0.098
on
Token on
Feature activation+0.172
Wednesday
Token Wednesday
Feature activation+2.770
acquitted
Token acquitted
Feature activation+0.000
anarchist
Token anarchist
Feature activation+0.080
Cost
Token Cost
Feature activation+0.000
as
Tokenas
Feature activation+0.000
Sak
Token Sak
Feature activation+0.000
.,
Token.,
Feature activation+0.000
defense
Token defense
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
were
Token were
Feature activation+0.967
in
Token in
Feature activation+1.690
the
Token the
Feature activation+2.917
courtroom
Token courtroom
Feature activation+2.593
awaiting
Token awaiting
Feature activation+0.696
the
Token the
Feature activation+0.486
judge
Token judge
Feature activation+0.000
.
Token.
Feature activation+0.037
D
Token D
Feature activation+0.000
us
Tokenus
Feature activation+0.113
se
Tokense
Feature activation+0.611
ld
Tokenld
Feature activation+0.000
orf
Tokenorf
Feature activation+2.077
State
Token State
Feature activation+2.681
Supreme
Token Supreme
Feature activation+1.641
Court
Token Court
Feature activation+0.701
.
Token.
Feature activation+0.000
Sale
Token Sale
Feature activation+0.000
h
Tokenh
Feature activation+0.000
team
Token team
Feature activation+0.000
to
Token to
Feature activation+0.088
federal
Token federal
Feature activation+0.726
court
Token court
Feature activation+0.168
in
Token in
Feature activation+0.106
Charlottesville
Token Charlottesville
Feature activation+2.945
,
Token,
Feature activation+0.513
Va
Token Va
Feature activation+1.809
.,
Token.,
Feature activation+1.078
on
Token on
Feature activation+0.877
Tuesday
Token Tuesday
Feature activation+1.396
lawsuit
Token lawsuit
Feature activation+0.000
was
Token was
Feature activation+0.000
filed
Token filed
Feature activation+0.000
in
Token in
Feature activation+0.020
the
Token the
Feature activation+0.741
state
Token state
Feature activation+3.044
superior
Token superior
Feature activation+1.355
court
Token court
Feature activation+0.228
in
Token in
Feature activation+0.000
San
Token San
Feature activation+1.066
Francisco
Token Francisco
Feature activation+1.769

INTERVAL 2.208 - 2.650
CONTAINS 0.005%

Paul
Token Paul
Feature activation+0.000
Cas
Token Cas
Feature activation+0.000
sell
Tokensell
Feature activation+1.162
,
Token,
Feature activation+0.895
a
Token a
Feature activation+2.473
University
Token University
Feature activation+2.583
of
Token of
Feature activation+0.357
Utah
Token Utah
Feature activation+3.695
law
Token law
Feature activation+0.379
professor
Token professor
Feature activation+0.654
and
Token and
Feature activation+2.303
decision
Token decision
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+1.512
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.611
s
Tokens
Feature activation+0.678
highest
Token highest
Feature activation+0.581
court
Token court
Feature activation+0.861
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
assistant
Token assistant
Feature activation+2.153
federal
Token federal
Feature activation+2.085
public
Token public
Feature activation+1.973
defender
Token defender
Feature activation+0.000
in
Token in
Feature activation+0.268
Raleigh
Token Raleigh
Feature activation+2.441
said
Token said
Feature activation+0.154
.
Token.
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.683
Sadly
TokenSadly
Feature activation+0.680
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
fought
Token fought
Feature activation+0.000
in
Token in
Feature activation+0.003
New
Token New
Feature activation+2.351
Jersey
Token Jersey
Feature activation+2.556
's
Token's
Feature activation+0.529
courts
Token courts
Feature activation+0.000
and
Token and
Feature activation+0.000
legislature
Token legislature
Feature activation+0.142
for
Token for
Feature activation+0.355
firm
Token firm
Feature activation+0.000
of
Token of
Feature activation+0.000
Robbins
Token Robbins
Feature activation+0.984
Ar
Token Ar
Feature activation+0.230
roy
Tokenroy
Feature activation+0.000
o
Tokeno
Feature activation+2.345
filed
Token filed
Feature activation+0.000
the
Token the
Feature activation+0.000
suit
Token suit
Feature activation+0.000
last
Token last
Feature activation+0.064
Wednesday
Token Wednesday
Feature activation+0.000

INTERVAL 1.767 - 2.208
CONTAINS 0.012%

years
Token years
Feature activation+0.578
,
Token,
Feature activation+0.254
Cas
Token Cas
Feature activation+0.000
sell
Tokensell
Feature activation+1.727
and
Token and
Feature activation+0.774
Florida
Token Florida
Feature activation+1.943
attorney
Token attorney
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
Edwards
Token Edwards
Feature activation+2.940
have
Token have
Feature activation+2.846
represented
Token represented
Feature activation+0.734
Circuit
Token Circuit
Feature activation+0.296
Court
Token Court
Feature activation+0.146
of
Token of
Feature activation+0.303
Appeals
Token Appeals
Feature activation+0.169
in
Token in
Feature activation+0.000
Chicago
Token Chicago
Feature activation+1.812
to
Token to
Feature activation+0.000
reconsider
Token reconsider
Feature activation+0.000
the
Token the
Feature activation+0.000
constitution
Token constitution
Feature activation+0.000
ality
Tokenality
Feature activation+0.000
state
Token state
Feature activation+0.919
,
Token,
Feature activation+0.496
county
Token county
Feature activation+1.058
,
Token,
Feature activation+1.281
and
Token and
Feature activation+1.434
municipal
Token municipal
Feature activation+2.158
agencies
Token agencies
Feature activation+0.130
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
duties
Token duties
Feature activation+0.000
to
Token to
Feature activation+0.426
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.020
and
Token and
Feature activation+0.000
2
Token 2
Feature activation+0.857
,
Token,
Feature activation+1.271
in
Token in
Feature activation+2.057
a
Token a
Feature activation+2.942
civil
Token civil
Feature activation+2.674
lawsuit
Token lawsuit
Feature activation+0.000
against
Token against
Feature activation+1.169
the
Token the
Feature activation+1.302
December
Token December
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
pleading
Token pleading
Feature activation+0.000
not
Token not
Feature activation+1.925
guilty
Token guilty
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 1.325 - 1.767
CONTAINS 0.027%

ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.576
Cato
Token Cato
Feature activation+0.302
Institute
Token Institute
Feature activation+1.652
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.376
think
Token think
Feature activation+0.000
-
Token-
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mal
TokenMal
Feature activation+0.000
ika
Tokenika
Feature activation+0.000
Brooks
Token Brooks
Feature activation+1.735
sued
Token sued
Feature activation+0.000
three
Token three
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.674
police
Token police
Feature activation+0.000
officers
Token officers
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
beneficial
Token beneficial
Feature activation+0.000
for
Token for
Feature activation+0.568
the
Token the
Feature activation+1.604
child
Token child
Feature activation+1.031
,
Token,
Feature activation+0.397
the
Token the
Feature activation+0.691
father
Token father
Feature activation+0.000
,
Token,
Feature activation+0.197
is
Token is
Feature activation+0.305
to
Token to
Feature activation+1.019
make
Token make
Feature activation+0.000
jurors
Token jurors
Feature activation+0.000
sign
Token sign
Feature activation+0.182
a
Token a
Feature activation+1.552
pledge
Token pledge
Feature activation+0.000
not
Token not
Feature activation+0.056
to
Token to
Feature activation+0.191
research
Token research
Feature activation+0.000
Bout
Token Bout
Feature activation+0.000
when
Token when
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+2.143
District
Token District
Feature activation+1.560
Court
Token Court
Feature activation+0.596
Judge
Token Judge
Feature activation+0.000
Susan
Token Susan
Feature activation+0.000
W
Token W
Feature activation+0.000
ig
Tokenig
Feature activation+0.068

INTERVAL 0.883 - 1.325
CONTAINS 0.068%

see
Token see
Feature activation+0.000
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.872
told
Token told
Feature activation+0.991
the
Token the
Feature activation+0.639
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
is
Token is
Feature activation+0.424
that
Token that
Feature activation+0.384
the
Token the
Feature activation+1.043
presiding
Token presiding
Feature activation+1.427
judge
Token judge
Feature activation+0.000
could
Token could
Feature activation+1.102
order
Token order
Feature activation+0.220
a
Token a
Feature activation+0.825
special
Token special
Feature activation+2.082
election
Token election
Feature activation+0.000
be
Token be
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.656
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.626
If
TokenIf
Feature activation+0.694
someone
Token someone
Feature activation+1.317
is
Token is
Feature activation+1.129
innocent
Token innocent
Feature activation+0.187
,
Token,
Feature activation+0.065
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.128
settlements
Token settlements
Feature activation+0.000
in
Token in
Feature activation+0.000
similar
Token similar
Feature activation+2.125
actions
Token actions
Feature activation+0.055
,
Token,
Feature activation+0.000
notably
Token notably
Feature activation+1.042
against
Token against
Feature activation+0.000
Dire
Token Dire
Feature activation+0.000
c
Tokenc
Feature activation+0.000
TV
TokenTV
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.108
sides
Token sides
Feature activation+0.256
have
Token have
Feature activation+0.427
already
Token already
Feature activation+1.109
armored
Token armored
Feature activation+0.575
up
Token up
Feature activation+1.206
for
Token for
Feature activation+1.688
the
Token the
Feature activation+0.549
next
Token next
Feature activation+1.524
pitched
Token pitched
Feature activation+1.857
battle
Token battle
Feature activation+0.256

INTERVAL 0.442 - 0.883
CONTAINS 0.166%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
inappropriate
Token inappropriate
Feature activation+0.000
about
Token about
Feature activation+0.634
doing
Token doing
Feature activation+0.216
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Florida
Token Florida
Feature activation+1.943
attorney
Token attorney
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
Edwards
Token Edwards
Feature activation+2.940
have
Token have
Feature activation+2.846
represented
Token represented
Feature activation+0.734
two
Token two
Feature activation+1.657
women
Token women
Feature activation+1.212
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.612
only
Token only
Feature activation+0.120
included
Token included
Feature activation+0.000
close
Token close
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
friend
Token friend
Feature activation+0.168
and
Token and
Feature activation+0.000
ally
Token ally
Feature activation+0.489
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Mike
Token Mike
Feature activation+0.646
Lee
Token Lee
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
gay
Token gay
Feature activation+0.176
marriage
Token marriage
Feature activation+0.000
only
Token only
Feature activation+0.000
applied
Token applied
Feature activation+0.000
in
Token in
Feature activation+0.000
California
Token California
Feature activation+0.529
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
states
Token states
Feature activation+0.000
like
Token like
Feature activation+0.000
Idaho
Token Idaho
Feature activation+0.000
after
Token after
Feature activation+0.000
her
Token her
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.456
in
Token in
Feature activation+0.000
Manila
Token Manila
Feature activation+0.458
on
Token on
Feature activation+0.000
February
Token February
Feature activation+0.000
24
Token 24
Feature activation+0.031

INTERVAL 0.000 - 0.442
CONTAINS 99.719%

range
Token range
Feature activation+0.000
to
Token to
Feature activation+0.000
kill
Token kill
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
penal
Token penal
Feature activation+0.000
code
Token code
Feature activation+0.000
has
Token has
Feature activation+0.000
Business
Token Business
Feature activation+0.000
,
Token,
Feature activation+0.000
Innovation
Token Innovation
Feature activation+0.000
and
Token and
Feature activation+0.000
Skills
Token Skills
Feature activation+0.000
admits
Token admits
Feature activation+0.000
graduates
Token graduates
Feature activation+0.000
could
Token could
Feature activation+0.000
find
Token find
Feature activation+0.000
things
Token things
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
police
Token police
Feature activation+0.000
officer
Token officer
Feature activation+0.000
moments
Token moments
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
just
Token just
Feature activation+0.000
meant
Token meant
Feature activation+0.000
to
Token to
Feature activation+0.000
000
Token000
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
Vietnamese
Token Vietnamese
Feature activation+0.000
walked
Token walked
Feature activation+0.000
near
Token near
Feature activation+0.000
a
Token a
Feature activation+0.000
mine
Token mine
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
in
Token in
Feature activation+0.000
Angola
Token Angola
Feature activation+0.000
to
Token to
Feature activation+0.000
dram
Token dram
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ize
Tokenize
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 H11.3: (feature 20140)

TOP ACTIVATIONS
MAX = 3.719

comeback
Token comeback
Feature activation+0.000
in
Token in
Feature activation+0.825
Montreal
Token Montreal
Feature activation+1.386
Canadiens
Token Canadiens
Feature activation+1.588
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.719
history
Token history
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Jaguars
Token Jaguars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.609
stadium
Token stadium
Feature activation+0.000
,
Token,
Feature activation+0.000
Ever
Token Ever
Feature activation+0.000
Bank
TokenBank
Feature activation+0.000
Field
Token Field
Feature activation+0.000
the
Token the
Feature activation+0.236
sixth
Token sixth
Feature activation+0.000
player
Token player
Feature activation+0.000
in
Token in
Feature activation+2.073
Ot
Token Ot
Feature activation+0.000
ters
Tokenters
Feature activation+3.601
history
Token history
Feature activation+0.760
to
Token to
Feature activation+0.167
reach
Token reach
Feature activation+0.477
100
Token 100
Feature activation+1.144
points
Token points
Feature activation+0.108
-
Token-
Feature activation+0.186
best
Tokenbest
Feature activation+0.934
record
Token record
Feature activation+0.000
in
Token in
Feature activation+0.825
the
Token the
Feature activation+0.365
American
Token American
Feature activation+3.364
League
Token League
Feature activation+0.158
?
Token?
Feature activation+0.000
Uh
Token Uh
Feature activation+0.000
-
Token-
Feature activation+0.000
h
Tokenh
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
several
Token several
Feature activation+2.217
of
Token of
Feature activation+0.448
our
Token our
Feature activation+3.262
predict
Token predict
Feature activation+0.069
ors
Tokenors
Feature activation+0.638
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
season
Token season
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
emerging
Token emerging
Feature activation+0.962
Puerto
Token Puerto
Feature activation+1.133
Rican
Token Rican
Feature activation+3.118
B
Token B
Feature activation+2.674
SN
TokenSN
Feature activation+1.578
.
Token.
Feature activation+0.000
Although
Token Although
Feature activation+0.000
Pow
Token Pow
Feature activation+0.000
forged
Token forged
Feature activation+0.711
close
Token close
Feature activation+0.963
relationships
Token relationships
Feature activation+0.000
with
Token with
Feature activation+0.346
management
Token management
Feature activation+0.000
and
Token and
Feature activation+2.959
players
Token players
Feature activation+0.000
in
Token in
Feature activation+0.031
his
Token his
Feature activation+0.152
seven
Token seven
Feature activation+1.276
years
Token years
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
following
Token following
Feature activation+0.000
the
Token the
Feature activation+0.000
Jets
Token Jets
Feature activation+0.148
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.922
elimination
Token elimination
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
playoffs
Token playoffs
Feature activation+0.000
at
Token at
Feature activation+0.000
York
Token York
Feature activation+0.000
Knicks
Token Knicks
Feature activation+0.000
'
Token'
Feature activation+0.000
unicorn
Token unicorn
Feature activation+0.000
,
Token,
Feature activation+0.000
per
Token per
Feature activation+2.746
ESPN
Token ESPN
Feature activation+1.846
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.566
's
Token's
Feature activation+2.551
Ian
Token Ian
Feature activation+0.000
in
Token in
Feature activation+0.031
his
Token his
Feature activation+0.152
seven
Token seven
Feature activation+1.276
years
Token years
Feature activation+0.000
as
Token as
Feature activation+0.515
head
Token head
Feature activation+2.674
coach
Token coach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
emerging
Token emerging
Feature activation+0.962
Puerto
Token Puerto
Feature activation+1.133
Rican
Token Rican
Feature activation+3.118
B
Token B
Feature activation+2.674
SN
TokenSN
Feature activation+1.578
.
Token.
Feature activation+0.000
Although
Token Although
Feature activation+0.000
Pow
Token Pow
Feature activation+0.000
e
Tokene
Feature activation+0.238
of
Token of
Feature activation+1.162
four
Token four
Feature activation+1.564
of
Token of
Feature activation+1.981
the
Token the
Feature activation+2.536
previous
Token previous
Feature activation+1.799
five
Token five
Feature activation+2.624
MVP
Token MVP
Feature activation+0.324
awards
Token awards
Feature activation+0.533
,
Token,
Feature activation+0.000
highlights
Token highlights
Feature activation+0.978
the
Token the
Feature activation+0.048
to
Token to
Feature activation+0.000
rebuild
Token rebuild
Feature activation+0.000
their
Token their
Feature activation+1.526
once
Token once
Feature activation+0.761
-
Token-
Feature activation+1.165
great
Tokengreat
Feature activation+2.622
franchise
Token franchise
Feature activation+0.661
,
Token,
Feature activation+0.803
to
Token to
Feature activation+0.775
lay
Token lay
Feature activation+0.000
a
Token a
Feature activation+0.000
middle
Token middle
Feature activation+0.000
-
Token-
Feature activation+1.454
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+1.145
the
Tokenthe
Feature activation+1.233
-
Token-
Feature activation+2.576
road
Tokenroad
Feature activation+0.000
players
Token players
Feature activation+0.000
,
Token,
Feature activation+0.000
meaning
Token meaning
Feature activation+0.000
you
Token you
Feature activation+0.000
unicorn
Token unicorn
Feature activation+0.000
,
Token,
Feature activation+0.000
per
Token per
Feature activation+2.746
ESPN
Token ESPN
Feature activation+1.846
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.566
's
Token's
Feature activation+2.551
Ian
Token Ian
Feature activation+0.000
Beg
Token Beg
Feature activation+0.000
ley
Tokenley
Feature activation+0.340
.
Token.
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
Houston
Token Houston
Feature activation+0.000
Texans
Token Texans
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.565
A
Token A
Feature activation+0.220
rian
Tokenrian
Feature activation+0.000
Foster
Token Foster
Feature activation+0.000
came
Token came
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
7
Token 7
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+1.158
.
Token.
Feature activation+2.557
Saturday
Token Saturday
Feature activation+1.480
matchup
Token matchup
Feature activation+0.000
with
Token with
Feature activation+0.000
defending
Token defending
Feature activation+0.000
MLS
Token MLS
Feature activation+0.000
,
Token,
Feature activation+0.000
per
Token per
Feature activation+2.746
ESPN
Token ESPN
Feature activation+1.846
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.566
's
Token's
Feature activation+2.551
Ian
Token Ian
Feature activation+0.000
Beg
Token Beg
Feature activation+0.000
ley
Tokenley
Feature activation+0.340
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
most
Token most
Feature activation+0.114
memorable
Token memorable
Feature activation+1.051
role
Token role
Feature activation+0.000
players
Token players
Feature activation+1.164
in
Token in
Feature activation+1.891
recent
Token recent
Feature activation+2.542
Celtics
Token Celtics
Feature activation+2.328
history
Token history
Feature activation+0.760
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+0.749
winner
Token winner
Feature activation+0.358
of
Token of
Feature activation+1.162
four
Token four
Feature activation+1.564
of
Token of
Feature activation+1.981
the
Token the
Feature activation+2.536
previous
Token previous
Feature activation+1.799
five
Token five
Feature activation+2.624
MVP
Token MVP
Feature activation+0.324
awards
Token awards
Feature activation+0.533
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 4.842

the
Token the
Feature activation+0.015
Top resid features:
biggest
Token biggest
Feature activation+0.028
Top resid features:
comeback
Token comeback
Feature activation+0.141
Top resid features:
in
Token in
Feature activation+0.195
Top resid features:
Montreal
Token Montreal
Feature activation+0.432
Top resid features:
Canadiens
Token Canadiens
Feature activation+3.119
Top resid features:
âĢ
TokenâĢ
Feature activation-0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
history
Token history
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:
the
Token the
Feature activation+0.009
Top resid features:
Brooklyn
Token Brooklyn
Feature activation+0.017
Top resid features:
neighborhood
Token neighborhood
Feature activation-0.093
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
Jaguars
Token Jaguars
Feature activation+4.842
Top resid features:
âĢ
TokenâĢ
Feature activation-0.053
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
stadium
Token stadium
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ever
Token Ever
Feature activation+0.000
Top resid features:
He
Token He
Feature activation-0.030
Top resid features:
becomes
Token becomes
Feature activation+0.133
Top resid features:
the
Token the
Feature activation+0.112
Top resid features:
sixth
Token sixth
Feature activation+0.618
Top resid features:
player
Token player
Feature activation+0.304
Top resid features:
in
Token in
Feature activation+0.942
Top resid features:
Ot
Token Ot
Feature activation+0.011
Top resid features:
ters
Tokenters
Feature activation+0.690
Top resid features:
history
Token history
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
reach
Token reach
Feature activation+0.000
Top resid features:
second
Token second
Feature activation+0.204
Top resid features:
-
Token-
Feature activation+0.029
Top resid features:
best
Tokenbest
Feature activation+0.691
Top resid features:
record
Token record
Feature activation+0.155
Top resid features:
in
Token in
Feature activation+0.873
Top resid features:
the
Token the
Feature activation+0.912
Top resid features:
American
Token American
Feature activation+0.032
Top resid features:
League
Token League
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Uh
Token Uh
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.048
Top resid features:
has
Token has
Feature activation-0.036
Top resid features:
led
Token led
Feature activation+0.093
Top resid features:
to
Token to
Feature activation+0.189
Top resid features:
support
Token support
Feature activation+0.198
Top resid features:
from
Token from
Feature activation+0.537
Top resid features:
several
Token several
Feature activation+0.128
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
our
Token our
Feature activation+0.002
Top resid features:
predict
Token predict
Feature activation+0.000
Top resid features:
ors
Tokenors
Feature activation+0.000
Top resid features:
playing
Token playing
Feature activation+0.479
Top resid features:
a
Token a
Feature activation+0.110
Top resid features:
season
Token season
Feature activation+0.181
Top resid features:
in
Token in
Feature activation+0.106
Top resid features:
the
Token the
Feature activation+1.078
Top resid features:
emerging
Token emerging
Feature activation+1.360
Top resid features:
Puerto
Token Puerto
Feature activation+0.040
Top resid features:
Rican
Token Rican
Feature activation+0.176
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
SN
TokenSN
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
has
Token has
Feature activation-0.037
Top resid features:
forged
Token forged
Feature activation+0.028
Top resid features:
close
Token close
Feature activation+0.007
Top resid features:
relationships
Token relationships
Feature activation+0.016
Top resid features:
with
Token with
Feature activation+1.693
Top resid features:
management
Token management
Feature activation+0.187
Top resid features:
and
Token and
Feature activation+0.113
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.013
Top resid features:
he
Token he
Feature activation-0.004
Top resid features:
spoke
Token spoke
Feature activation+0.006
Top resid features:
following
Token following
Feature activation+0.572
Top resid features:
the
Token the
Feature activation+0.434
Top resid features:
Jets
Token Jets
Feature activation+1.604
Top resid features:
âĢ
TokenâĢ
Feature activation-0.058
Top resid features:
Ļ
TokenĻ
Feature activation-0.010
Top resid features:
elimination
Token elimination
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:
the
Token the
Feature activation-0.030
Top resid features:
New
Token New
Feature activation+0.010
Top resid features:
York
Token York
Feature activation+0.058
Top resid features:
Knicks
Token Knicks
Feature activation+0.729
Top resid features:
'
Token'
Feature activation+0.086
Top resid features:
unicorn
Token unicorn
Feature activation+0.960
Top resid features:
,
Token,
Feature activation+0.195
Top resid features:
per
Token per
Feature activation-0.048
Top resid features:
ESPN
Token ESPN
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.099
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
his
Token his
Feature activation+0.136
Top resid features:
seven
Token seven
Feature activation+0.024
Top resid features:
years
Token years
Feature activation+0.065
Top resid features:
as
Token as
Feature activation+0.969
Top resid features:
head
Token head
Feature activation+0.185
Top resid features:
coach
Token coach
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:
playing
Token playing
Feature activation+0.143
Top resid features:
a
Token a
Feature activation+0.063
Top resid features:
season
Token season
Feature activation+0.070
Top resid features:
in
Token in
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.965
Top resid features:
emerging
Token emerging
Feature activation+1.343
Top resid features:
Puerto
Token Puerto
Feature activation+0.135
Top resid features:
Rican
Token Rican
Feature activation+0.237
Top resid features:
B
Token B
Feature activation+0.055
Top resid features:
SN
TokenSN
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.147
Top resid features:
2012
Token 2012
Feature activation+0.133
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
13
Token13
Feature activation+0.075
Top resid features:
K
Token K
Feature activation+0.679
Top resid features:
ia
Tokenia
Feature activation+0.173
Top resid features:
NBA
Token NBA
Feature activation+0.427
Top resid features:
Most
Token Most
Feature activation-0.001
Top resid features:
Val
Token Val
Feature activation-0.007
Top resid features:
uable
Tokenuable
Feature activation+0.070
Top resid features:
U
TokenU
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.014
Top resid features:
The
TokenThe
Feature activation-0.027
Top resid features:
Los
Token Los
Feature activation+0.045
Top resid features:
Angeles
Token Angeles
Feature activation+0.120
Top resid features:
Lakers
Token Lakers
Feature activation+1.576
Top resid features:
are
Token are
Feature activation-0.080
Top resid features:
currently
Token currently
Feature activation-0.027
Top resid features:
looking
Token looking
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.091
Top resid features:
rebuild
Token rebuild
Feature activation+0.621
Top resid features:
toward
Token toward
Feature activation+0.016
Top resid features:
middle
Token middle
Feature activation+0.531
Top resid features:
-
Token-
Feature activation+0.091
Top resid features:
of
Tokenof
Feature activation+0.502
Top resid features:
-
Token-
Feature activation+0.094
Top resid features:
the
Tokenthe
Feature activation+1.759
Top resid features:
-
Token-
Feature activation+0.269
Top resid features:
road
Tokenroad
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:
meaning
Token meaning
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.028
Top resid features:
dealing
Token dealing
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
New
Token New
Feature activation+0.013
Top resid features:
York
Token York
Feature activation+0.038
Top resid features:
Knicks
Token Knicks
Feature activation+0.895
Top resid features:
'
Token'
Feature activation+0.196
Top resid features:
unicorn
Token unicorn
Feature activation+0.645
Top resid features:
,
Token,
Feature activation+0.203
Top resid features:
per
Token per
Feature activation+0.214
Top resid features:
ESPN
Token ESPN
Feature activation+0.301
Top resid features:
few
Token few
Feature activation-0.054
Top resid features:
days
Token days
Feature activation+0.002
Top resid features:
since
Token since
Feature activation-0.092
Top resid features:
the
Token the
Feature activation-0.085
Top resid features:
Houston
Token Houston
Feature activation+0.445
Top resid features:
Texans
Token Texans
Feature activation+2.867
Top resid features:
âĢ
TokenâĢ
Feature activation-0.055
Top resid features:
Ļ
TokenĻ
Feature activation-0.038
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
rian
Tokenrian
Feature activation+0.000
Top resid features:
Foster
Token Foster
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.073
Top resid features:
key
Token key
Feature activation+0.034
Top resid features:
pieces
Token pieces
Feature activation+0.076
Top resid features:
heading
Token heading
Feature activation+0.025
Top resid features:
into
Token into
Feature activation+0.621
Top resid features:
a
Token a
Feature activation+0.750
Top resid features:
7
Token 7
Feature activation-0.004
Top resid features:
p
Token p
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
m
Tokenm
Feature activation+0.582
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
from
Token from
Feature activation-0.005
Top resid features:
dealing
Token dealing
Feature activation+0.052
Top resid features:
the
Token the
Feature activation-0.028
Top resid features:
New
Token New
Feature activation+0.028
Top resid features:
York
Token York
Feature activation+0.074
Top resid features:
Knicks
Token Knicks
Feature activation+1.165
Top resid features:
'
Token'
Feature activation+0.101
Top resid features:
unicorn
Token unicorn
Feature activation+0.642
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
per
Token per
Feature activation+0.313
Top resid features:
ESPN
Token ESPN
Feature activation+0.476
Top resid features:
the
Token the
Feature activation+0.294
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
memorable
Token memorable
Feature activation+0.223
Top resid features:
role
Token role
Feature activation+0.008
Top resid features:
players
Token players
Feature activation+0.414
Top resid features:
in
Token in
Feature activation+0.968
Top resid features:
recent
Token recent
Feature activation+0.136
Top resid features:
Celtics
Token Celtics
Feature activation+0.000
Top resid features:
history
Token history
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:
.
Token.
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.019
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.008
Top resid features:
The
Token The
Feature activation-0.006
Top resid features:
Miami
Token Miami
Feature activation+0.049
Top resid features:
Heat
Token Heat
Feature activation+0.948
Top resid features:
's
Token's
Feature activation+0.058
Top resid features:
LeBron
Token LeBron
Feature activation+0.064
Top resid features:
James
Token James
Feature activation+0.055
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.04

Head 2: 0.04

Head 3: 0.34

Head 4: 0.06

Head 5: 0.04

Head 6: 0.03

Head 7: 0.06

Head 8: 0.17

Head 9: 0.03

Head 10: 0.05

Head 11: 0.05

Positive logits

NBA5.03

NBA4.99

asketball4.94

Baseball4.93

MLB4.93

Basketball4.92

basketball4.90

Football4.88

NFL4.88

league4.88

offseason4.82

baseball4.78

NFL4.75

football4.73

Players4.71

Coach4.70

NHL4.67

basketball4.67

Football4.66

preseason4.60

Negative logits

unsupported-2.56

Indones-2.46

cens-2.43

Tanz-2.42

Feminist-2.32

SPONSORED-2.31

TRAN-2.22

Merkel-2.19

Tablet-2.18

censorship-2.18

Shant-2.17

ë-2.15

animate-2.15

diarr-2.14

BOOK-2.14

izen-2.13

UNESCO-2.12

Farage-2.12

moderator-2.09

Soros-2.07

INTERVAL 3.347 - 3.719
CONTAINS 0.000%

neighborhood
Token neighborhood
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Jaguars
Token Jaguars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.609
stadium
Token stadium
Feature activation+0.000
,
Token,
Feature activation+0.000
Ever
Token Ever
Feature activation+0.000
Bank
TokenBank
Feature activation+0.000
Field
Token Field
Feature activation+0.000
comeback
Token comeback
Feature activation+0.000
in
Token in
Feature activation+0.825
Montreal
Token Montreal
Feature activation+1.386
Canadiens
Token Canadiens
Feature activation+1.588
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.719
history
Token history
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
-
Token-
Feature activation+0.186
best
Tokenbest
Feature activation+0.934
record
Token record
Feature activation+0.000
in
Token in
Feature activation+0.825
the
Token the
Feature activation+0.365
American
Token American
Feature activation+3.364
League
Token League
Feature activation+0.158
?
Token?
Feature activation+0.000
Uh
Token Uh
Feature activation+0.000
-
Token-
Feature activation+0.000
h
Tokenh
Feature activation+0.000
the
Token the
Feature activation+0.236
sixth
Token sixth
Feature activation+0.000
player
Token player
Feature activation+0.000
in
Token in
Feature activation+2.073
Ot
Token Ot
Feature activation+0.000
ters
Tokenters
Feature activation+3.601
history
Token history
Feature activation+0.760
to
Token to
Feature activation+0.167
reach
Token reach
Feature activation+0.477
100
Token 100
Feature activation+1.144
points
Token points
Feature activation+0.108

INTERVAL 2.975 - 3.347
CONTAINS 0.000%

to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
several
Token several
Feature activation+2.217
of
Token of
Feature activation+0.448
our
Token our
Feature activation+3.262
predict
Token predict
Feature activation+0.069
ors
Tokenors
Feature activation+0.638
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
season
Token season
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
emerging
Token emerging
Feature activation+0.962
Puerto
Token Puerto
Feature activation+1.133
Rican
Token Rican
Feature activation+3.118
B
Token B
Feature activation+2.674
SN
TokenSN
Feature activation+1.578
.
Token.
Feature activation+0.000
Although
Token Although
Feature activation+0.000
Pow
Token Pow
Feature activation+0.000

INTERVAL 2.603 - 2.975
CONTAINS 0.001%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
emerging
Token emerging
Feature activation+0.962
Puerto
Token Puerto
Feature activation+1.133
Rican
Token Rican
Feature activation+3.118
B
Token B
Feature activation+2.674
SN
TokenSN
Feature activation+1.578
.
Token.
Feature activation+0.000
Although
Token Although
Feature activation+0.000
Pow
Token Pow
Feature activation+0.000
e
Tokene
Feature activation+0.238
to
Token to
Feature activation+0.000
rebuild
Token rebuild
Feature activation+0.000
their
Token their
Feature activation+1.526
once
Token once
Feature activation+0.761
-
Token-
Feature activation+1.165
great
Tokengreat
Feature activation+2.622
franchise
Token franchise
Feature activation+0.661
,
Token,
Feature activation+0.803
to
Token to
Feature activation+0.775
lay
Token lay
Feature activation+0.000
a
Token a
Feature activation+0.000
in
Token in
Feature activation+0.031
his
Token his
Feature activation+0.152
seven
Token seven
Feature activation+1.276
years
Token years
Feature activation+0.000
as
Token as
Feature activation+0.515
head
Token head
Feature activation+2.674
coach
Token coach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.000
York
Token York
Feature activation+0.000
Knicks
Token Knicks
Feature activation+0.000
'
Token'
Feature activation+0.000
unicorn
Token unicorn
Feature activation+0.000
,
Token,
Feature activation+0.000
per
Token per
Feature activation+2.746
ESPN
Token ESPN
Feature activation+1.846
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.566
's
Token's
Feature activation+2.551
Ian
Token Ian
Feature activation+0.000
of
Token of
Feature activation+1.162
four
Token four
Feature activation+1.564
of
Token of
Feature activation+1.981
the
Token the
Feature activation+2.536
previous
Token previous
Feature activation+1.799
five
Token five
Feature activation+2.624
MVP
Token MVP
Feature activation+0.324
awards
Token awards
Feature activation+0.533
,
Token,
Feature activation+0.000
highlights
Token highlights
Feature activation+0.978
the
Token the
Feature activation+0.048

INTERVAL 2.232 - 2.603
CONTAINS 0.004%

memorable
Token memorable
Feature activation+1.051
role
Token role
Feature activation+0.000
players
Token players
Feature activation+1.164
in
Token in
Feature activation+1.891
recent
Token recent
Feature activation+2.542
Celtics
Token Celtics
Feature activation+2.328
history
Token history
Feature activation+0.760
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+0.970
of
Token of
Feature activation+2.035
G
Token G
Feature activation+0.172
NG
TokenNG
Feature activation+2.405
H
TokenH
Feature activation+2.418
ockey
Tokenockey
Feature activation+1.311
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.255
beginnings
Token beginnings
Feature activation+0.000
101
Token 101
Feature activation+0.334
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.132
Heat
Token Heat
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.306
s
Tokens
Feature activation+0.000
facility
Token facility
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.413
odds
Token odds
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+2.320
C
Token C
Feature activation+0.074
ough
Tokenough
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
's
Token's
Feature activation+0.256
favor
Token favor
Feature activation+0.762
Located
Token Located
Feature activation+0.000
in
Token in
Feature activation+0.000
Mississ
Token Mississ
Feature activation+0.000
auga
Tokenauga
Feature activation+0.660
,
Token,
Feature activation+0.000
20
Token 20
Feature activation+2.250
minutes
Token minutes
Feature activation+1.203
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.000
downtown
Token downtown
Feature activation+0.000
Toronto
Token Toronto
Feature activation+1.012

INTERVAL 1.860 - 2.232
CONTAINS 0.006%

Blues
Token Blues
Feature activation+0.000
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.604
ahead
Token ahead
Feature activation+2.193
of
Token of
Feature activation+1.280
schedule
Token schedule
Feature activation+2.107
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
you
Token you
Feature activation+0.000
consider
Token consider
Feature activation+0.451
many
Token many
Feature activation+0.988
best
Tokenbest
Feature activation+0.000
single
Token single
Feature activation+0.000
season
Token season
Feature activation+0.000
total
Token total
Feature activation+0.000
in
Token in
Feature activation+0.000
USC
Token USC
Feature activation+1.933
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
finished
Token finished
Feature activation+0.000
the
Token the
Feature activation+0.030
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.275
15
Token 15
Feature activation+1.562
-
Token-
Feature activation+1.483
year
Tokenyear
Feature activation+2.059
career
Token career
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Base
TokenBase
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
shape
Token shape
Feature activation+0.090
of
Token of
Feature activation+0.520
his
Token his
Feature activation+2.151
life
Token life
Feature activation+0.000
and
Token and
Feature activation+0.000
wanting
Token wanting
Feature activation+0.965
to
Token to
Feature activation+0.708
be
Token be
Feature activation+0.000
er
Tokener
Feature activation+0.000
as
Token as
Feature activation+0.000
their
Token their
Feature activation+0.402
19
Token 19
Feature activation+0.794
th
Tokenth
Feature activation+0.567
head
Token head
Feature activation+2.090
coach
Token coach
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
start
Token start
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.488 - 1.860
CONTAINS 0.013%

s
Tokens
Feature activation+0.000
claim
Token claim
Feature activation+0.000
and
Token and
Feature activation+0.521
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
followed
Token followed
Feature activation+1.518
the
Token the
Feature activation+0.518
mandated
Token mandated
Feature activation+0.170
protocol
Token protocol
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
Knicks
Token Knicks
Feature activation+0.000
'
Token'
Feature activation+0.000
unicorn
Token unicorn
Feature activation+0.000
,
Token,
Feature activation+0.000
per
Token per
Feature activation+2.746
ESPN
Token ESPN
Feature activation+1.846
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.566
's
Token's
Feature activation+2.551
Ian
Token Ian
Feature activation+0.000
Beg
Token Beg
Feature activation+0.000
.),
Token.),
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
McCabe
Token McCabe
Feature activation+0.000
(
Token (
Feature activation+0.000
Players
TokenPlayers
Feature activation+0.331
Development
Token Development
Feature activation+1.619
Academy
Token Academy
Feature activation+0.545
;
Token;
Feature activation+0.000
South
Token South
Feature activation+0.000
Orange
Token Orange
Feature activation+0.444
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Tigers
Token Tigers
Feature activation+0.000
a
Token a
Feature activation+0.000
14
Token 14
Feature activation+0.889
.
Token.
Feature activation+0.000
4
Token4
Feature activation+1.847
percent
Token percent
Feature activation+0.406
chance
Token chance
Feature activation+0.000
of
Token of
Feature activation+0.000
making
Token making
Feature activation+0.000
the
Token the
Feature activation+0.000
he
Token he
Feature activation+0.000
end
Token end
Feature activation+0.000
ures
Tokenures
Feature activation+0.636
as
Token as
Feature activation+0.327
one
Token one
Feature activation+0.618
of
Token of
Feature activation+1.539
the
Token the
Feature activation+0.868
most
Token most
Feature activation+0.114
memorable
Token memorable
Feature activation+1.051
role
Token role
Feature activation+0.000
players
Token players
Feature activation+1.164

INTERVAL 1.116 - 1.488
CONTAINS 0.031%

in
Token in
Feature activation+0.000
Mississ
Token Mississ
Feature activation+0.000
auga
Tokenauga
Feature activation+0.660
,
Token,
Feature activation+0.000
20
Token 20
Feature activation+2.250
minutes
Token minutes
Feature activation+1.203
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.000
downtown
Token downtown
Feature activation+0.000
Toronto
Token Toronto
Feature activation+1.012
,
Token,
Feature activation+0.000
coaching
Token coaching
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.175
Pirates
Token Pirates
Feature activation+0.376
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.296
farm
Token farm
Feature activation+0.120
system
Token system
Feature activation+0.000
during
Token during
Feature activation+0.599
Vog
Token Vog
Feature activation+0.000
els
Tokenels
Feature activation+0.000
Heat
Token Heat
Feature activation+0.204
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.304
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+1.473
Back
TokenBack
Feature activation+0.476
To
Token To
Feature activation+1.218
School
Token School
Feature activation+1.969
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.667
from
Token from
Feature activation+0.119
High
Token High
Feature activation+0.039
Five
Token Five
Feature activation+1.368
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.565
new
Token new
Feature activation+1.271
and
Token and
Feature activation+0.145
rising
Token rising
Feature activation+1.382
club
Token club
Feature activation+0.000
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.506
itt
Tokenitt
Feature activation+0.000
said
Token said
Feature activation+0.000
after
Token after
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.143
s
Tokens
Feature activation+0.000
workout
Token workout
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.744 - 1.116
CONTAINS 0.063%

an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.000
of
Token of
Feature activation+0.000
18
Token 18
Feature activation+0.775
.
Token.
Feature activation+0.000
9
Token9
Feature activation+1.033
points
Token points
Feature activation+0.000
per
Token per
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
overall
Token overall
Feature activation+0.000
in
Token in
Feature activation+0.333
ESPN
Token ESPN
Feature activation+1.511
's
Token's
Feature activation+2.333
class
Token class
Feature activation+0.639
of
Token of
Feature activation+0.864
2017
Token 2017
Feature activation+0.157
rankings
Token rankings
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
received
Token received
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.333
the
Token the
Feature activation+1.011
other
Token other
Feature activation+0.931
hand
Token hand
Feature activation+0.219
,
Token,
Feature activation+0.062
the
Token the
Feature activation+0.159
Dodgers
Token Dodgers
Feature activation+0.000
,
Token,
Feature activation+0.000
named
Token named
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.251
strong
Token strong
Feature activation+0.000
South
Token South
Feature activation+0.000
Africa
Token Africa
Feature activation+1.020
A
Token A
Feature activation+0.228
squad
Token squad
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
fixture
Token fixture
Feature activation+0.000
.
Token.
Feature activation+0.000
75
Token75
Feature activation+0.289
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
Average
Token Average
Feature activation+0.995
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
916
Token916
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000

INTERVAL 0.372 - 0.744
CONTAINS 0.139%

despite
Token despite
Feature activation+0.000
signing
Token signing
Feature activation+0.000
a
Token a
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.659
year
Tokenyear
Feature activation+0.415
deal
Token deal
Feature activation+0.000
worth
Token worth
Feature activation+0.000
$
Token $
Feature activation+0.000
13
Token13
Feature activation+0.000
million
Token million
Feature activation+0.000
of
Token of
Feature activation+0.289
the
Token the
Feature activation+0.000
sport
Token sport
Feature activation+0.204
at
Token at
Feature activation+0.000
their
Token their
Feature activation+0.564
respective
Token respective
Feature activation+0.509
institutions
Token institutions
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
behavior
Token behavior
Feature activation+0.000
that
Token that
Feature activation+0.237
threatens
Token threatens
Feature activation+1.328
to
Token to
Feature activation+0.000
undermine
Token undermine
Feature activation+1.536
the
Token the
Feature activation+0.551
fabric
Token fabric
Feature activation+0.000
of
Token of
Feature activation+2.531
the
Token the
Feature activation+1.637
game
Token game
Feature activation+0.110
.
Token.
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.345
Italy
Token Italy
Feature activation+0.485
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.407
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+0.000
by
Token by
Feature activation+0.000
Commissioner
Token Commissioner
Feature activation+0.000
Roger
Token Roger
Feature activation+0.000
Goodell
Token Goodell
Feature activation+0.000
to
Token to
Feature activation+0.000
mend
Token mend
Feature activation+0.498
fences
Token fences
Feature activation+0.000
with
Token with
Feature activation+0.057
players
Token players
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.372
CONTAINS 99.743%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Zen
TokenZen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Love
TokenLove
Feature activation+0.000
or
Tokenor
Feature activation+0.000
mold
Token mold
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
)
Token)
Feature activation+0.000
toilets
Token toilets
Feature activation+0.000
,
Token,
Feature activation+0.000
active
Token active
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
(
Token (
Feature activation+0.000
self
Tokenself
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Kaine
Token Kaine
Feature activation+0.000
continued
Token continued
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
But
TokenBut
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
robbery
Token robbery
Feature activation+0.000
gone
Token gone
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
appear
Token appear
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
directly
Token directly
Feature activation+0.000
change
Token change
Feature activation+0.000
policy
Token policy
Feature activation+0.000
and
Token and
Feature activation+0.000
procedure
Token procedure
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
widely
Token widely
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 H11.3: (feature 9406)

TOP ACTIVATIONS
MAX = 3.194

also
Token also
Feature activation+0.000
running
Token running
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Working
Token Working
Feature activation+0.234
Families
Token Families
Feature activation+3.194
line
Token line
Feature activation+0.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
and
Token and
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
is
Token is
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
based
Token based
Feature activation+3.126
on
Token on
Feature activation+0.000
overall
Token overall
Feature activation+0.000
turnout
Token turnout
Feature activation+0.000
.
Token.
Feature activation+0.000
Sources
Token Sources
Feature activation+2.244
ittal
Tokenittal
Feature activation+0.000
on
Token on
Feature activation+0.837
what
Token what
Feature activation+0.832
,
Token,
Feature activation+0.000
if
Token if
Feature activation+2.146
anything
Token anything
Feature activation+3.092
,
Token,
Feature activation+0.469
the
Token the
Feature activation+0.639
president
Token president
Feature activation+0.913
will
Token will
Feature activation+1.045
do
Token do
Feature activation+0.000
Dave
Token Dave
Feature activation+0.000
Le
Token Le
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.036
s
Tokens
Feature activation+3.011
Atlas
Token Atlas
Feature activation+0.530
of
Token of
Feature activation+0.795
U
Token U
Feature activation+0.577
.
Token.
Feature activation+2.202
S
TokenS
Feature activation+2.982
s
Tokens
Feature activation+3.011
Atlas
Token Atlas
Feature activation+0.530
of
Token of
Feature activation+0.795
U
Token U
Feature activation+0.577
.
Token.
Feature activation+2.202
S
TokenS
Feature activation+2.982
.
Token.
Feature activation+2.367
Presidential
Token Presidential
Feature activation+0.133
Elections
Token Elections
Feature activation+0.662
,
Token,
Feature activation+1.958
The
Token The
Feature activation+1.143
a
Token a
Feature activation+0.000
major
Token major
Feature activation+1.591
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+2.360
.
Token.
Feature activation+2.885
political
Token political
Feature activation+1.581
party
Token party
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Elections
Token Elections
Feature activation+0.662
,
Token,
Feature activation+1.958
The
Token The
Feature activation+1.143
Green
Token Green
Feature activation+0.439
Papers
Token Papers
Feature activation+1.548
,
Token,
Feature activation+2.818
U
Token U
Feature activation+0.627
.
Token.
Feature activation+2.379
S
TokenS
Feature activation+2.126
.
Token.
Feature activation+1.542
Elections
Token Elections
Feature activation+0.000
John
Token John
Feature activation+0.000
Av
Token Av
Feature activation+0.000
lon
Tokenlon
Feature activation+0.206
,
Token,
Feature activation+0.324
author
Token author
Feature activation+0.297
of
Token of
Feature activation+2.791
"
Token "
Feature activation+0.938
Independent
TokenIndependent
Feature activation+1.048
Nation
Token Nation
Feature activation+1.533
:
Token:
Feature activation+0.711
How
Token How
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.000
New
Token New
Feature activation+1.635
York
Token York
Feature activation+1.606
âĢ
TokenâĢ
Feature activation+0.098
Ļ
TokenĻ
Feature activation+2.752
s
Tokens
Feature activation+1.712
contest
Token contest
Feature activation+0.000
by
Token by
Feature activation+0.000
accusing
Token accusing
Feature activation+0.412
Michael
Token Michael
Feature activation+0.000
,
Token,
Feature activation+2.194
one
Token one
Feature activation+2.043
of
Token of
Feature activation+2.202
Indiana
Token Indiana
Feature activation+2.169
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.714
s
Tokens
Feature activation+1.513
two
Token two
Feature activation+1.696
members
Token members
Feature activation+0.843
of
Token of
Feature activation+1.692
the
Token the
Feature activation+1.533
a
Token a
Feature activation+2.357
political
Token political
Feature activation+0.888
veteran
Token veteran
Feature activation+1.508
as
Token as
Feature activation+1.160
chief
Token chief
Feature activation+2.599
of
Token of
Feature activation+2.703
staff
Token staff
Feature activation+0.749
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.815
political
Token political
Feature activation+0.000
action
Token action
Feature activation+0.018
2012
Token 2012
Feature activation+0.889
presidential
Token presidential
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.744
analysts
Token analysts
Feature activation+0.000
and
Token and
Feature activation+2.683
experts
Token experts
Feature activation+0.162
say
Token say
Feature activation+0.477
.
Token.
Feature activation+1.332
Conservative
Token Conservative
Feature activation+0.502
groups
Token groups
Feature activation+0.000
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+1.086
pockets
Token pockets
Feature activation+0.047
of
Token of
Feature activation+0.967
corporate
Token corporate
Feature activation+2.622
America
Token America
Feature activation+0.827
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
donations
Token donations
Feature activation+0.000
coming
Token coming
Feature activation+0.000
is
Token is
Feature activation+0.000
set
Token set
Feature activation+0.117
to
Token to
Feature activation+0.000
pick
Token pick
Feature activation+0.000
up
Token up
Feature activation+1.038
one
Token one
Feature activation+2.610
of
Token of
Feature activation+0.992
his
Token his
Feature activation+0.961
biggest
Token biggest
Feature activation+0.948
endorsements
Token endorsements
Feature activation+0.000
yet
Token yet
Feature activation+0.198
hired
Token hired
Feature activation+1.858
a
Token a
Feature activation+2.357
political
Token political
Feature activation+0.888
veteran
Token veteran
Feature activation+1.508
as
Token as
Feature activation+1.160
chief
Token chief
Feature activation+2.599
of
Token of
Feature activation+2.703
staff
Token staff
Feature activation+0.749
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.815
political
Token political
Feature activation+0.000
face
Token face
Feature activation+0.000
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.253
and
Token and
Feature activation+0.000
Independence
Token Independence
Feature activation+2.565
primaries
Token primaries
Feature activation+0.000
.
Token.
Feature activation+0.000
Th
Token Th
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
en
Tokenen
Feature activation+1.020
polling
Token polling
Feature activation+0.000
sites
Token sites
Feature activation+0.103
available
Token available
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.136
duration
Token duration
Feature activation+2.555
of
Token of
Feature activation+1.341
in
Token in
Feature activation+1.771
-
Token-
Feature activation+2.143
person
Tokenperson
Feature activation+1.352
early
Token early
Feature activation+2.198
PAC
Token PAC
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.511
the
Token the
Feature activation+0.253
âĢ
Token âĢ
Feature activation+0.176
ĺ
Tokenĺ
Feature activation+2.523
cand
Tokencand
Feature activation+0.000
idate
Tokenidate
Feature activation+0.000
windows
Token windows
Feature activation+1.365
âĢ
TokenâĢ
Feature activation+0.172
Ļ
TokenĻ
Feature activation+2.190
Wu
Token Wu
Feature activation+0.039
,
Token,
Feature activation+0.257
in
Token in
Feature activation+0.468
Tuesday
Token Tuesday
Feature activation+1.664
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.500
s
Tokens
Feature activation+1.989
primary
Token primary
Feature activation+0.929
,
Token,
Feature activation+0.491
party
Token party
Feature activation+0.120
insiders
Token insiders
Feature activation+0.438
In
Token In
Feature activation+0.177
a
Token a
Feature activation+0.000
live
Token live
Feature activation+0.566
-
Token-
Feature activation+1.798
stream
Tokenstream
Feature activation+1.931
ed
Tokened
Feature activation+2.473
video
Token video
Feature activation+1.013
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Vermont
Token Vermont
Feature activation+0.000
senator
Token senator
Feature activation+0.000

Top DFA by src position
MAX = 2.393

ki
Tokenki
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.023
Top resid features:
also
Token also
Feature activation+0.045
Top resid features:
running
Token running
Feature activation+0.835
Top resid features:
on
Token on
Feature activation+0.554
Top resid features:
the
Token the
Feature activation+1.002
Top resid features:
Working
Token Working
Feature activation+0.051
Top resid features:
Families
Token Families
Feature activation+0.070
Top resid features:
line
Token line
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
actual
Token actual
Feature activation+0.071
Top resid features:
results
Token results
Feature activation+0.083
Top resid features:
Popular
Token Popular
Feature activation+0.170
Top resid features:
vote
Token vote
Feature activation+0.416
Top resid features:
in
Token in
Feature activation+0.172
Top resid features:
Iowa
Token Iowa
Feature activation+0.491
Top resid features:
,
Token,
Feature activation+0.137
Top resid features:
Nevada
Token Nevada
Feature activation+0.140
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
Maine
Token Maine
Feature activation+0.221
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
been
Token been
Feature activation+0.021
Top resid features:
non
Token non
Feature activation+0.063
Top resid features:
comm
Tokencomm
Feature activation+0.002
Top resid features:
ittal
Tokenittal
Feature activation-0.018
Top resid features:
on
Token on
Feature activation+0.298
Top resid features:
what
Token what
Feature activation+0.817
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
if
Token if
Feature activation+0.011
Top resid features:
anything
Token anything
Feature activation+0.124
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.279
Top resid features:
overall
Token overall
Feature activation+0.103
Top resid features:
turnout
Token turnout
Feature activation+0.183
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
Sources
Token Sources
Feature activation+0.053
Top resid features:
:
Token:
Feature activation+0.824
Top resid features:
Dave
Token Dave
Feature activation+0.111
Top resid features:
Le
Token Le
Feature activation+0.033
Top resid features:
ip
Tokenip
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.099
Top resid features:
Ļ
TokenĻ
Feature activation+0.270
Top resid features:
ip
Tokenip
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.065
Top resid features:
Ļ
TokenĻ
Feature activation+0.065
Top resid features:
s
Tokens
Feature activation+0.057
Top resid features:
Atlas
Token Atlas
Feature activation+0.146
Top resid features:
of
Token of
Feature activation+2.249
Top resid features:
U
Token U
Feature activation+0.062
Top resid features:
.
Token.
Feature activation-0.058
Top resid features:
S
TokenS
Feature activation+0.156
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Presidential
Token Presidential
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
presidential
Token presidential
Feature activation+0.002
Top resid features:
nomination
Token nomination
Feature activation+0.038
Top resid features:
of
Token of
Feature activation-0.027
Top resid features:
a
Token a
Feature activation+0.541
Top resid features:
major
Token major
Feature activation+2.194
Top resid features:
U
Token U
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
S
TokenS
Feature activation+0.462
Top resid features:
.
Token.
Feature activation-0.068
Top resid features:
political
Token political
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.075
Top resid features:
U
Token U
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
S
TokenS
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Presidential
Token Presidential
Feature activation+1.089
Top resid features:
Elections
Token Elections
Feature activation+0.329
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
The
Token The
Feature activation-0.014
Top resid features:
Green
Token Green
Feature activation+0.179
Top resid features:
Papers
Token Papers
Feature activation+0.138
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
Republican
Token Republican
Feature activation+0.150
Top resid features:
parties
Token parties
Feature activation+0.078
Top resid features:
--
Token --
Feature activation+0.126
Top resid features:
their
Token their
Feature activation+0.133
Top resid features:
votes
Token votes
Feature activation+0.730
Top resid features:
are
Token are
Feature activation+0.042
Top resid features:
predictable
Token predictable
Feature activation+0.358
Top resid features:
,"
Token,"
Feature activation+0.007
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
John
Token John
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
who
Token who
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
stuck
Token stuck
Feature activation+0.020
Top resid features:
in
Token in
Feature activation+0.076
Top resid features:
third
Token third
Feature activation+0.664
Top resid features:
place
Token place
Feature activation+0.164
Top resid features:
in
Token in
Feature activation+0.178
Top resid features:
a
Token a
Feature activation+0.039
Top resid features:
three
Token three
Feature activation+0.059
Top resid features:
-
Token-
Feature activation+0.015
Top resid features:
John
Token John
Feature activation+0.087
Top resid features:
Hammond
Token Hammond
Feature activation+0.099
Top resid features:
,
Token,
Feature activation+0.248
Top resid features:
one
Token one
Feature activation+0.391
Top resid features:
of
Token of
Feature activation+0.264
Top resid features:
Indiana
Token Indiana
Feature activation+0.758
Top resid features:
âĢ
TokenâĢ
Feature activation-0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.025
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.026
Top resid features:
hired
Token hired
Feature activation+0.257
Top resid features:
a
Token a
Feature activation+0.200
Top resid features:
political
Token political
Feature activation+0.142
Top resid features:
veteran
Token veteran
Feature activation+0.107
Top resid features:
as
Token as
Feature activation+0.675
Top resid features:
chief
Token chief
Feature activation+0.629
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
warm
Token warm
Feature activation-0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
up
Tokenup
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.277
Top resid features:
the
Token the
Feature activation+0.195
Top resid features:
2012
Token 2012
Feature activation+0.564
Top resid features:
presidential
Token presidential
Feature activation+0.083
Top resid features:
race
Token race
Feature activation+0.327
Top resid features:
,
Token,
Feature activation+0.183
Top resid features:
analysts
Token analysts
Feature activation+0.104
Top resid features:
and
Token and
Feature activation+0.077
Top resid features:
a
Token a
Feature activation+0.046
Top resid features:
respectable
Token respectable
Feature activation+0.049
Top resid features:
amount
Token amount
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+0.312
Top resid features:
support
Token support
Feature activation+0.090
Top resid features:
from
Token from
Feature activation+0.532
Top resid features:
pockets
Token pockets
Feature activation+0.075
Top resid features:
of
Token of
Feature activation+0.321
Top resid features:
corporate
Token corporate
Feature activation+0.039
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sanders
Token Sanders
Feature activation+0.043
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
set
Token set
Feature activation+0.081
Top resid features:
to
Token to
Feature activation+0.096
Top resid features:
pick
Token pick
Feature activation+0.523
Top resid features:
up
Token up
Feature activation+2.322
Top resid features:
one
Token one
Feature activation+0.158
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
biggest
Token biggest
Feature activation+0.000
Top resid features:
endorsements
Token endorsements
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.029
Top resid features:
hired
Token hired
Feature activation+0.229
Top resid features:
a
Token a
Feature activation+0.336
Top resid features:
political
Token political
Feature activation+0.113
Top resid features:
veteran
Token veteran
Feature activation+0.063
Top resid features:
as
Token as
Feature activation+0.878
Top resid features:
chief
Token chief
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.035
Top resid features:
candidates
Token candidates
Feature activation+0.160
Top resid features:
will
Token will
Feature activation+0.021
Top resid features:
face
Token face
Feature activation+0.243
Top resid features:
off
Token off
Feature activation+0.546
Top resid features:
in
Token in
Feature activation+1.258
Top resid features:
Conservative
Token Conservative
Feature activation+0.707
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
Independence
Token Independence
Feature activation+0.406
Top resid features:
primaries
Token primaries
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.047
Top resid features:
polling
Token polling
Feature activation+0.292
Top resid features:
sites
Token sites
Feature activation+0.077
Top resid features:
available
Token available
Feature activation+0.083
Top resid features:
for
Token for
Feature activation+0.808
Top resid features:
the
Token the
Feature activation+1.405
Top resid features:
duration
Token duration
Feature activation+0.062
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
person
Tokenperson
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.291
Top resid features:
Super
Token Super
Feature activation-0.044
Top resid features:
PAC
Token PAC
Feature activation+0.177
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
during
Token during
Feature activation+1.070
Top resid features:
the
Token the
Feature activation+1.580
Top resid features:
âĢ
Token âĢ
Feature activation+0.066
Top resid features:
ĺ
Tokenĺ
Feature activation+0.091
Top resid features:
cand
Tokencand
Feature activation+0.000
Top resid features:
idate
Tokenidate
Feature activation+0.000
Top resid features:
windows
Token windows
Feature activation+0.000
Top resid features:
mate
Token mate
Feature activation+0.114
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Tim
Token Tim
Feature activation+0.075
Top resid features:
Wu
Token Wu
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
in
Token in
Feature activation+1.302
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.331
Top resid features:
âĢ
TokenâĢ
Feature activation-0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.037
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
primary
Token primary
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
transform
Token transform
Feature activation-0.002
Top resid features:
Democratic
Token Democratic
Feature activation-0.137
Top resid features:
Party
Token Party
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.095
Top resid features:
a
Token a
Feature activation+2.393
Top resid features:
live
Token live
Feature activation+0.543
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
stream
Tokenstream
Feature activation+0.046
Top resid features:
ed
Tokened
Feature activation+0.222
Top resid features:
video
Token video
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.12

Head 1: 0.06

Head 2: 0.04

Head 3: 0.34

Head 4: 0.05

Head 5: 0.03

Head 6: 0.03

Head 7: 0.04

Head 8: 0.15

Head 9: 0.03

Head 10: 0.04

Head 11: 0.06

Positive logits

Election6.19

voter5.96

polling5.88

Voter5.88

election5.73

election5.71

Democrats5.71

Republican5.68

Voters5.66

Republicans5.54

GOP5.52

Romney5.51

polls5.47

voters5.43

Elections5.42

caucus5.40

GOP5.36

Republican5.32

candidate5.32

caucuses5.31

Negative logits

isu-2.89

sterdam-2.82

licences-2.52

¥-2.50

nav-2.45

licence-2.44

REDACTED-2.39

atche-2.38

TOR-2.38

patents-2.37

Templ-2.35

utical-2.33

Cout-2.33

liner-2.32

Wass-2.31

Ubisoft-2.31

Konami-2.30

sson-2.27

infring-2.25

å-2.25

INTERVAL 2.874 - 3.194
CONTAINS 0.001%

ittal
Tokenittal
Feature activation+0.000
on
Token on
Feature activation+0.837
what
Token what
Feature activation+0.832
,
Token,
Feature activation+0.000
if
Token if
Feature activation+2.146
anything
Token anything
Feature activation+3.092
,
Token,
Feature activation+0.469
the
Token the
Feature activation+0.639
president
Token president
Feature activation+0.913
will
Token will
Feature activation+1.045
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
major
Token major
Feature activation+1.591
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+2.360
.
Token.
Feature activation+2.885
political
Token political
Feature activation+1.581
party
Token party
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
and
Token and
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
is
Token is
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
based
Token based
Feature activation+3.126
on
Token on
Feature activation+0.000
overall
Token overall
Feature activation+0.000
turnout
Token turnout
Feature activation+0.000
.
Token.
Feature activation+0.000
Sources
Token Sources
Feature activation+2.244
also
Token also
Feature activation+0.000
running
Token running
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Working
Token Working
Feature activation+0.234
Families
Token Families
Feature activation+3.194
line
Token line
Feature activation+0.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Dave
Token Dave
Feature activation+0.000
Le
Token Le
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.036
s
Tokens
Feature activation+3.011
Atlas
Token Atlas
Feature activation+0.530
of
Token of
Feature activation+0.795
U
Token U
Feature activation+0.577
.
Token.
Feature activation+2.202
S
TokenS
Feature activation+2.982

INTERVAL 2.555 - 2.874
CONTAINS 0.001%

of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+1.086
pockets
Token pockets
Feature activation+0.047
of
Token of
Feature activation+0.967
corporate
Token corporate
Feature activation+2.622
America
Token America
Feature activation+0.827
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
donations
Token donations
Feature activation+0.000
coming
Token coming
Feature activation+0.000
face
Token face
Feature activation+0.000
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.253
and
Token and
Feature activation+0.000
Independence
Token Independence
Feature activation+2.565
primaries
Token primaries
Feature activation+0.000
.
Token.
Feature activation+0.000
Th
Token Th
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
en
Tokenen
Feature activation+1.020
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.000
New
Token New
Feature activation+1.635
York
Token York
Feature activation+1.606
âĢ
TokenâĢ
Feature activation+0.098
Ļ
TokenĻ
Feature activation+2.752
s
Tokens
Feature activation+1.712
contest
Token contest
Feature activation+0.000
by
Token by
Feature activation+0.000
accusing
Token accusing
Feature activation+0.412
Michael
Token Michael
Feature activation+0.000
,
Token,
Feature activation+2.194
one
Token one
Feature activation+2.043
of
Token of
Feature activation+2.202
Indiana
Token Indiana
Feature activation+2.169
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.714
s
Tokens
Feature activation+1.513
two
Token two
Feature activation+1.696
members
Token members
Feature activation+0.843
of
Token of
Feature activation+1.692
the
Token the
Feature activation+1.533
2012
Token 2012
Feature activation+0.889
presidential
Token presidential
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.744
analysts
Token analysts
Feature activation+0.000
and
Token and
Feature activation+2.683
experts
Token experts
Feature activation+0.162
say
Token say
Feature activation+0.477
.
Token.
Feature activation+1.332
Conservative
Token Conservative
Feature activation+0.502
groups
Token groups
Feature activation+0.000

INTERVAL 2.236 - 2.555
CONTAINS 0.003%

Wu
Token Wu
Feature activation+0.039
,
Token,
Feature activation+0.257
in
Token in
Feature activation+0.468
Tuesday
Token Tuesday
Feature activation+1.664
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.500
s
Tokens
Feature activation+1.989
primary
Token primary
Feature activation+0.929
,
Token,
Feature activation+0.491
party
Token party
Feature activation+0.120
insiders
Token insiders
Feature activation+0.438
have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.964
billions
Token billions
Feature activation+1.230
of
Token of
Feature activation+1.707
dollars
Token dollars
Feature activation+1.047
worth
Token worth
Feature activation+2.366
of
Token of
Feature activation+1.629
promises
Token promises
Feature activation+1.674
so
Token so
Feature activation+0.476
far
Token far
Feature activation+0.456
,
Token,
Feature activation+0.817
ranked
Token ranked
Feature activation+0.000
second
Token second
Feature activation+0.280
in
Token in
Feature activation+0.537
the
Token the
Feature activation+0.626
amount
Token amount
Feature activation+1.451
of
Token of
Feature activation+2.339
money
Token money
Feature activation+0.000
raised
Token raised
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.092
first
Token first
Feature activation+1.883
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.458
office
Token office
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
sharper
Token sharper
Feature activation+0.000
and
Token and
Feature activation+0.000
won
Token won
Feature activation+0.000
a
Token a
Feature activation+0.000
full
Token full
Feature activation+0.180
four
Token four
Feature activation+0.064
-
Token-
Feature activation+2.252
year
Tokenyear
Feature activation+0.350
term
Token term
Feature activation+0.193
as
Token as
Feature activation+0.000
president
Token president
Feature activation+0.606
in
Token in
Feature activation+0.000

INTERVAL 1.916 - 2.236
CONTAINS 0.007%

pret
Tokenpret
Feature activation+0.000
entious
Tokenentious
Feature activation+0.929
candidate
Token candidate
Feature activation+0.000
he
Token he
Feature activation+1.213
has
Token has
Feature activation+1.787
ever
Token ever
Feature activation+1.939
covered
Token covered
Feature activation+0.149
.
Token.
Feature activation+0.000
Carlson
Token Carlson
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
presidential
Token presidential
Feature activation+0.154
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
Kat
Token Kat
Feature activation+0.000
bi
Tokenbi
Feature activation+1.957
voted
Token voted
Feature activation+0.000
for
Token for
Feature activation+0.000
Jill
Token Jill
Feature activation+0.000
Stein
Token Stein
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+1.745
the
Token the
Feature activation+1.436
opening
Token opening
Feature activation+0.941
of
Token of
Feature activation+0.215
his
Token his
Feature activation+0.171
new
Token new
Feature activation+2.224
hotel
Token hotel
Feature activation+1.333
in
Token in
Feature activation+0.000
Washington
Token Washington
Feature activation+0.889
,
Token,
Feature activation+0.000
D
Token D
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.240
first
Token first
Feature activation+1.248
front
Token front
Feature activation+0.413
in
Token in
Feature activation+0.618
what
Token what
Feature activation+2.046
Bannon
Token Bannon
Feature activation+0.185
has
Token has
Feature activation+0.154
described
Token described
Feature activation+0.640
as
Token as
Feature activation+2.021
a
Token a
Feature activation+2.416
comm
Tokencomm
Feature activation+0.000
ittal
Tokenittal
Feature activation+0.000
on
Token on
Feature activation+0.837
what
Token what
Feature activation+0.832
,
Token,
Feature activation+0.000
if
Token if
Feature activation+2.146
anything
Token anything
Feature activation+3.092
,
Token,
Feature activation+0.469
the
Token the
Feature activation+0.639
president
Token president
Feature activation+0.913
will
Token will
Feature activation+1.045

INTERVAL 1.597 - 1.916
CONTAINS 0.012%

record
Token record
Feature activation+0.554
-
Token-
Feature activation+0.081
sh
Tokensh
Feature activation+0.000
attering
Tokenattering
Feature activation+0.000
amounts
Token amounts
Feature activation+1.082
outside
Token outside
Feature activation+1.767
groups
Token groups
Feature activation+0.012
spent
Token spent
Feature activation+0.000
to
Token to
Feature activation+0.000
oust
Token oust
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
President
Token President
Feature activation+0.000
,
Token,
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
,
Token,
Feature activation+1.713
and
Token and
Feature activation+1.811
the
Token the
Feature activation+1.614
2016
Token 2016
Feature activation+0.000
race
Token race
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
living
Token living
Feature activation+0.000
overseas
Token overseas
Feature activation+0.596
called
Token called
Feature activation+0.207
Democrats
Token Democrats
Feature activation+0.428
Ab
Token Ab
Feature activation+0.172
road
Tokenroad
Feature activation+1.793
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Overall
TokenOverall
Feature activation+0.830
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.165
have
Token have
Feature activation+0.276
taken
Token taken
Feature activation+1.631
any
Token any
Feature activation+1.746
other
Token other
Feature activation+1.855
concrete
Token concrete
Feature activation+1.802
steps
Token steps
Feature activation+0.058
that
Token that
Feature activation+0.609
might
Token might
Feature activation+0.000
indicate
Token indicate
Feature activation+0.000
a
Token a
Feature activation+0.000
prep
Token prep
Feature activation+1.314
surrog
Token surrog
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
during
Token during
Feature activation+1.122
the
Token the
Feature activation+1.051
day
Token day
Feature activation+1.644
.
Token.
Feature activation+0.567
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.714
Two
TokenTwo
Feature activation+1.001
former
Token former
Feature activation+0.651

INTERVAL 1.277 - 1.597
CONTAINS 0.022%

when
Token when
Feature activation+0.743
many
Token many
Feature activation+0.691
of
Token of
Feature activation+1.617
the
Token the
Feature activation+0.280
district
Token district
Feature activation+1.413
's
Token's
Feature activation+1.313
residence
Token residence
Feature activation+1.673
head
Token head
Feature activation+2.288
north
Token north
Feature activation+0.578
for
Token for
Feature activation+1.418
vacation
Token vacation
Feature activation+1.218
Stein
Token Stein
Feature activation+0.000
has
Token has
Feature activation+0.000
3
Token 3
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.462
Ċ
TokenĊ
Feature activation+0.408
Ess
TokenEss
Feature activation+0.076
entially
Tokenentially
Feature activation+0.978
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.001
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.051
the
Token the
Feature activation+0.367
polls
Token polls
Feature activation+0.000
the
Token the
Feature activation+0.941
following
Token following
Feature activation+1.509
day
Token day
Feature activation+0.191
and
Token and
Feature activation+0.000
grant
Token grant
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
percent
Token percent
Feature activation+0.000
on
Token on
Feature activation+0.671
an
Token an
Feature activation+1.830
average
Token average
Feature activation+1.968
of
Token of
Feature activation+1.124
five
Token five
Feature activation+1.453
national
Token national
Feature activation+1.174
polls
Token polls
Feature activation+0.000
the
Token the
Feature activation+0.905
debate
Token debate
Feature activation+0.000
commission
Token commission
Feature activation+1.037
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.408
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.712
said
Token said
Feature activation+1.329
John
Token John
Feature activation+0.044
Hammond
Token Hammond
Feature activation+1.235
,
Token,
Feature activation+2.194
one
Token one
Feature activation+2.043
of
Token of
Feature activation+2.202

INTERVAL 0.958 - 1.277
CONTAINS 0.047%

to
Token to
Feature activation+0.000
prep
Token prep
Feature activation+1.314
surrog
Token surrog
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
during
Token during
Feature activation+1.122
the
Token the
Feature activation+1.051
day
Token day
Feature activation+1.644
.
Token.
Feature activation+0.567
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.714
Two
TokenTwo
Feature activation+1.001
a
Token a
Feature activation+0.833
29
Token 29
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+1.621
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+1.089
pastor
Token pastor
Feature activation+0.161
-
Token-
Feature activation+0.912
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.874
be
Tokenbe
Feature activation+0.608
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.355
spent
Token spent
Feature activation+0.563
by
Token by
Feature activation+0.435
the
Token the
Feature activation+0.729
same
Token same
Feature activation+1.002
groups
Token groups
Feature activation+0.000
working
Token working
Feature activation+0.000
against
Token against
Feature activation+0.000
SB
Token SB
Feature activation+0.000
5
Token 5
Feature activation+0.000
does
Token does
Feature activation+0.689
do
Token do
Feature activation+1.194
a
Token a
Feature activation+0.262
form
Token form
Feature activation+0.330
of
Token of
Feature activation+1.406
hypothetical
Token hypothetical
Feature activation+1.179
questions
Token questions
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.047
just
Token just
Feature activation+0.316
this
Token this
Feature activation+0.850
week
Token week
Feature activation+0.000
all
Token all
Feature activation+1.283
three
Token three
Feature activation+0.440
parties
Token parties
Feature activation+0.000
combined
Token combined
Feature activation+0.093
have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.964
billions
Token billions
Feature activation+1.230
of
Token of
Feature activation+1.707
dollars
Token dollars
Feature activation+1.047
worth
Token worth
Feature activation+2.366
of
Token of
Feature activation+1.629

INTERVAL 0.639 - 0.958
CONTAINS 0.096%

in
Token in
Feature activation+0.807
an
Token an
Feature activation+1.334
interview
Token interview
Feature activation+0.000
a
Token a
Feature activation+1.937
couple
Token couple
Feature activation+1.487
of
Token of
Feature activation+0.912
months
Token months
Feature activation+0.000
ago
Token ago
Feature activation+0.503
.
Token.
Feature activation+0.984
Mr
Token Mr
Feature activation+0.790
Hammond
Token Hammond
Feature activation+0.457
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.539
big
Tokenbig
Feature activation+1.307
organizing
Token organizing
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.754
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
revolutionary
Token revolutionary
Feature activation+0.000
mass
Token mass
Feature activation+0.182
movement
Token movement
Feature activation+0.000
is
Token is
Feature activation+0.051
neither
Token neither
Feature activation+0.639
wise
Token wise
Feature activation+0.863
nor
Token nor
Feature activation+0.366
careful
Token careful
Feature activation+0.148
,
Token,
Feature activation+0.695
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.989
reads
Token reads
Feature activation+0.077
an
Token an
Feature activation+0.735
editorial
Token editorial
Feature activation+0.000
,
Token,
Feature activation+0.500
was
Token was
Feature activation+0.631
introduced
Token introduced
Feature activation+0.194
to
Token to
Feature activation+0.149
the
Token the
Feature activation+0.804
students
Token students
Feature activation+0.875
in
Token in
Feature activation+0.993
the
Token the
Feature activation+1.223
program
Token program
Feature activation+0.455
as
Token as
Feature activation+0.953
a
Token a
Feature activation+1.388
day
Token day
Feature activation+1.644
.
Token.
Feature activation+0.567
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.714
Two
TokenTwo
Feature activation+1.001
former
Token former
Feature activation+0.651
Trump
Token Trump
Feature activation+1.263
White
Token White
Feature activation+0.000
House
Token House
Feature activation+1.143
officials
Token officials
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.291

INTERVAL 0.319 - 0.639
CONTAINS 0.196%

ton
Token ton
Feature activation+0.512
of
Token of
Feature activation+0.652
good
Token good
Feature activation+0.834
news
Token news
Feature activation+0.000
for
Token for
Feature activation+0.000
Romney
Token Romney
Feature activation+0.563
in
Token in
Feature activation+0.046
this
Token this
Feature activation+0.139
poll
Token poll
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
after
Token after
Feature activation+0.000
Super
Token Super
Feature activation+1.399
Tuesday
Token Tuesday
Feature activation+0.078
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
respected
Token respected
Feature activation+0.413
polling
Token polling
Feature activation+0.017
analysts
Token analysts
Feature activation+0.159
at
Token at
Feature activation+1.354
Five
Token Five
Feature activation+0.322
Thirty
TokenThirty
Feature activation+0.000
memoir
Token memoir
Feature activation+0.000
:
Token:
Feature activation+0.000
report
Token report
Feature activation+0.000
Former
Token Former
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.383
on
Token on
Feature activation+0.345
death
Token death
Feature activation+0.000
of
Token of
Feature activation+0.000
7
Token 7
Feature activation+0.111
-
Token-
Feature activation+0.000
Mex
Token Mex
Feature activation+0.091
ÂŃ
TokenÂŃ
Feature activation+0.000
ico
Tokenico
Feature activation+0.204
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.514
s
Tokens
Feature activation+0.473
Mar
Token Mar
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
tin
Tokentin
Feature activation+0.039
Hein
Token Hein
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
help
Token help
Feature activation+0.000
of
Token of
Feature activation+0.071
some
Token some
Feature activation+0.349
of
Token of
Feature activation+0.945
Washington
Token Washington
Feature activation+0.757
's
Token's
Feature activation+0.630
most
Token most
Feature activation+0.535
successful
Token successful
Feature activation+0.773
-
Token -
Feature activation+0.609
and
Token and
Feature activation+0.301
infamous
Token infamous
Feature activation+1.159

INTERVAL 0.000 - 0.319
CONTAINS 99.616%

it
Token it
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
in
Token in
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
verbal
Token verbal
Feature activation+0.000
brawl
Token brawl
Feature activation+0.000
with
Token with
Feature activation+0.000
facts
Token facts
Feature activation+0.000
and
Token and
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
and
Token and
Feature activation+0.000
game
Token game
Feature activation+0.000
the
Token the
Feature activation+0.000
cosmos
Token cosmos
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
earliest
Token earliest
Feature activation+0.000
moments
Token moments
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
observ
Token observ
Feature activation+0.000
atories
Tokenatories
Feature activation+0.000
(
Token (
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Environmental
Token Environmental
Feature activation+0.000
Protection
Token Protection
Feature activation+0.000
since
Token since
Feature activation+0.000
fish
Token fish
Feature activation+0.000
first
Token first
Feature activation+0.000
slit
Token slit
Feature activation+0.000
hered
Tokenhered
Feature activation+0.000
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+0.000
f
Token f
Feature activation+0.000
***
Token***
Feature activation+0.000
ing
Tokening
Feature activation+0.000
land
Token land
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 H11.3: (feature 3396)

TOP ACTIVATIONS
MAX = 4.859

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.107
ors
Tokenors
Feature activation+2.291
a
Tokena
Feature activation+2.040
Istanbul
Token Istanbul
Feature activation+4.859
National
Token National
Feature activation+3.694
100
Token 100
Feature activation+0.937
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
on
Token on
Feature activation+0.315
banks
Token banks
Feature activation+0.000
suspected
Token suspected
Feature activation+0.270
of
Token of
Feature activation+0.672
rigging
Token rigging
Feature activation+2.780
global
Token global
Feature activation+4.858
interest
Token interest
Feature activation+1.576
rate
Token rate
Feature activation+1.358
benchmarks
Token benchmarks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.203
After
TokenAfter
Feature activation+0.223
,
Token,
Feature activation+2.207
publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
of
Token of
Feature activation+0.573
the
Token the
Feature activation+0.245
bombing
Token bombing
Feature activation+1.558
,
Token,
Feature activation+2.021
which
Token which
Feature activation+2.566
a
Token a
Feature activation+4.490
Syrian
Token Syrian
Feature activation+3.026
military
Token military
Feature activation+1.569
source
Token source
Feature activation+0.848
denied
Token denied
Feature activation+1.339
.
Token.
Feature activation+0.000
of
Token of
Feature activation+1.385
the
Token the
Feature activation+1.687
modern
Token modern
Feature activation+3.096
pound
Token pound
Feature activation+0.373
,
Token,
Feature activation+0.000
shocking
Token shocking
Feature activation+4.370
financial
Token financial
Feature activation+1.311
markets
Token markets
Feature activation+0.000
,
Token,
Feature activation+1.030
as
Token as
Feature activation+2.284
poll
Token poll
Feature activation+0.019
publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.815
the
Token the
Feature activation+0.252
over
Token over
Feature activation+2.448
-
Token-
Feature activation+4.134
the
Tokenthe
Feature activation+0.608
-
Token-
Feature activation+4.123
counter
Tokencounter
Feature activation+2.936
market
Token market
Feature activation+2.279
,
Token,
Feature activation+0.438
on
Token on
Feature activation+0.815
the
Token the
Feature activation+0.252
over
Token over
Feature activation+2.448
-
Token-
Feature activation+4.134
the
Tokenthe
Feature activation+0.608
-
Token-
Feature activation+4.123
counter
Tokencounter
Feature activation+2.936
market
Token market
Feature activation+2.279
,
Token,
Feature activation+0.438
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.678
markets
Token markets
Feature activation+0.000
,
Token,
Feature activation+1.030
as
Token as
Feature activation+2.284
poll
Token poll
Feature activation+0.019
sters
Tokensters
Feature activation+0.109
and
Token and
Feature activation+3.975
fore
Token fore
Feature activation+0.000
casters
Tokencasters
Feature activation+0.000
had
Token had
Feature activation+0.000
almost
Token almost
Feature activation+0.000
uniformly
Token uniformly
Feature activation+0.425
Stephen
Token Stephen
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
ork
Tokenork
Feature activation+0.668
,
Token,
Feature activation+2.207
publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
.
Token.
Feature activation+1.161
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+2.706
of
Token of
Feature activation+1.480
Third
Token Third
Feature activation+1.165
Point
Token Point
Feature activation+3.735
Management
Token Management
Feature activation+1.445
called
Token called
Feature activation+2.138
a
Token a
Feature activation+1.545
âĢ
Token âĢ
Feature activation+0.002
ľ
Tokenľ
Feature activation+0.827
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.107
ors
Tokenors
Feature activation+2.291
a
Tokena
Feature activation+2.040
Istanbul
Token Istanbul
Feature activation+4.859
National
Token National
Feature activation+3.694
100
Token 100
Feature activation+0.937
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
6
Token 6
Feature activation+0.000
,
Token,
Feature activation+0.660
some
Token some
Feature activation+1.812
members
Token members
Feature activation+0.000
of
Token of
Feature activation+1.049
a
Token a
Feature activation+2.693
House
Token House
Feature activation+3.651
subcommittee
Token subcommittee
Feature activation+0.063
questioned
Token questioned
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.734
of
Token of
Feature activation+0.000
key
Token key
Feature activation+0.000
index
Token index
Feature activation+0.000
for
Token for
Feature activation+0.000
stocks
Token stocks
Feature activation+0.000
on
Token on
Feature activation+0.000
Turkey
Token Turkey
Feature activation+3.479
's
Token's
Feature activation+0.270
main
Token main
Feature activation+1.629
exchange
Token exchange
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hype
Token hype
Feature activation+0.000
and
Token and
Feature activation+1.900
myths
Token myths
Feature activation+0.000
about
Token about
Feature activation+0.258
âĢ
Token âĢ
Feature activation+0.635
ľ
Tokenľ
Feature activation+3.474
economic
Tokeneconomic
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
ork
Tokenork
Feature activation+0.668
,
Token,
Feature activation+2.207
publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
May
Token May
Feature activation+0.000
1
Token 1
Feature activation+0.154
,
Token,
Feature activation+0.000
ten
Token ten
Feature activation+0.699
major
Token major
Feature activation+1.271
Japanese
Token Japanese
Feature activation+3.366
companies
Token companies
Feature activation+0.087
are
Token are
Feature activation+0.000
planning
Token planning
Feature activation+0.919
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000
for
Token for
Feature activation+1.378
more
Token more
Feature activation+1.356
cur
Token cur
Feature activation+0.000
bs
Tokenbs
Feature activation+0.335
on
Token on
Feature activation+1.700
big
Token big
Feature activation+3.346
banks
Token banks
Feature activation+0.000
,
Token,
Feature activation+0.486
possibly
Token possibly
Feature activation+0.000
including
Token including
Feature activation+0.000
trim
Token trim
Feature activation+1.102
the
Token the
Feature activation+0.928
Syrian
Token Syrian
Feature activation+0.675
Observatory
Token Observatory
Feature activation+0.408
for
Token for
Feature activation+0.416
Human
Token Human
Feature activation+0.000
Rights
Token Rights
Feature activation+3.259
report
Token report
Feature activation+0.417
of
Token of
Feature activation+0.573
the
Token the
Feature activation+0.245
bombing
Token bombing
Feature activation+1.558
,
Token,
Feature activation+2.021

Top DFA by src position
MAX = 4.529

stocks
Token stocks
Feature activation+0.403
Top resid features:
on
Token on
Feature activation+0.487
Top resid features:
Turkey
Token Turkey
Feature activation+0.105
Top resid features:
's
Token's
Feature activation+0.490
Top resid features:
main
Token main
Feature activation+0.167
Top resid features:
exchange
Token exchange
Feature activation+1.494
Top resid features:
,
Token,
Feature activation+0.468
Top resid features:
the
Token the
Feature activation+0.707
Top resid features:
B
Token B
Feature activation+0.185
Top resid features:
ors
Tokenors
Feature activation+0.022
Top resid features:
a
Tokena
Feature activation+0.605
Top resid features:
down
Token down
Feature activation+0.028
Top resid features:
on
Token on
Feature activation+0.083
Top resid features:
banks
Token banks
Feature activation+0.493
Top resid features:
suspected
Token suspected
Feature activation+0.092
Top resid features:
of
Token of
Feature activation+0.121
Top resid features:
rigging
Token rigging
Feature activation+3.600
Top resid features:
global
Token global
Feature activation+0.802
Top resid features:
interest
Token interest
Feature activation+0.000
Top resid features:
rate
Token rate
Feature activation+0.000
Top resid features:
benchmarks
Token benchmarks
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
publisher
Token publisher
Feature activation+0.196
Top resid features:
of
Token of
Feature activation+0.503
Top resid features:
the
Token the
Feature activation+0.887
Top resid features:
industry
Token industry
Feature activation+0.126
Top resid features:
newsletter
Token newsletter
Feature activation+0.431
Top resid features:
The
Token The
Feature activation+1.069
Top resid features:
Sch
Token Sch
Feature activation+0.007
Top resid features:
ork
Tokenork
Feature activation+0.041
Top resid features:
Report
Token Report
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
spiked
Token spiked
Feature activation+0.011
Top resid features:
back
Token back
Feature activation+0.001
Top resid features:
up
Token up
Feature activation+0.001
Top resid features:
again
Token again
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.116
Top resid features:
the
Token the
Feature activation+0.646
Top resid features:
"
Token "
Feature activation+0.064
Top resid features:
market
Tokenmarket
Feature activation+0.308
Top resid features:
realized
Token realized
Feature activation+0.026
Top resid features:
that
Token that
Feature activation+0.313
Top resid features:
the
Token the
Feature activation+0.416
Top resid features:
trading
Token trading
Feature activation+0.650
Top resid features:
but
Token but
Feature activation+0.398
Top resid features:
still
Token still
Feature activation+0.106
Top resid features:
above
Token above
Feature activation+0.150
Top resid features:
session
Token session
Feature activation+0.143
Top resid features:
lows
Token lows
Feature activation+0.722
Top resid features:
after
Token after
Feature activation+0.619
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Syrian
Token Syrian
Feature activation+0.087
Top resid features:
Observatory
Token Observatory
Feature activation+0.087
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
history
Token history
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
modern
Token modern
Feature activation+0.061
Top resid features:
pound
Token pound
Feature activation+4.529
Top resid features:
,
Token,
Feature activation+0.146
Top resid features:
shocking
Token shocking
Feature activation+0.055
Top resid features:
financial
Token financial
Feature activation+0.000
Top resid features:
markets
Token markets
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation-0.008
Top resid features:
Sch
Token Sch
Feature activation-0.021
Top resid features:
ork
Tokenork
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.342
Top resid features:
publisher
Token publisher
Feature activation+0.163
Top resid features:
of
Token of
Feature activation+0.926
Top resid features:
the
Token the
Feature activation+0.397
Top resid features:
industry
Token industry
Feature activation+0.153
Top resid features:
newsletter
Token newsletter
Feature activation+0.449
Top resid features:
The
Token The
Feature activation+0.274
Top resid features:
Sch
Token Sch
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
S
TokenS
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
on
Token on
Feature activation+0.931
Top resid features:
the
Token the
Feature activation+0.280
Top resid features:
over
Token over
Feature activation+1.655
Top resid features:
-
Token-
Feature activation+0.246
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
counter
Tokencounter
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
S
TokenS
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.202
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
over
Token over
Feature activation+2.535
Top resid features:
-
Token-
Feature activation+0.435
Top resid features:
the
Tokenthe
Feature activation+0.591
Top resid features:
-
Token-
Feature activation+0.426
Top resid features:
counter
Tokencounter
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.084
Top resid features:
history
Token history
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.151
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
modern
Token modern
Feature activation+0.197
Top resid features:
pound
Token pound
Feature activation+1.887
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
shocking
Token shocking
Feature activation+0.526
Top resid features:
financial
Token financial
Feature activation+0.495
Top resid features:
markets
Token markets
Feature activation+0.119
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
spiked
Token spiked
Feature activation+0.028
Top resid features:
back
Token back
Feature activation+0.003
Top resid features:
up
Token up
Feature activation+0.005
Top resid features:
again
Token again
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+0.160
Top resid features:
the
Token the
Feature activation+0.577
Top resid features:
"
Token "
Feature activation+0.066
Top resid features:
market
Tokenmarket
Feature activation+0.178
Top resid features:
realized
Token realized
Feature activation+0.056
Top resid features:
that
Token that
Feature activation+0.237
Top resid features:
the
Token the
Feature activation+0.355
Top resid features:
fund
Token fund
Feature activation+0.299
Top resid features:
hotel
Token hotel
Feature activation+0.097
Top resid features:
stocks
Token stocks
Feature activation+0.347
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
leading
Token leading
Feature activation+0.448
Top resid features:
what
Token what
Feature activation+1.149
Top resid features:
Daniel
Token Daniel
Feature activation+0.060
Top resid features:
S
Token S
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Lo
Token Lo
Feature activation+0.007
Top resid features:
eb
Tokeneb
Feature activation+0.127
Top resid features:
stocks
Token stocks
Feature activation+0.391
Top resid features:
on
Token on
Feature activation+0.310
Top resid features:
Turkey
Token Turkey
Feature activation+0.116
Top resid features:
's
Token's
Feature activation+0.285
Top resid features:
main
Token main
Feature activation+0.061
Top resid features:
exchange
Token exchange
Feature activation+0.861
Top resid features:
,
Token,
Feature activation+0.507
Top resid features:
the
Token the
Feature activation+0.479
Top resid features:
B
Token B
Feature activation+0.117
Top resid features:
ors
Tokenors
Feature activation+0.038
Top resid features:
a
Tokena
Feature activation+0.277
Top resid features:
urch
Tokenurch
Feature activation+0.000
Top resid features:
ased
Tokenased
Feature activation+0.059
Top resid features:
its
Token its
Feature activation+0.263
Top resid features:
warrants
Token warrants
Feature activation+0.263
Top resid features:
from
Token from
Feature activation+0.437
Top resid features:
the
Token the
Feature activation+0.984
Top resid features:
government
Token government
Feature activation+0.170
Top resid features:
for
Token for
Feature activation+0.071
Top resid features:
$
Token $
Feature activation-0.004
Top resid features:
1
Token1
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
The
Token The
Feature activation+0.032
Top resid features:
key
Token key
Feature activation+0.078
Top resid features:
index
Token index
Feature activation+0.659
Top resid features:
for
Token for
Feature activation+0.101
Top resid features:
stocks
Token stocks
Feature activation+0.525
Top resid features:
on
Token on
Feature activation+2.197
Top resid features:
Turkey
Token Turkey
Feature activation+0.108
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
main
Token main
Feature activation+0.000
Top resid features:
exchange
Token exchange
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fed
Token fed
Feature activation+0.023
Top resid features:
by
Token by
Feature activation+0.273
Top resid features:
hype
Token hype
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+0.068
Top resid features:
myths
Token myths
Feature activation+0.007
Top resid features:
about
Token about
Feature activation+3.037
Top resid features:
âĢ
Token âĢ
Feature activation+0.286
Top resid features:
ľ
Tokenľ
Feature activation-0.029
Top resid features:
economic
Tokeneconomic
Feature activation+0.000
Top resid features:
recovery
Token recovery
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation+0.004
Top resid features:
Sch
Token Sch
Feature activation-0.023
Top resid features:
ork
Tokenork
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.280
Top resid features:
publisher
Token publisher
Feature activation+0.143
Top resid features:
of
Token of
Feature activation+0.575
Top resid features:
the
Token the
Feature activation+0.240
Top resid features:
industry
Token industry
Feature activation+0.000
Top resid features:
newsletter
Token newsletter
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Sch
Token Sch
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
May
Token May
Feature activation-0.003
Top resid features:
1
Token 1
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
ten
Token ten
Feature activation+0.700
Top resid features:
major
Token major
Feature activation+1.427
Top resid features:
Japanese
Token Japanese
Feature activation+0.636
Top resid features:
companies
Token companies
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
planning
Token planning
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.104
Top resid features:
for
Token for
Feature activation+0.290
Top resid features:
more
Token more
Feature activation+0.146
Top resid features:
cur
Token cur
Feature activation+0.111
Top resid features:
bs
Tokenbs
Feature activation+0.147
Top resid features:
on
Token on
Feature activation+1.913
Top resid features:
big
Token big
Feature activation+0.119
Top resid features:
banks
Token banks
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
possibly
Token possibly
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
trading
Token trading
Feature activation+0.576
Top resid features:
but
Token but
Feature activation+0.070
Top resid features:
still
Token still
Feature activation+0.109
Top resid features:
above
Token above
Feature activation+0.124
Top resid features:
session
Token session
Feature activation+0.222
Top resid features:
lows
Token lows
Feature activation+1.129
Top resid features:
after
Token after
Feature activation+0.379
Top resid features:
the
Token the
Feature activation+0.099
Top resid features:
Syrian
Token Syrian
Feature activation+0.063
Top resid features:
Observatory
Token Observatory
Feature activation+0.037
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.05

Head 2: 0.05

Head 3: 0.34

Head 4: 0.06

Head 5: 0.04

Head 6: 0.03

Head 7: 0.05

Head 8: 0.15

Head 9: 0.03

Head 10: 0.05

Head 11: 0.07

Positive logits

liquidity6.81

securities6.17

lender6.07

Securities5.86

Bank5.84

lenders5.76

Investors5.69

investors5.68

Banking5.63

bank5.58

ETF5.57

banking5.55

stocks5.54

stocks5.53

brokerage5.53

traders5.51

banks5.50

trading5.50

trader5.49

bankers5.47

Negative logits

YPG-2.62

-2.47

volunteers-2.47

Ribbon-2.46

ć-2.46

atoon-2.44

Ake-2.42

ACLU-2.39

Bliss-2.36

Burke-2.35

Rape-2.35

Volunteer-2.35

misogyn-2.31

────-2.31

Volunteers-2.30

Kand-2.28

dehuman-2.28

liter-2.27

Femin-2.27

camer-2.27

INTERVAL 4.373 - 4.859
CONTAINS 0.001%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.107
ors
Tokenors
Feature activation+2.291
a
Tokena
Feature activation+2.040
Istanbul
Token Istanbul
Feature activation+4.859
National
Token National
Feature activation+3.694
100
Token 100
Feature activation+0.937
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
,
Token,
Feature activation+2.207
publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.203
After
TokenAfter
Feature activation+0.223
of
Token of
Feature activation+0.573
the
Token the
Feature activation+0.245
bombing
Token bombing
Feature activation+1.558
,
Token,
Feature activation+2.021
which
Token which
Feature activation+2.566
a
Token a
Feature activation+4.490
Syrian
Token Syrian
Feature activation+3.026
military
Token military
Feature activation+1.569
source
Token source
Feature activation+0.848
denied
Token denied
Feature activation+1.339
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.315
banks
Token banks
Feature activation+0.000
suspected
Token suspected
Feature activation+0.270
of
Token of
Feature activation+0.672
rigging
Token rigging
Feature activation+2.780
global
Token global
Feature activation+4.858
interest
Token interest
Feature activation+1.576
rate
Token rate
Feature activation+1.358
benchmarks
Token benchmarks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.887 - 4.373
CONTAINS 0.001%

publisher
Token publisher
Feature activation+1.742
of
Token of
Feature activation+3.782
the
Token the
Feature activation+3.373
industry
Token industry
Feature activation+1.908
newsletter
Token newsletter
Feature activation+4.532
The
Token The
Feature activation+4.190
Sch
Token Sch
Feature activation+1.472
ork
Tokenork
Feature activation+4.630
Report
Token Report
Feature activation+1.930
.
Token.
Feature activation+0.642
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+1.385
the
Token the
Feature activation+1.687
modern
Token modern
Feature activation+3.096
pound
Token pound
Feature activation+0.373
,
Token,
Feature activation+0.000
shocking
Token shocking
Feature activation+4.370
financial
Token financial
Feature activation+1.311
markets
Token markets
Feature activation+0.000
,
Token,
Feature activation+1.030
as
Token as
Feature activation+2.284
poll
Token poll
Feature activation+0.019
markets
Token markets
Feature activation+0.000
,
Token,
Feature activation+1.030
as
Token as
Feature activation+2.284
poll
Token poll
Feature activation+0.019
sters
Tokensters
Feature activation+0.109
and
Token and
Feature activation+3.975
fore
Token fore
Feature activation+0.000
casters
Tokencasters
Feature activation+0.000
had
Token had
Feature activation+0.000
almost
Token almost
Feature activation+0.000
uniformly
Token uniformly
Feature activation+0.425
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.815
the
Token the
Feature activation+0.252
over
Token over
Feature activation+2.448
-
Token-
Feature activation+4.134
the
Tokenthe
Feature activation+0.608
-
Token-
Feature activation+4.123
counter
Tokencounter
Feature activation+2.936
market
Token market
Feature activation+2.279
,
Token,
Feature activation+0.438
on
Token on
Feature activation+0.815
the
Token the
Feature activation+0.252
over
Token over
Feature activation+2.448
-
Token-
Feature activation+4.134
the
Tokenthe
Feature activation+0.608
-
Token-
Feature activation+4.123
counter
Tokencounter
Feature activation+2.936
market
Token market
Feature activation+2.279
,
Token,
Feature activation+0.438
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.678

INTERVAL 3.401 - 3.887
CONTAINS 0.001%

.
Token.
Feature activation+1.161
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+2.706
of
Token of
Feature activation+1.480
Third
Token Third
Feature activation+1.165
Point
Token Point
Feature activation+3.735
Management
Token Management
Feature activation+1.445
called
Token called
Feature activation+2.138
a
Token a
Feature activation+1.545
âĢ
Token âĢ
Feature activation+0.002
ľ
Tokenľ
Feature activation+0.827
key
Token key
Feature activation+0.000
index
Token index
Feature activation+0.000
for
Token for
Feature activation+0.000
stocks
Token stocks
Feature activation+0.000
on
Token on
Feature activation+0.000
Turkey
Token Turkey
Feature activation+3.479
's
Token's
Feature activation+0.270
main
Token main
Feature activation+1.629
exchange
Token exchange
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hype
Token hype
Feature activation+0.000
and
Token and
Feature activation+1.900
myths
Token myths
Feature activation+0.000
about
Token about
Feature activation+0.258
âĢ
Token âĢ
Feature activation+0.635
ľ
Tokenľ
Feature activation+3.474
economic
Tokeneconomic
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.107
ors
Tokenors
Feature activation+2.291
a
Tokena
Feature activation+2.040
Istanbul
Token Istanbul
Feature activation+4.859
National
Token National
Feature activation+3.694
100
Token 100
Feature activation+0.937
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
6
Token 6
Feature activation+0.000
,
Token,
Feature activation+0.660
some
Token some
Feature activation+1.812
members
Token members
Feature activation+0.000
of
Token of
Feature activation+1.049
a
Token a
Feature activation+2.693
House
Token House
Feature activation+3.651
subcommittee
Token subcommittee
Feature activation+0.063
questioned
Token questioned
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.734
of
Token of
Feature activation+0.000

INTERVAL 2.915 - 3.401
CONTAINS 0.002%

low
Token low
Feature activation+1.125
volume
Token volume
Feature activation+0.359
,
Token,
Feature activation+0.077
short
Token short
Feature activation+0.901
-
Token-
Feature activation+2.307
cover
Tokencover
Feature activation+3.083
ing
Tokening
Feature activation+2.977
and
Token and
Feature activation+1.894
a
Token a
Feature activation+1.341
much
Token much
Feature activation+1.602
weaker
Token weaker
Feature activation+1.235
gest
Tokengest
Feature activation+2.668
economy
Token economy
Feature activation+0.559
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.540
A
TokenA
Feature activation+3.138
man
Token man
Feature activation+2.802
looks
Token looks
Feature activation+1.646
at
Token at
Feature activation+2.612
at
Token at
Feature activation+2.607
an
Token an
Feature activation+2.526
expect
Token expect
Feature activation+1.245
as
Token as
Feature activation+1.014
consumer
Token consumer
Feature activation+1.361
confidence
Token confidence
Feature activation+0.000
and
Token and
Feature activation+1.545
real
Token real
Feature activation+2.924
estate
Token estate
Feature activation+0.145
prices
Token prices
Feature activation+0.000
drop
Token drop
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.015
pay
Token pay
Feature activation+0.000
less
Token less
Feature activation+0.000
for
Token for
Feature activation+2.179
risky
Token risky
Feature activation+3.103
assets
Token assets
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.928
Syrian
Token Syrian
Feature activation+0.675
Observatory
Token Observatory
Feature activation+0.408
for
Token for
Feature activation+0.416
Human
Token Human
Feature activation+0.000
Rights
Token Rights
Feature activation+3.259
report
Token report
Feature activation+0.417
of
Token of
Feature activation+0.573
the
Token the
Feature activation+0.245
bombing
Token bombing
Feature activation+1.558
,
Token,
Feature activation+2.021

INTERVAL 2.429 - 2.915
CONTAINS 0.005%

step
Token step
Feature activation+0.176
towards
Token towards
Feature activation+0.825
legitim
Token legitim
Feature activation+0.069
izing
Tokenizing
Feature activation+2.369
bitcoin
Token bitcoin
Feature activation+2.232
as
Token as
Feature activation+2.770
an
Token an
Feature activation+2.932
asset
Token asset
Feature activation+0.441
class
Token class
Feature activation+1.668
for
Token for
Feature activation+2.684
institutional
Token institutional
Feature activation+1.602
Ŀ
TokenĿ
Feature activation+0.194
said
Token said
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Murray
Token Murray
Feature activation+0.116
of
Token of
Feature activation+1.152
Real
Token Real
Feature activation+2.553
Trends
Token Trends
Feature activation+1.371
,
Token,
Feature activation+0.183
a
Token a
Feature activation+1.299
Denver
Token Denver
Feature activation+2.804
research
Token research
Feature activation+0.506
trading
Token trading
Feature activation+0.000
game
Token game
Feature activation+2.025
platform
Token platform
Feature activation+2.422
Stock
Token Stock
Feature activation+0.218
f
Tokenf
Feature activation+0.749
use
Tokenuse
Feature activation+2.446
is
Token is
Feature activation+0.452
in
Token in
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
talks
Token talks
Feature activation+0.000
to
Token to
Feature activation+0.064
illegal
Token illegal
Feature activation+2.084
fees
Token fees
Feature activation+0.237
and
Token and
Feature activation+0.000
carry
Token carry
Feature activation+0.000
o
Token o
Feature activation+0.541
u
Tokenu
Feature activation+2.498
et
Token et
Feature activation+1.343
improper
Token improper
Feature activation+0.831
fore
Token fore
Feature activation+0.000
cl
Tokencl
Feature activation+0.000
osures
Tokenosures
Feature activation+0.000
Reserve
Token Reserve
Feature activation+0.447
warning
Token warning
Feature activation+2.277
late
Token late
Feature activation+0.000
the
Token the
Feature activation+0.869
previous
Token previous
Feature activation+1.901
day
Token day
Feature activation+2.772
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
outlook
Token outlook
Feature activation+0.000
for
Token for
Feature activation+1.454
the
Token the
Feature activation+0.275

INTERVAL 1.943 - 2.429
CONTAINS 0.011%

FX
Token FX
Feature activation+0.000
p
Token p
Feature activation+0.112
ips
Tokenips
Feature activation+0.000
and
Token and
Feature activation+0.585
a
Token a
Feature activation+0.542
few
Token few
Feature activation+1.995
basis
Token basis
Feature activation+0.065
points
Token points
Feature activation+0.000
in
Token in
Feature activation+1.316
the
Token the
Feature activation+0.751
ES
Token ES
Feature activation+0.204
companies
Token companies
Feature activation+0.497
used
Token used
Feature activation+0.747
cheap
Token cheap
Feature activation+2.235
credit
Token credit
Feature activation+0.000
to
Token to
Feature activation+0.021
buy
Token buy
Feature activation+1.969
their
Token their
Feature activation+2.060
own
Token own
Feature activation+2.588
stocks
Token stocks
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
field
Token field
Feature activation+0.412
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.958
in
Token in
Feature activation+0.731
a
Token a
Feature activation+0.884
recent
Token recent
Feature activation+2.000
investor
Token investor
Feature activation+0.524
letter
Token letter
Feature activation+0.861
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.912
weak
Token weak
Feature activation+1.030
global
Token global
Feature activation+1.615
growth
Token growth
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.673
International
Token International
Feature activation+2.083
Monetary
Token Monetary
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
(
Token (
Feature activation+0.000
IM
TokenIM
Feature activation+0.000
F
TokenF
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.580
,
Token,
Feature activation+0.235
chief
Token chief
Feature activation+2.242
market
Token market
Feature activation+0.000
analyst
Token analyst
Feature activation+0.000
at
Token at
Feature activation+0.104
FX
Token FX
Feature activation+0.679
broker
Token broker
Feature activation+0.103

INTERVAL 1.458 - 1.943
CONTAINS 0.027%

a
Token a
Feature activation+0.580
bank
Token bank
Feature activation+0.000
run
Token run
Feature activation+0.000
that
Token that
Feature activation+0.097
could
Token could
Feature activation+0.000
spread
Token spread
Feature activation+1.478
to
Token to
Feature activation+0.504
other
Token other
Feature activation+0.678
vulnerable
Token vulnerable
Feature activation+0.437
periphery
Token periphery
Feature activation+1.409
euro
Token euro
Feature activation+0.000
we
Token we
Feature activation+0.614
can
Token can
Feature activation+0.339
see
Token see
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Chosen
Token Chosen
Feature activation+1.876
People
Token People
Feature activation+1.001
have
Token have
Feature activation+0.008
not
Token not
Feature activation+0.022
done
Token done
Feature activation+0.341
very
Token very
Feature activation+0.154
million
Token million
Feature activation+0.000
after
Token after
Feature activation+0.000
its
Token its
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+0.000
filing
Token filing
Feature activation+0.000
,
Token,
Feature activation+1.611
according
Token according
Feature activation+0.000
to
Token to
Feature activation+1.775
Fact
Token Fact
Feature activation+1.477
Set
TokenSet
Feature activation+1.736
,
Token,
Feature activation+0.737
underest
Token underest
Feature activation+0.000
imating
Tokenimating
Feature activation+0.396
the
Token the
Feature activation+0.000
further
Token further
Feature activation+0.000
upside
Token upside
Feature activation+0.000
for
Token for
Feature activation+1.533
inflation
Token inflation
Feature activation+0.000
from
Token from
Feature activation+0.000
here
Token here
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.257
The
TokenThe
Feature activation+0.820
data
Token data
Feature activation+0.000
points
Token points
Feature activation+0.393
can
Token can
Feature activation+0.000
give
Token give
Feature activation+1.599
you
Token you
Feature activation+0.243
the
Token the
Feature activation+0.434
will
Token will
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
:
Token:
Feature activation+1.122

INTERVAL 0.972 - 1.458
CONTAINS 0.064%

Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.499
the
Token the
Feature activation+0.000
going
Token going
Feature activation+0.028
gets
Token gets
Feature activation+0.049
tough
Token tough
Feature activation+1.135
,
Token,
Feature activation+0.343
investors
Token investors
Feature activation+0.000
have
Token have
Feature activation+0.133
historically
Token historically
Feature activation+0.046
fl
Token fl
Feature activation+0.144
asured
Tokenasured
Feature activation+0.000
factor
Token factor
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
affecting
Token affecting
Feature activation+0.000
all
Token all
Feature activation+1.249
three
Token three
Feature activation+0.550
variables
Token variables
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.170
special
Token special
Feature activation+0.491
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.075
s
Tokens
Feature activation+0.495
$
Token $
Feature activation+0.000
100
Token100
Feature activation+0.000
billion
Token billion
Feature activation+1.103
investment
Token investment
Feature activation+0.000
portfolio
Token portfolio
Feature activation+0.000
.
Token.
Feature activation+0.000
Klein
Token Klein
Feature activation+0.000
said
Token said
Feature activation+0.706
Interest
TokenInterest
Feature activation+0.000
rates
Token rates
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
far
Token far
Feature activation+1.283
and
Token and
Feature activation+0.000
away
Token away
Feature activation+0.120
the
Token the
Feature activation+0.087
biggest
Token biggest
Feature activation+0.105
factor
Token factor
Feature activation+0.000
firm
Token firm
Feature activation+0.927
's
Token's
Feature activation+0.515
books
Token books
Feature activation+0.000
and
Token and
Feature activation+0.545
records
Token records
Feature activation+0.000
as
Token as
Feature activation+1.231
well
Token well
Feature activation+0.825
as
Token as
Feature activation+0.690
in
Token in
Feature activation+1.676
any
Token any
Feature activation+1.330
disclosures
Token disclosures
Feature activation+0.000

INTERVAL 0.486 - 0.972
CONTAINS 0.158%

said
Token said
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.340
more
Token more
Feature activation+0.817
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.855
getting
Token getting
Feature activation+1.157
into
Token into
Feature activation+0.674
using
Token using
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
as
Token as
Feature activation+0.000
trading
Token trading
Feature activation+0.000
and
Token and
Feature activation+0.734
announce
Token announce
Feature activation+0.000
a
Token a
Feature activation+0.729
stop
Token stop
Feature activation+1.306
to
Token to
Feature activation+0.666
new
Token new
Feature activation+0.386
user
Token user
Feature activation+2.470
registrations
Token registrations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
make
Token make
Feature activation+0.000
that
Token that
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
.
Token.
Feature activation+0.000
Opt
Token Opt
Feature activation+0.000
ima
Tokenima
Feature activation+0.496
also
Token also
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.038
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
Co
Token Co
Feature activation+0.000
,
Token,
Feature activation+0.000
subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.000
FIR
Token FIR
Feature activation+0.000
B
TokenB
Feature activation+0.549
approval
Token approval
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
sale
Token sale
Feature activation+0.000
of
Token of
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
30
Token 30
Feature activation+0.840
-
Token-
Feature activation+1.026
story
Tokenstory
Feature activation+0.000
downtown
Token downtown
Feature activation+0.689
building
Token building
Feature activation+0.000
,
Token,
Feature activation+0.000
its
Token its
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.486
CONTAINS 99.732%

not
Token not
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
knows
Token knows
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
another
Token another
Feature activation+0.000
plasma
Token plasma
Feature activation+0.000
rifle
Token rifle
Feature activation+0.000
'.
Token'.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
S
Token S
Feature activation+0.000
esse
Tokenesse
Feature activation+0.000
gn
Tokengn
Feature activation+0.000
on
Tokenon
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
massive
Token massive
Feature activation+0.000
impact
Token impact
Feature activation+0.000
shortly
Token shortly
Feature activation+0.000
thereafter
Token thereafter
Feature activation+0.000
,
Token,
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
ned
Tokenned
Feature activation+0.000
the
Token the
Feature activation+0.000
aspirations
Token aspirations
Feature activation+0.000
of
Token of
Feature activation+0.000
Israelis
Token Israelis
Feature activation+0.000
and
Token and
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token'
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
array
Token array
Feature activation+0.000
of
Token of
Feature activation+0.000
useless
Token useless
Feature activation+0.000
feminine
Token feminine
Feature activation+0.000
was
Token was
Feature activation+0.000
hes
Tokenhes
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 8 in H11.3: (feature 8194)

TOP ACTIVATIONS
MAX = 5.138

Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278
sole
Token sole
Feature activation+2.051
protect
Token protect
Feature activation+0.000
stocks
Token stocks
Feature activation+0.000
of
Token of
Feature activation+0.132
Columbia
Token Columbia
Feature activation+0.610
River
Token River
Feature activation+1.041
basin
Token basin
Feature activation+4.289
Chin
Token Chin
Feature activation+0.458
ook
Tokenook
Feature activation+1.361
salmon
Token salmon
Feature activation+0.375
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
car
Token car
Feature activation+0.545
r
Tokenr
Feature activation+0.000
ion
Tokenion
Feature activation+0.541
beetles
Token beetles
Feature activation+0.000
for
Token for
Feature activation+0.412
cross
Token cross
Feature activation+4.099
poll
Token poll
Feature activation+0.000
ination
Tokenination
Feature activation+0.000
.[
Token.[
Feature activation+0.000
20
Token20
Feature activation+0.000
]
Token]
Feature activation+0.000
g
Tokeng
Feature activation+1.284
arten
Tokenarten
Feature activation+3.616
Sch
Token Sch
Feature activation+0.129
oen
Tokenoen
Feature activation+3.819
br
Tokenbr
Feature activation+0.158
unn
Tokenunn
Feature activation+3.913
'
Token'
Feature activation+2.787
Zoo
Token Zoo
Feature activation+1.675
in
Token in
Feature activation+1.128
Vienna
Token Vienna
Feature activation+0.851
,
Token,
Feature activation+0.583
'
Token '
Feature activation+0.000
Tier
TokenTier
Feature activation+0.629
g
Tokeng
Feature activation+1.284
arten
Tokenarten
Feature activation+3.616
Sch
Token Sch
Feature activation+0.129
oen
Tokenoen
Feature activation+3.819
br
Tokenbr
Feature activation+0.158
unn
Tokenunn
Feature activation+3.913
'
Token'
Feature activation+2.787
Zoo
Token Zoo
Feature activation+1.675
in
Token in
Feature activation+1.128
first
Token first
Feature activation+2.018
seen
Token seen
Feature activation+1.078
and
Token and
Feature activation+3.117
collected
Token collected
Feature activation+0.005
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
.
Token.
Feature activation+0.026
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.326
University
TokenUniversity
Feature activation+2.349
of
Token of
Feature activation+0.000
Washington
Token Washington
Feature activation+3.718
scientists
Token scientists
Feature activation+1.113
recently
Token recently
Feature activation+1.238
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.097
name
Token name
Feature activation+0.347
ius
Tokenius
Feature activation+0.422
Pick
Token Pick
Feature activation+0.000
ard
Tokenard
Feature activation+0.930
-
Token-
Feature activation+0.000
Cam
TokenCam
Feature activation+0.000
bridge
Tokenbridge
Feature activation+3.642
described
Token described
Feature activation+0.000
another
Token another
Feature activation+0.000
at
Token at
Feature activation+0.000
rac
Tokenrac
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278
sole
Token sole
Feature activation+2.051
specimen
Token specimen
Feature activation+1.532
time
Token time
Feature activation+1.684
at
Token at
Feature activation+0.849
'
Token '
Feature activation+0.000
Tier
TokenTier
Feature activation+0.629
g
Tokeng
Feature activation+1.284
arten
Tokenarten
Feature activation+3.616
Sch
Token Sch
Feature activation+0.129
oen
Tokenoen
Feature activation+3.819
br
Tokenbr
Feature activation+0.158
unn
Tokenunn
Feature activation+3.913
'
Token'
Feature activation+2.787
International
Token International
Feature activation+2.882
Union
Token Union
Feature activation+2.094
for
Token for
Feature activation+0.521
Conservation
Token Conservation
Feature activation+0.534
of
Token of
Feature activation+0.443
Nature
Token Nature
Feature activation+3.513
(
Token (
Feature activation+0.482
I
TokenI
Feature activation+0.948
UC
TokenUC
Feature activation+0.000
N
TokenN
Feature activation+0.953
)
Token)
Feature activation+3.182
these
Token these
Feature activation+0.359
accounts
Token accounts
Feature activation+0.493
of
Token of
Feature activation+0.763
rising
Token rising
Feature activation+1.243
numbers
Token numbers
Feature activation+0.877
real
Token real
Feature activation+3.453
,
Token,
Feature activation+1.067
or
Token or
Feature activation+1.232
are
Token are
Feature activation+1.593
humans
Token humans
Feature activation+0.996
just
Token just
Feature activation+1.185
a
Token a
Feature activation+1.613
biologist
Token biologist
Feature activation+0.458
who
Token who
Feature activation+1.674
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
wrapper
Token wrapper
Feature activation+3.441
appeared
Token appeared
Feature activation+0.342
to
Token to
Feature activation+0.572
be
Token be
Feature activation+0.545
squeezing
Token squeezing
Feature activation+2.134
the
Token the
Feature activation+0.962
a
Token a
Feature activation+0.535
day
Token day
Feature activation+0.891
before
Token before
Feature activation+1.033
three
Token three
Feature activation+1.401
Pacific
Token Pacific
Feature activation+0.833
Northwest
Token Northwest
Feature activation+3.405
states
Token states
Feature activation+2.422
are
Token are
Feature activation+0.738
authorized
Token authorized
Feature activation+0.778
to
Token to
Feature activation+2.217
begin
Token begin
Feature activation+2.325
eastern
Token eastern
Feature activation+0.758
Asia
Token Asia
Feature activation+3.075
,
Token,
Feature activation+1.358
particularly
Token particularly
Feature activation+0.000
India
Token India
Feature activation+1.750
,
Token,
Feature activation+3.244
and
Token and
Feature activation+0.000
owe
Token owe
Feature activation+0.933
their
Token their
Feature activation+1.120
appearance
Token appearance
Feature activation+0.000
to
Token to
Feature activation+0.000
Nature
Token Nature
Feature activation+3.513
(
Token (
Feature activation+0.482
I
TokenI
Feature activation+0.948
UC
TokenUC
Feature activation+0.000
N
TokenN
Feature activation+0.953
)
Token)
Feature activation+3.182
Red
Token Red
Feature activation+1.131
List
Token List
Feature activation+2.238
are
Token are
Feature activation+0.000
classified
Token classified
Feature activation+0.000
as
Token as
Feature activation+0.152
of
Token of
Feature activation+0.000
st
Token st
Feature activation+0.260
inging
Tokeninging
Feature activation+1.061
insects
Token insects
Feature activation+2.554
are
Token are
Feature activation+1.371
still
Token still
Feature activation+3.177
banned
Token banned
Feature activation+1.578
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-----
Token-----
Feature activation+0.270
The
Token The
Feature activation+0.000
fish
Token fish
Feature activation+0.256
was
Token was
Feature activation+0.161
first
Token first
Feature activation+2.018
seen
Token seen
Feature activation+1.078
and
Token and
Feature activation+3.117
collected
Token collected
Feature activation+0.005
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
found
Token found
Feature activation+0.648
in
Token in
Feature activation+0.000
southern
Token southern
Feature activation+0.794
and
Token and
Feature activation+1.145
eastern
Token eastern
Feature activation+0.758
Asia
Token Asia
Feature activation+3.075
,
Token,
Feature activation+1.358
particularly
Token particularly
Feature activation+0.000
India
Token India
Feature activation+1.750
,
Token,
Feature activation+3.244
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 2.523

in
Token in
Feature activation+0.042
Top resid features:
Australia
Token Australia
Feature activation+0.093
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
1980
Token 1980
Feature activation+0.076
Top resid features:
by
Token by
Feature activation+0.729
Top resid features:
a
Token a
Feature activation+1.062
Top resid features:
UW
Token UW
Feature activation+0.127
Top resid features:
graduate
Token graduate
Feature activation+0.000
Top resid features:
student
Token student
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:
in
Token in
Feature activation+0.024
Top resid features:
Australia
Token Australia
Feature activation+0.081
Top resid features:
in
Token in
Feature activation+0.016
Top resid features:
1980
Token 1980
Feature activation+0.102
Top resid features:
by
Token by
Feature activation+0.718
Top resid features:
a
Token a
Feature activation+0.820
Top resid features:
UW
Token UW
Feature activation+0.117
Top resid features:
graduate
Token graduate
Feature activation-0.044
Top resid features:
student
Token student
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:
sea
Token sea
Feature activation+0.348
Top resid features:
lions
Token lions
Feature activation-0.230
Top resid features:
to
Token to
Feature activation-0.015
Top resid features:
protect
Token protect
Feature activation+0.330
Top resid features:
stocks
Token stocks
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+2.383
Top resid features:
Columbia
Token Columbia
Feature activation+0.095
Top resid features:
River
Token River
Feature activation+1.005
Top resid features:
basin
Token basin
Feature activation+0.239
Top resid features:
Chin
Token Chin
Feature activation+0.000
Top resid features:
ook
Tokenook
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.206
Top resid features:
car
Token car
Feature activation+0.087
Top resid features:
r
Tokenr
Feature activation+0.032
Top resid features:
ion
Tokenion
Feature activation+0.151
Top resid features:
beetles
Token beetles
Feature activation+0.173
Top resid features:
for
Token for
Feature activation+1.497
Top resid features:
cross
Token cross
Feature activation+0.144
Top resid features:
poll
Token poll
Feature activation+0.000
Top resid features:
ination
Tokenination
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
20
Token20
Feature activation+0.000
Top resid features:
sea
Token sea
Feature activation-0.002
Top resid features:
lion
Token lion
Feature activation+0.088
Top resid features:
during
Token during
Feature activation+0.173
Top resid features:
feeding
Token feeding
Feature activation+0.155
Top resid features:
time
Token time
Feature activation+0.132
Top resid features:
at
Token at
Feature activation+2.523
Top resid features:
'
Token '
Feature activation+0.580
Top resid features:
Tier
TokenTier
Feature activation-0.005
Top resid features:
g
Tokeng
Feature activation+0.015
Top resid features:
arten
Tokenarten
Feature activation+0.240
Top resid features:
Sch
Token Sch
Feature activation+0.003
Top resid features:
sea
Token sea
Feature activation+0.065
Top resid features:
lion
Token lion
Feature activation+0.355
Top resid features:
during
Token during
Feature activation+0.157
Top resid features:
feeding
Token feeding
Feature activation+0.271
Top resid features:
time
Token time
Feature activation+0.084
Top resid features:
at
Token at
Feature activation+0.920
Top resid features:
'
Token '
Feature activation+0.908
Top resid features:
Tier
TokenTier
Feature activation-0.022
Top resid features:
g
Tokeng
Feature activation+0.021
Top resid features:
arten
Tokenarten
Feature activation+0.398
Top resid features:
Sch
Token Sch
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.092
Top resid features:
The
Token The
Feature activation+0.013
Top resid features:
fish
Token fish
Feature activation+0.257
Top resid features:
was
Token was
Feature activation+0.128
Top resid features:
first
Token first
Feature activation+0.155
Top resid features:
seen
Token seen
Feature activation+1.499
Top resid features:
and
Token and
Feature activation+0.160
Top resid features:
collected
Token collected
Feature activation+0.515
Top resid features:
in
Token in
Feature activation+0.331
Top resid features:
Australia
Token Australia
Feature activation+0.015
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.002
Top resid features:
".
Token ".
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.003
Top resid features:
New
TokenNew
Feature activation-0.022
Top resid features:
fish
Token fish
Feature activation+0.061
Top resid features:
genus
Token genus
Feature activation+0.599
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
species
Token species
Feature activation+0.101
Top resid features:
named
Token named
Feature activation+0.101
Top resid features:
for
Token for
Feature activation+0.057
Top resid features:
its
Token its
Feature activation+0.041
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
first
Token first
Feature activation+0.031
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
rac
Tokenrac
Feature activation+0.006
Top resid features:
ide
Tokenide
Feature activation+0.047
Top resid features:
spider
Token spider
Feature activation+0.927
Top resid features:
,
Token,
Feature activation+0.353
Top resid features:
Had
Token Had
Feature activation+0.000
Top resid features:
ron
Tokenron
Feature activation+0.021
Top resid features:
y
Tokeny
Feature activation-0.004
Top resid features:
che
Tokenche
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.078
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
fish
Token fish
Feature activation+0.270
Top resid features:
was
Token was
Feature activation+0.168
Top resid features:
first
Token first
Feature activation+0.198
Top resid features:
seen
Token seen
Feature activation+0.551
Top resid features:
and
Token and
Feature activation+0.181
Top resid features:
collected
Token collected
Feature activation+0.233
Top resid features:
in
Token in
Feature activation+0.027
Top resid features:
Australia
Token Australia
Feature activation+0.055
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
sea
Token sea
Feature activation+0.025
Top resid features:
lion
Token lion
Feature activation+0.099
Top resid features:
during
Token during
Feature activation+0.316
Top resid features:
feeding
Token feeding
Feature activation+0.402
Top resid features:
time
Token time
Feature activation+0.168
Top resid features:
at
Token at
Feature activation+1.782
Top resid features:
'
Token '
Feature activation+0.692
Top resid features:
Tier
TokenTier
Feature activation-0.043
Top resid features:
g
Tokeng
Feature activation+0.007
Top resid features:
arten
Tokenarten
Feature activation+0.122
Top resid features:
Sch
Token Sch
Feature activation+0.000
Top resid features:
marine
Token marine
Feature activation+0.016
Top resid features:
inver
Token inver
Feature activation-0.009
Top resid features:
te
Tokente
Feature activation-0.001
Top resid features:
brates
Tokenbrates
Feature activation+0.023
Top resid features:
assessed
Token assessed
Feature activation+0.120
Top resid features:
on
Token on
Feature activation+2.029
Top resid features:
the
Token the
Feature activation+0.649
Top resid features:
International
Token International
Feature activation+0.543
Top resid features:
Union
Token Union
Feature activation+0.403
Top resid features:
for
Token for
Feature activation+0.092
Top resid features:
Conservation
Token Conservation
Feature activation+0.041
Top resid features:
sh
Token sh
Feature activation+0.003
Top resid features:
rim
Tokenrim
Feature activation+0.004
Top resid features:
pers
Tokenpers
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.222
Top resid features:
But
Token But
Feature activation+0.213
Top resid features:
are
Token are
Feature activation+0.583
Top resid features:
these
Token these
Feature activation+0.430
Top resid features:
accounts
Token accounts
Feature activation+0.203
Top resid features:
of
Token of
Feature activation+0.517
Top resid features:
rising
Token rising
Feature activation+0.158
Top resid features:
numbers
Token numbers
Feature activation+0.496
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
biologist
Token biologist
Feature activation+0.029
Top resid features:
who
Token who
Feature activation+0.025
Top resid features:
said
Token said
Feature activation+1.432
Top resid features:
the
Token the
Feature activation+1.609
Top resid features:
wrapper
Token wrapper
Feature activation+0.263
Top resid features:
appeared
Token appeared
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
squeezing
Token squeezing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.093
Top resid features:
animals
Token animals
Feature activation+0.035
Top resid features:
a
Token a
Feature activation+0.164
Top resid features:
day
Token day
Feature activation+0.021
Top resid features:
before
Token before
Feature activation+0.224
Top resid features:
three
Token three
Feature activation+2.006
Top resid features:
Pacific
Token Pacific
Feature activation+0.088
Top resid features:
Northwest
Token Northwest
Feature activation+0.145
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:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
White
TokenWhite
Feature activation-0.161
Top resid features:
tigers
Token tigers
Feature activation+1.318
Top resid features:
are
Token are
Feature activation+0.592
Top resid features:
found
Token found
Feature activation+1.773
Top resid features:
in
Token in
Feature activation+0.327
Top resid features:
southern
Token southern
Feature activation+0.072
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
eastern
Token eastern
Feature activation+0.025
Top resid features:
Asia
Token Asia
Feature activation+0.295
Top resid features:
marine
Token marine
Feature activation+0.019
Top resid features:
inver
Token inver
Feature activation-0.012
Top resid features:
te
Tokente
Feature activation-0.001
Top resid features:
brates
Tokenbrates
Feature activation+0.071
Top resid features:
assessed
Token assessed
Feature activation+0.138
Top resid features:
on
Token on
Feature activation+1.228
Top resid features:
the
Token the
Feature activation+0.210
Top resid features:
International
Token International
Feature activation+0.268
Top resid features:
Union
Token Union
Feature activation+0.177
Top resid features:
for
Token for
Feature activation+0.039
Top resid features:
Conservation
Token Conservation
Feature activation+0.116
Top resid features:
mell
Token mell
Feature activation+0.003
Top resid features:
ifer
Tokenifer
Feature activation+0.018
Top resid features:
a
Tokena
Feature activation+0.133
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Was
Token Was
Feature activation+0.012
Top resid features:
ps
Tokenps
Feature activation+1.163
Top resid features:
,
Token,
Feature activation+0.184
Top resid features:
horn
Token horn
Feature activation+0.015
Top resid features:
ets
Tokenets
Feature activation+0.160
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
world
Token world
Feature activation+0.023
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
The
Token The
Feature activation+0.026
Top resid features:
fish
Token fish
Feature activation+0.166
Top resid features:
was
Token was
Feature activation+0.393
Top resid features:
first
Token first
Feature activation+1.445
Top resid features:
seen
Token seen
Feature activation+0.197
Top resid features:
and
Token and
Feature activation+0.226
Top resid features:
collected
Token collected
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Australia
Token Australia
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.067
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
White
TokenWhite
Feature activation+0.010
Top resid features:
tigers
Token tigers
Feature activation+0.937
Top resid features:
are
Token are
Feature activation+0.609
Top resid features:
found
Token found
Feature activation+2.292
Top resid features:
in
Token in
Feature activation+0.163
Top resid features:
southern
Token southern
Feature activation+0.056
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
eastern
Token eastern
Feature activation+0.022
Top resid features:
Asia
Token Asia
Feature activation+0.150
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.04

Head 3: 0.33

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.04

Head 8: 0.14

Head 9: 0.04

Head 10: 0.06

Head 11: 0.11

Positive logits

species6.61

wildlife6.44

species6.11

biologists5.91

habitat5.83

Wildlife5.78

zoo5.73

mammal5.68

Species5.61

animals5.54

biodiversity5.47

breeding5.45

extinct5.39

birds5.34

biologist5.32

Bird5.32

mammals5.32

habitats5.31

fishes5.31

animal5.30

Negative logits

Gilmore-3.04

Rouhani-2.90

Valve-2.70

Substance-2.62

accuser-2.60

-2.58

Kaepernick-2.56

Polic-2.52

akeru-2.49

-2.49

Meh-2.48

Unified-2.45

ipolar-2.43

DUI-2.43

Shap-2.39

ESL-2.38

FML-2.37

Weiner-2.37

Lenovo-2.36

Manafort-2.35

INTERVAL 4.624 - 5.138
CONTAINS 0.000%

Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278

INTERVAL 4.110 - 4.624
CONTAINS 0.000%

in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278
sole
Token sole
Feature activation+2.051
protect
Token protect
Feature activation+0.000
stocks
Token stocks
Feature activation+0.000
of
Token of
Feature activation+0.132
Columbia
Token Columbia
Feature activation+0.610
River
Token River
Feature activation+1.041
basin
Token basin
Feature activation+4.289
Chin
Token Chin
Feature activation+0.458
ook
Tokenook
Feature activation+1.361
salmon
Token salmon
Feature activation+0.375
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.597 - 4.110
CONTAINS 0.001%

1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
graduate
Token graduate
Feature activation+4.547
student
Token student
Feature activation+3.624
,
Token,
Feature activation+1.154
but
Token but
Feature activation+1.544
the
Token the
Feature activation+0.278
sole
Token sole
Feature activation+2.051
specimen
Token specimen
Feature activation+1.532
first
Token first
Feature activation+2.018
seen
Token seen
Feature activation+1.078
and
Token and
Feature activation+3.117
collected
Token collected
Feature activation+0.005
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
by
Token by
Feature activation+1.810
a
Token a
Feature activation+1.864
UW
Token UW
Feature activation+5.138
time
Token time
Feature activation+1.684
at
Token at
Feature activation+0.849
'
Token '
Feature activation+0.000
Tier
TokenTier
Feature activation+0.629
g
Tokeng
Feature activation+1.284
arten
Tokenarten
Feature activation+3.616
Sch
Token Sch
Feature activation+0.129
oen
Tokenoen
Feature activation+3.819
br
Tokenbr
Feature activation+0.158
unn
Tokenunn
Feature activation+3.913
'
Token'
Feature activation+2.787
'
Token '
Feature activation+0.000
Tier
TokenTier
Feature activation+0.629
g
Tokeng
Feature activation+1.284
arten
Tokenarten
Feature activation+3.616
Sch
Token Sch
Feature activation+0.129
oen
Tokenoen
Feature activation+3.819
br
Tokenbr
Feature activation+0.158
unn
Tokenunn
Feature activation+3.913
'
Token'
Feature activation+2.787
Zoo
Token Zoo
Feature activation+1.675
in
Token in
Feature activation+1.128
car
Token car
Feature activation+0.545
r
Tokenr
Feature activation+0.000
ion
Tokenion
Feature activation+0.541
beetles
Token beetles
Feature activation+0.000
for
Token for
Feature activation+0.412
cross
Token cross
Feature activation+4.099
poll
Token poll
Feature activation+0.000
ination
Tokenination
Feature activation+0.000
.[
Token.[
Feature activation+0.000
20
Token20
Feature activation+0.000
]
Token]
Feature activation+0.000

INTERVAL 3.083 - 3.597
CONTAINS 0.001%

Nature
Token Nature
Feature activation+3.513
(
Token (
Feature activation+0.482
I
TokenI
Feature activation+0.948
UC
TokenUC
Feature activation+0.000
N
TokenN
Feature activation+0.953
)
Token)
Feature activation+3.182
Red
Token Red
Feature activation+1.131
List
Token List
Feature activation+2.238
are
Token are
Feature activation+0.000
classified
Token classified
Feature activation+0.000
as
Token as
Feature activation+0.152
The
Token The
Feature activation+0.000
fish
Token fish
Feature activation+0.256
was
Token was
Feature activation+0.161
first
Token first
Feature activation+2.018
seen
Token seen
Feature activation+1.078
and
Token and
Feature activation+3.117
collected
Token collected
Feature activation+0.005
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+3.795
in
Token in
Feature activation+0.000
1980
Token 1980
Feature activation+0.576
eastern
Token eastern
Feature activation+0.758
Asia
Token Asia
Feature activation+3.075
,
Token,
Feature activation+1.358
particularly
Token particularly
Feature activation+0.000
India
Token India
Feature activation+1.750
,
Token,
Feature activation+3.244
and
Token and
Feature activation+0.000
owe
Token owe
Feature activation+0.933
their
Token their
Feature activation+1.120
appearance
Token appearance
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
st
Token st
Feature activation+0.260
inging
Tokeninging
Feature activation+1.061
insects
Token insects
Feature activation+2.554
are
Token are
Feature activation+1.371
still
Token still
Feature activation+3.177
banned
Token banned
Feature activation+1.578
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-----
Token-----
Feature activation+0.270
a
Token a
Feature activation+1.613
biologist
Token biologist
Feature activation+0.458
who
Token who
Feature activation+1.674
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
wrapper
Token wrapper
Feature activation+3.441
appeared
Token appeared
Feature activation+0.342
to
Token to
Feature activation+0.572
be
Token be
Feature activation+0.545
squeezing
Token squeezing
Feature activation+2.134
the
Token the
Feature activation+0.962

INTERVAL 2.569 - 3.083
CONTAINS 0.003%

that
Token that
Feature activation+0.223
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+1.989
has
Token has
Feature activation+2.789
never
Token never
Feature activation+2.674
shared
Token shared
Feature activation+1.000
water
Token water
Feature activation+0.113
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.351
male
Token male
Feature activation+0.000
te
Tokente
Feature activation+0.000
brates
Tokenbrates
Feature activation+0.683
assessed
Token assessed
Feature activation+1.688
on
Token on
Feature activation+0.257
the
Token the
Feature activation+0.832
International
Token International
Feature activation+2.882
Union
Token Union
Feature activation+2.094
for
Token for
Feature activation+0.521
Conservation
Token Conservation
Feature activation+0.534
of
Token of
Feature activation+0.443
Nature
Token Nature
Feature activation+3.513
In
Token In
Feature activation+0.000
that
Token that
Feature activation+0.223
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+1.989
has
Token has
Feature activation+2.789
never
Token never
Feature activation+2.674
shared
Token shared
Feature activation+1.000
water
Token water
Feature activation+0.113
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.351
among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.000
species
Token species
Feature activation+0.107
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.748
be
Token be
Feature activation+2.625
harvested
Token harvested
Feature activation+0.000
,
Token,
Feature activation+0.033
although
Token although
Feature activation+0.000
some
Token some
Feature activation+0.000
have
Token have
Feature activation+0.206
big
Token big
Feature activation+0.000
cat
Token cat
Feature activation+0.000
was
Token was
Feature activation+0.000
caught
Token caught
Feature activation+0.731
on
Token on
Feature activation+1.300
camera
Token camera
Feature activation+2.861
roaming
Token roaming
Feature activation+0.000
through
Token through
Feature activation+0.000
back
Token back
Feature activation+0.432
yards
Tokenyards
Feature activation+0.252
near
Token near
Feature activation+0.000

INTERVAL 2.055 - 2.569
CONTAINS 0.007%

.
Token.
Feature activation+0.378
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.066
Still
TokenStill
Feature activation+0.380
,
Token,
Feature activation+1.246
some
Token some
Feature activation+2.157
fishermen
Token fishermen
Feature activation+0.249
said
Token said
Feature activation+0.427
that
Token that
Feature activation+0.000
although
Token although
Feature activation+0.783
the
Token the
Feature activation+0.731
The
Token The
Feature activation+0.017
P
Token P
Feature activation+0.000
ines
Tokenines
Feature activation+0.052
from
Token from
Feature activation+0.092
encro
Token encro
Feature activation+0.000
aching
Tokenaching
Feature activation+2.096
development
Token development
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
was
Token was
Feature activation+0.638
observed
Token observed
Feature activation+1.444
beating
Token beating
Feature activation+0.096
the
Token the
Feature activation+0.000
single
Token single
Feature activation+1.203
-
Token-
Feature activation+2.262
t
Tokent
Feature activation+0.680
usk
Tokenusk
Feature activation+0.000
African
Token African
Feature activation+0.013
elephant
Token elephant
Feature activation+0.559
in
Token in
Feature activation+0.330
escaping
Token escaping
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
dog
Token dog
Feature activation+0.000
from
Token from
Feature activation+0.000
Perez
Token Perez
Feature activation+2.292
's
Token's
Feature activation+0.119
mother
Token mother
Feature activation+0.102
's
Token's
Feature activation+0.000
property
Token property
Feature activation+0.235
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.963
captain
Token captain
Feature activation+0.000
of
Token of
Feature activation+0.000
Re
Token Re
Feature activation+0.163
el
Tokenel
Feature activation+0.869
Candy
Token Candy
Feature activation+2.442
Sport
Token Sport
Feature activation+1.487
Fishing
Token Fishing
Feature activation+0.496
in
Token in
Feature activation+0.000
Jupiter
Token Jupiter
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.541 - 2.055
CONTAINS 0.020%

.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
the
Token the
Feature activation+0.328
scientists
Token scientists
Feature activation+1.446
filmed
Token filmed
Feature activation+0.000
them
Token them
Feature activation+1.834
feeding
Token feeding
Feature activation+0.000
on
Token on
Feature activation+0.887
algae
Token algae
Feature activation+0.000
-
Token-
Feature activation+0.038
covered
Tokencovered
Feature activation+2.130
you
Token you
Feature activation+0.000
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
hedge
Token hedge
Feature activation+0.000
hog
Tokenhog
Feature activation+0.123
out
Token out
Feature activation+1.737
and
Token and
Feature activation+0.000
about
Token about
Feature activation+1.916
in
Token in
Feature activation+0.650
the
Token the
Feature activation+0.755
wild
Token wild
Feature activation+0.982
ines
Tokenines
Feature activation+0.054
have
Token have
Feature activation+0.000
suffered
Token suffered
Feature activation+1.959
massive
Token massive
Feature activation+2.904
mortal
Token mortal
Feature activation+1.864
ities
Tokenities
Feature activation+1.602
from
Token from
Feature activation+1.345
the
Token the
Feature activation+1.394
deadly
Token deadly
Feature activation+1.723
convergence
Token convergence
Feature activation+0.916
of
Token of
Feature activation+1.778
as
Token as
Feature activation+1.420
competition
Token competition
Feature activation+1.100
for
Token for
Feature activation+1.244
cheap
Token cheap
Feature activation+2.433
taxpayer
Token taxpayer
Feature activation+1.660
subsidized
Token subsidized
Feature activation+1.783
grazing
Token grazing
Feature activation+0.258
on
Token on
Feature activation+0.031
public
Token public
Feature activation+1.952
lands
Token lands
Feature activation+0.000
.
Token.
Feature activation+0.000
det
Tokendet
Feature activation+0.000
angling
Tokenangling
Feature activation+0.000
nightmare
Token nightmare
Feature activation+0.000
and
Token and
Feature activation+0.000
killed
Token killed
Feature activation+0.000
untold
Token untold
Feature activation+1.878
numbers
Token numbers
Feature activation+0.000
of
Token of
Feature activation+1.371
marine
Token marine
Feature activation+0.550
creatures
Token creatures
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 1.028 - 1.541
CONTAINS 0.048%

dead
Token dead
Feature activation+0.825
,
Token,
Feature activation+0.889
but
Token but
Feature activation+0.879
last
Token last
Feature activation+0.876
Wednesday
Token Wednesday
Feature activation+0.537
a
Token a
Feature activation+1.283
man
Token man
Feature activation+1.114
was
Token was
Feature activation+0.995
killed
Token killed
Feature activation+0.077
by
Token by
Feature activation+0.000
an
Token an
Feature activation+1.063
,
Token,
Feature activation+0.533
stock
Token stock
Feature activation+0.440
y
Tokeny
Feature activation+0.585
creatures
Token creatures
Feature activation+1.614
found
Token found
Feature activation+0.827
in
Token in
Feature activation+1.066
most
Token most
Feature activation+1.645
tropical
Token tropical
Feature activation+1.656
and
Token and
Feature activation+1.161
subt
Token subt
Feature activation+0.000
rop
Tokenrop
Feature activation+0.757
,
Token,
Feature activation+0.431
the
Token the
Feature activation+0.276
au
Token au
Feature activation+0.000
ks
Tokenks
Feature activation+0.364
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+1.056
feed
Token feed
Feature activation+0.000
further
Token further
Feature activation+0.782
offshore
Token offshore
Feature activation+0.000
.
Token.
Feature activation+0.000
Strong
Token Strong
Feature activation+0.330
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
threatened
Token threatened
Feature activation+0.000
by
Token by
Feature activation+0.199
endless
Token endless
Feature activation+0.759
,
Token,
Feature activation+1.093
bigger
Token bigger
Feature activation+1.268
monsters
Token monsters
Feature activation+0.000
and
Token and
Feature activation+0.376
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
can
Token can
Feature activation+0.000
fish
Token fish
Feature activation+0.000
,
Token,
Feature activation+0.000
reptiles
Token reptiles
Feature activation+0.000
and
Token and
Feature activation+0.948
birds
Token birds
Feature activation+1.082
have
Token have
Feature activation+0.000
virgin
Token virgin
Feature activation+0.000
births
Token births
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 0.514 - 1.028
CONTAINS 0.131%

for
Token for
Feature activation+0.147
the
Token the
Feature activation+0.000
further
Token further
Feature activation+0.235
development
Token development
Feature activation+0.000
of
Token of
Feature activation+1.019
effective
Token effective
Feature activation+0.846
treatments
Token treatments
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
all
Token all
Feature activation+0.207
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.109
zoo
Token zoo
Feature activation+0.298
's
Token's
Feature activation+0.768
seven
Token seven
Feature activation+0.686
tigers
Token tigers
Feature activation+0.000
and
Token and
Feature activation+0.000
eight
Token eight
Feature activation+0.000
lions
Token lions
Feature activation+0.584
were
Token were
Feature activation+1.462
"
Token"
Feature activation+0.226
The
TokenThe
Feature activation+0.015
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.439
revenue
Token revenue
Feature activation+0.346
and
Token and
Feature activation+0.582
jobs
Token jobs
Feature activation+0.067
that
Token that
Feature activation+0.142
gor
Token gor
Feature activation+0.000
illas
Tokenillas
Feature activation+0.391
generate
Token generate
Feature activation+0.000
change
Token change
Feature activation+0.000
will
Token will
Feature activation+0.000
cause
Token cause
Feature activation+0.000
the
Token the
Feature activation+0.000
disappearance
Token disappearance
Feature activation+0.000
of
Token of
Feature activation+0.556
the
Token the
Feature activation+0.427
glaciers
Token glaciers
Feature activation+0.000
in
Token in
Feature activation+0.000
Montana
Token Montana
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
killing
Token killing
Feature activation+0.000
and
Token and
Feature activation+0.000
slaughter
Token slaughter
Feature activation+0.000
of
Token of
Feature activation+0.775
the
Token the
Feature activation+0.780
animals
Token animals
Feature activation+0.814
that
Token that
Feature activation+1.650
the
Token the
Feature activation+1.036
BLM
Token BLM
Feature activation+1.731
considers
Token considers
Feature activation+2.229

INTERVAL 0.000 - 0.514
CONTAINS 99.790%

taxes
Token taxes
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
them
Token them
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Burke
Token Burke
Feature activation+0.000
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.000
destroy
Token destroy
Feature activation+0.000
H
Token H
Feature activation+0.000
anka
Tokenanka
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
advancements
Token advancements
Feature activation+0.000
in
Token in
Feature activation+0.000
cyber
Token cyber
Feature activation+0.000
technology
Token technology
Feature activation+0.000
ries
Tokenries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
1
Token 1
Feature activation+0.000
kg
Tokenkg
Feature activation+0.000
packs
Token packs
Feature activation+0.000
the
Token the
Feature activation+0.000
widespread
Token widespread
Feature activation+0.057
threats
Token threats
Feature activation+0.000
posed
Token posed
Feature activation+0.000
by
Token by
Feature activation+0.062
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
or
Token or
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Syrians
Token Syrians
Feature activation+0.000
expressed
Token expressed
Feature activation+0.000
a
Token a
Feature activation+0.000
keen
Token keen
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H11.3: (feature 651)

TOP ACTIVATIONS
MAX = 5.355

the
Token the
Feature activation+1.757
1
Token 1
Feature activation+0.764
.
Token.
Feature activation+0.220
9
Token9
Feature activation+2.732
million
Token million
Feature activation+3.083
-
Token-
Feature activation+5.355
member
Tokenmember
Feature activation+3.928
church
Token church
Feature activation+1.582
can
Token can
Feature activation+1.678
offic
Token offic
Feature activation+0.000
iate
Tokeniate
Feature activation+0.196
resigned
Token resigned
Feature activation+0.000
as
Token as
Feature activation+0.648
senior
Token senior
Feature activation+1.572
pastor
Token pastor
Feature activation+0.234
at
Token at
Feature activation+1.733
the
Token the
Feature activation+4.562
church
Token church
Feature activation+2.522
in
Token in
Feature activation+0.242
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.873
Ċ
TokenĊ
Feature activation+0.000
others
Token others
Feature activation+1.315
through
Token through
Feature activation+2.044
her
Token her
Feature activation+2.054
church
Token church
Feature activation+1.263
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.415
s
Tokens
Feature activation+2.306
nursing
Token nursing
Feature activation+0.855
home
Token home
Feature activation+3.073
ministry
Token ministry
Feature activation+1.573
and
Token and
Feature activation+2.578
pastor
Token pastor
Feature activation+0.000
of
Token of
Feature activation+0.981
the
Token the
Feature activation+2.349
City
Token City
Feature activation+3.511
of
Token of
Feature activation+1.714
Light
Token Light
Feature activation+4.370
church
Token church
Feature activation+2.330
in
Token in
Feature activation+0.000
Donetsk
Token Donetsk
Feature activation+1.426
,
Token,
Feature activation+0.843
Ukraine
Token Ukraine
Feature activation+0.917
,
Token,
Feature activation+1.172
Scientist
Token Scientist
Feature activation+3.949
;
Token;
Feature activation+3.522
and
Token and
Feature activation+3.442
the
Token the
Feature activation+3.442
Boston
Token Boston
Feature activation+4.358
Chinese
Token Chinese
Feature activation+4.007
Evangel
Token Evangel
Feature activation+0.161
ical
Tokenical
Feature activation+2.161
,
Token,
Feature activation+1.909
say
Token say
Feature activation+1.295
home
Token home
Feature activation+3.073
ministry
Token ministry
Feature activation+1.573
and
Token and
Feature activation+2.578
also
Token also
Feature activation+2.780
the
Token the
Feature activation+2.046
monthly
Token monthly
Feature activation+4.338
dinners
Token dinners
Feature activation+2.731
given
Token given
Feature activation+2.289
by
Token by
Feature activation+1.857
her
Token her
Feature activation+2.424
church
Token church
Feature activation+3.009
reass
Token reass
Feature activation+0.000
igned
Tokenigned
Feature activation+0.000
in
Token in
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
from
Token from
Feature activation+1.589
Mississippi
Token Mississippi
Feature activation+4.221
to
Token to
Feature activation+0.957
a
Token a
Feature activation+2.067
small
Token small
Feature activation+2.129
church
Token church
Feature activation+1.750
in
Token in
Feature activation+0.000
ivity
Tokenivity
Feature activation+0.414
of
Token of
Feature activation+0.293
the
Token the
Feature activation+0.678
Blessed
Token Blessed
Feature activation+0.154
Virgin
Token Virgin
Feature activation+0.990
Mary
Token Mary
Feature activation+4.178
Parish
Token Parish
Feature activation+3.363
at
Token at
Feature activation+0.089
219
Token 219
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
they
Token they
Feature activation+0.780
mean
Token mean
Feature activation+3.481
more
Token more
Feature activation+3.229
than
Token than
Feature activation+3.374
m
Token m
Feature activation+0.000
umbling
Tokenumbling
Feature activation+4.158
a
Token a
Feature activation+3.028
Hail
Token Hail
Feature activation+0.000
Mary
Token Mary
Feature activation+3.170
before
Token before
Feature activation+2.453
voting
Token voting
Feature activation+0.359
Christ
Token Christ
Feature activation+0.000
of
Token of
Feature activation+0.000
Latter
Token Latter
Feature activation+0.108
-
Token-
Feature activation+0.800
day
Tokenday
Feature activation+0.123
Saints
Token Saints
Feature activation+4.143
has
Token has
Feature activation+1.721
sat
Token sat
Feature activation+0.068
next
Token next
Feature activation+1.517
door
Token door
Feature activation+0.522
to
Token to
Feature activation+0.769
sermon
Token sermon
Feature activation+0.000
by
Token by
Feature activation+0.174
the
Token the
Feature activation+0.810
Bishop
Token Bishop
Feature activation+1.551
of
Token of
Feature activation+0.000
London
Token London
Feature activation+4.028
,
Token,
Feature activation+2.171
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.336
no
Token no
Feature activation+0.000
great
Token great
Feature activation+0.126
at
Token at
Feature activation+0.821
St
Token St
Feature activation+0.000
Charles
Token Charles
Feature activation+3.298
Bor
Token Bor
Feature activation+0.000
rome
Tokenrome
Feature activation+0.000
o
Tokeno
Feature activation+4.008
sem
Token sem
Feature activation+0.000
inary
Tokeninary
Feature activation+1.832
.
Token.
Feature activation+0.390
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.305
Scientist
Token Scientist
Feature activation+3.949
;
Token;
Feature activation+3.522
and
Token and
Feature activation+3.442
the
Token the
Feature activation+3.442
Boston
Token Boston
Feature activation+4.358
Chinese
Token Chinese
Feature activation+4.007
Evangel
Token Evangel
Feature activation+0.161
ical
Tokenical
Feature activation+2.161
,
Token,
Feature activation+1.909
say
Token say
Feature activation+1.295
officials
Token officials
Feature activation+0.000
Second
Token Second
Feature activation+0.601
Church
Token Church
Feature activation+2.347
of
Token of
Feature activation+0.419
Christ
Token Christ
Feature activation+3.888
,
Token,
Feature activation+1.172
Scientist
Token Scientist
Feature activation+3.949
;
Token;
Feature activation+3.522
and
Token and
Feature activation+3.442
the
Token the
Feature activation+3.442
Boston
Token Boston
Feature activation+4.358
Chinese
Token Chinese
Feature activation+4.007
1
Token 1
Feature activation+0.764
.
Token.
Feature activation+0.220
9
Token9
Feature activation+2.732
million
Token million
Feature activation+3.083
-
Token-
Feature activation+5.355
member
Tokenmember
Feature activation+3.928
church
Token church
Feature activation+1.582
can
Token can
Feature activation+1.678
offic
Token offic
Feature activation+0.000
iate
Tokeniate
Feature activation+0.196
blessings
Token blessings
Feature activation+0.695
;
Token;
Feature activation+3.061
the
Token the
Feature activation+3.210
Second
Token Second
Feature activation+0.601
Church
Token Church
Feature activation+2.347
of
Token of
Feature activation+0.419
Christ
Token Christ
Feature activation+3.888
,
Token,
Feature activation+1.172
Scientist
Token Scientist
Feature activation+3.949
;
Token;
Feature activation+3.522
and
Token and
Feature activation+3.442
the
Token the
Feature activation+3.442
Our
Token Our
Feature activation+0.000
Lady
Token Lady
Feature activation+0.571
of
Token of
Feature activation+0.000
L
Token L
Feature activation+0.000
our
Tokenour
Feature activation+0.000
des
Tokendes
Feature activation+3.831
Catholic
Token Catholic
Feature activation+2.580
Church
Token Church
Feature activation+2.438
on
Token on
Feature activation+1.277
Sunday
Token Sunday
Feature activation+2.355
morning
Token morning
Feature activation+2.765
Americans
Token Americans
Feature activation+1.507
never
Token never
Feature activation+0.836
attending
Token attending
Feature activation+2.201
church
Token church
Feature activation+0.000
or
Token or
Feature activation+1.821
other
Token other
Feature activation+3.804
worship
Token worship
Feature activation+1.886
services
Token services
Feature activation+0.395
each
Token each
Feature activation+2.139
weekend
Token weekend
Feature activation+0.000
is
Token is
Feature activation+0.000
be
Token be
Feature activation+0.000
eline
Tokeneline
Feature activation+0.044
from
Token from
Feature activation+1.978
Mass
Token Mass
Feature activation+0.000
at
Token at
Feature activation+2.224
the
Token the
Feature activation+3.799
Bethesda
Token Bethesda
Feature activation+3.706
church
Token church
Feature activation+2.058
to
Token to
Feature activation+2.240
the
Token the
Feature activation+3.430
gym
Token gym
Feature activation+0.919
eline
Tokeneline
Feature activation+0.044
from
Token from
Feature activation+1.978
Mass
Token Mass
Feature activation+0.000
at
Token at
Feature activation+2.224
the
Token the
Feature activation+3.799
Bethesda
Token Bethesda
Feature activation+3.706
church
Token church
Feature activation+2.058
to
Token to
Feature activation+2.240
the
Token the
Feature activation+3.430
gym
Token gym
Feature activation+0.919
.
Token.
Feature activation+1.075

Top DFA by src position
MAX = 4.262

in
Token in
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.507
Top resid features:
1
Token 1
Feature activation+0.126
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
9
Token9
Feature activation+0.155
Top resid features:
million
Token million
Feature activation+4.262
Top resid features:
-
Token-
Feature activation+0.192
Top resid features:
member
Tokenmember
Feature activation+0.000
Top resid features:
church
Token church
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
offic
Token offic
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation+0.059
Top resid features:
Coy
Token Coy
Feature activation+0.002
Top resid features:
resigned
Token resigned
Feature activation+0.013
Top resid features:
as
Token as
Feature activation+0.084
Top resid features:
senior
Token senior
Feature activation+0.061
Top resid features:
pastor
Token pastor
Feature activation+2.568
Top resid features:
at
Token at
Feature activation+2.448
Top resid features:
the
Token the
Feature activation+0.361
Top resid features:
church
Token church
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2014
Token 2014
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
serving
Token serving
Feature activation+0.150
Top resid features:
others
Token others
Feature activation+0.113
Top resid features:
through
Token through
Feature activation+0.627
Top resid features:
her
Token her
Feature activation+0.681
Top resid features:
church
Token church
Feature activation+2.109
Top resid features:
âĢ
TokenâĢ
Feature activation+0.058
Top resid features:
Ļ
TokenĻ
Feature activation+0.239
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
nursing
Token nursing
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
onom
Tokenonom
Feature activation-0.015
Top resid features:
aren
Tokenaren
Feature activation+0.021
Top resid features:
ko
Tokenko
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.257
Top resid features:
pastor
Token pastor
Feature activation+0.778
Top resid features:
of
Token of
Feature activation+1.534
Top resid features:
the
Token the
Feature activation+1.187
Top resid features:
City
Token City
Feature activation+0.130
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
Light
Token Light
Feature activation+0.255
Top resid features:
church
Token church
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.295
Top resid features:
Catholic
Token Catholic
Feature activation+0.099
Top resid features:
Char
Token Char
Feature activation+0.075
Top resid features:
ities
Tokenities
Feature activation+0.115
Top resid features:
;
Token;
Feature activation+0.236
Top resid features:
the
Token the
Feature activation+0.450
Top resid features:
Islamic
Token Islamic
Feature activation+0.095
Top resid features:
Society
Token Society
Feature activation+0.124
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
Boston
Token Boston
Feature activation+0.028
Top resid features:
;
Token;
Feature activation+0.187
Top resid features:
in
Token in
Feature activation+0.418
Top resid features:
ministry
Token ministry
Feature activation+0.216
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
serving
Token serving
Feature activation+0.250
Top resid features:
others
Token others
Feature activation+0.075
Top resid features:
through
Token through
Feature activation+1.088
Top resid features:
her
Token her
Feature activation+0.356
Top resid features:
church
Token church
Feature activation+0.402
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.072
Top resid features:
s
Tokens
Feature activation+0.227
Top resid features:
was
Token was
Feature activation+0.064
Top resid features:
reass
Token reass
Feature activation+0.010
Top resid features:
igned
Tokenigned
Feature activation+0.089
Top resid features:
in
Token in
Feature activation+0.050
Top resid features:
2003
Token 2003
Feature activation+0.046
Top resid features:
from
Token from
Feature activation+4.156
Top resid features:
Mississippi
Token Mississippi
Feature activation+0.100
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
church
Token church
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.082
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
-
Token-
Feature activation+0.059
Top resid features:
Nat
Token Nat
Feature activation+0.054
Top resid features:
ivity
Tokenivity
Feature activation+1.956
Top resid features:
of
Token of
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
Blessed
Token Blessed
Feature activation+0.229
Top resid features:
Virgin
Token Virgin
Feature activation+0.429
Top resid features:
Mary
Token Mary
Feature activation+1.717
Top resid features:
that
Token that
Feature activation+0.153
Top resid features:
when
Token when
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
bishops
Token bishops
Feature activation+0.217
Top resid features:
urge
Token urge
Feature activation+0.066
Top resid features:
prayer
Token prayer
Feature activation+0.764
Top resid features:
,
Token,
Feature activation+0.400
Top resid features:
they
Token they
Feature activation+0.041
Top resid features:
mean
Token mean
Feature activation+0.385
Top resid features:
more
Token more
Feature activation+0.169
Top resid features:
than
Token than
Feature activation+0.710
Top resid features:
ue
Tokenue
Feature activation+0.004
Top resid features:
St
Token St
Feature activation+0.031
Top resid features:
ake
Tokenake
Feature activation+0.354
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.062
Top resid features:
Church
Token Church
Feature activation+2.319
Top resid features:
of
Token of
Feature activation+0.071
Top resid features:
Jesus
Token Jesus
Feature activation+0.292
Top resid features:
Christ
Token Christ
Feature activation+0.080
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Latter
Token Latter
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
listen
Token listen
Feature activation+0.117
Top resid features:
to
Token to
Feature activation+0.132
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
sermon
Token sermon
Feature activation+3.601
Top resid features:
by
Token by
Feature activation+0.484
Top resid features:
the
Token the
Feature activation+0.115
Top resid features:
Bishop
Token Bishop
Feature activation+0.506
Top resid features:
of
Token of
Feature activation+0.064
Top resid features:
London
Token London
Feature activation+0.054
Top resid features:
speaking
Token speaking
Feature activation+0.054
Top resid features:
to
Token to
Feature activation+0.098
Top resid features:
a
Token a
Feature activation+0.126
Top resid features:
gathering
Token gathering
Feature activation+0.206
Top resid features:
of
Token of
Feature activation+0.081
Top resid features:
priests
Token priests
Feature activation+1.323
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
bishops
Token bishops
Feature activation+0.438
Top resid features:
at
Token at
Feature activation+0.818
Top resid features:
St
Token St
Feature activation+0.392
Top resid features:
Charles
Token Charles
Feature activation+0.832
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
Boston
Token Boston
Feature activation+0.097
Top resid features:
;
Token;
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.148
Top resid features:
Second
Token Second
Feature activation+0.094
Top resid features:
Church
Token Church
Feature activation+0.540
Top resid features:
of
Token of
Feature activation+0.046
Top resid features:
Christ
Token Christ
Feature activation+0.218
Top resid features:
,
Token,
Feature activation+0.107
Top resid features:
Scientist
Token Scientist
Feature activation+0.160
Top resid features:
;
Token;
Feature activation+0.108
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
Boston
Token Boston
Feature activation+0.023
Top resid features:
;
Token;
Feature activation+0.269
Top resid features:
the
Token the
Feature activation+0.136
Top resid features:
Second
Token Second
Feature activation+0.061
Top resid features:
Church
Token Church
Feature activation+0.619
Top resid features:
of
Token of
Feature activation+0.087
Top resid features:
Christ
Token Christ
Feature activation+0.229
Top resid features:
,
Token,
Feature activation+0.325
Top resid features:
Scientist
Token Scientist
Feature activation+0.203
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Indianapolis
Token Indianapolis
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
means
Token means
Feature activation+0.066
Top resid features:
that
Token that
Feature activation+0.266
Top resid features:
priests
Token priests
Feature activation+0.530
Top resid features:
in
Token in
Feature activation+0.803
Top resid features:
the
Token the
Feature activation+0.442
Top resid features:
1
Token 1
Feature activation+0.056
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
9
Token9
Feature activation+0.035
Top resid features:
million
Token million
Feature activation+0.230
Top resid features:
of
Token of
Feature activation+0.037
Top resid features:
Boston
Token Boston
Feature activation+0.041
Top resid features:
;
Token;
Feature activation+0.178
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
Second
Token Second
Feature activation+0.168
Top resid features:
Church
Token Church
Feature activation+0.693
Top resid features:
of
Token of
Feature activation+0.053
Top resid features:
Christ
Token Christ
Feature activation+0.275
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Scientist
Token Scientist
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Commun
Token Commun
Feature activation+0.056
Top resid features:
ion
Tokenion
Feature activation+1.272
Top resid features:
line
Token line
Feature activation+0.250
Top resid features:
at
Token at
Feature activation+0.523
Top resid features:
Our
Token Our
Feature activation+0.203
Top resid features:
Lady
Token Lady
Feature activation+2.336
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
L
Token L
Feature activation+0.013
Top resid features:
our
Tokenour
Feature activation+0.003
Top resid features:
des
Tokendes
Feature activation+0.174
Top resid features:
Catholic
Token Catholic
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.071
Top resid features:
Americans
Token Americans
Feature activation+0.036
Top resid features:
never
Token never
Feature activation+0.031
Top resid features:
attending
Token attending
Feature activation+1.103
Top resid features:
church
Token church
Feature activation+1.380
Top resid features:
or
Token or
Feature activation+0.224
Top resid features:
other
Token other
Feature activation+0.147
Top resid features:
worship
Token worship
Feature activation+0.000
Top resid features:
services
Token services
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
eline
Tokeneline
Feature activation-0.012
Top resid features:
from
Token from
Feature activation+0.575
Top resid features:
Mass
Token Mass
Feature activation+0.659
Top resid features:
at
Token at
Feature activation+1.080
Top resid features:
the
Token the
Feature activation+0.282
Top resid features:
Bethesda
Token Bethesda
Feature activation+0.000
Top resid features:
church
Token church
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:
a
Token a
Feature activation+0.029
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
eline
Tokeneline
Feature activation-0.005
Top resid features:
from
Token from
Feature activation+0.490
Top resid features:
Mass
Token Mass
Feature activation+0.786
Top resid features:
at
Token at
Feature activation+1.472
Top resid features:
the
Token the
Feature activation+1.022
Top resid features:
Bethesda
Token Bethesda
Feature activation+0.097
Top resid features:
church
Token church
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: 0.09

Head 1: 0.09

Head 2: 0.06

Head 3: 0.33

Head 4: 0.05

Head 5: 0.04

Head 6: 0.04

Head 7: 0.04

Head 8: 0.09

Head 9: 0.04

Head 10: 0.06

Head 11: 0.07

Positive logits

church8.29

pastor8.15

congregation8.02

pastors7.86

parish7.64

Episcopal7.59

Pastor7.57

Church7.54

bapt7.47

prayer7.32

sermon7.31

churches7.30

baptized7.27

chapel7.21

Church7.17

Bapt7.16

church7.13

Baptist7.13

Churches7.08

bishop7.05

Negative logits

Xiaomi-3.26

Poké-3.04

Agent-3.00

netflix-2.97

assetsadobe-2.92

droid-2.89

Metroid-2.86

Gadget-2.84

Greenwald-2.80

TF-2.79

Nit-2.77

imet-2.74

overe-2.72

daq-2.71

Sabres-2.71

leneck-2.60

Blumenthal-2.59

artificially-2.59

Hitman-2.56

HIT-2.53

INTERVAL 4.820 - 5.355
CONTAINS 0.000%

the
Token the
Feature activation+1.757
1
Token 1
Feature activation+0.764
.
Token.
Feature activation+0.220
9
Token9
Feature activation+2.732
million
Token million
Feature activation+3.083
-
Token-
Feature activation+5.355
member
Tokenmember
Feature activation+3.928
church
Token church
Feature activation+1.582
can
Token can
Feature activation+1.678
offic
Token offic
Feature activation+0.000
iate
Tokeniate
Feature activation+0.196

INTERVAL 4.284 - 4.820
CONTAINS 0.001%

,
Token,
Feature activation+1.172
Scientist
Token Scientist
Feature activation+3.949
;
Token;
Feature activation+3.522
and
Token and
Feature activation+3.442
the
Token the
Feature activation+3.442
Boston
Token Boston
Feature activation+4.358
Chinese
Token Chinese
Feature activation+4.007
Evangel
Token Evangel
Feature activation+0.161
ical
Tokenical
Feature activation+2.161
,
Token,
Feature activation+1.909
say
Token say
Feature activation+1.295
others
Token others
Feature activation+1.315
through
Token through
Feature activation+2.044
her
Token her
Feature activation+2.054
church
Token church
Feature activation+1.263
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.415
s
Tokens
Feature activation+2.306
nursing
Token nursing
Feature activation+0.855
home
Token home
Feature activation+3.073
ministry
Token ministry
Feature activation+1.573
and
Token and
Feature activation+2.578
home
Token home
Feature activation+3.073
ministry
Token ministry
Feature activation+1.573
and
Token and
Feature activation+2.578
also
Token also
Feature activation+2.780
the
Token the
Feature activation+2.046
monthly
Token monthly
Feature activation+4.338
dinners
Token dinners
Feature activation+2.731
given
Token given
Feature activation+2.289
by
Token by
Feature activation+1.857
her
Token her
Feature activation+2.424
church
Token church
Feature activation+3.009
pastor
Token pastor
Feature activation+0.000
of
Token of
Feature activation+0.981
the
Token the
Feature activation+2.349
City
Token City
Feature activation+3.511
of
Token of
Feature activation+1.714
Light
Token Light
Feature activation+4.370
church
Token church
Feature activation+2.330
in
Token in
Feature activation+0.000
Donetsk
Token Donetsk
Feature activation+1.426
,
Token,
Feature activation+0.843
Ukraine
Token Ukraine
Feature activation+0.917
resigned
Token resigned
Feature activation+0.000
as
Token as
Feature activation+0.648
senior
Token senior
Feature activation+1.572
pastor
Token pastor
Feature activation+0.234
at
Token at
Feature activation+1.733
the
Token the
Feature activation+4.562
church
Token church
Feature activation+2.522
in
Token in
Feature activation+0.242
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.873
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.749 - 4.284
CONTAINS 0.001%

sermon
Token sermon
Feature activation+0.000
by
Token by
Feature activation+0.174
the
Token the
Feature activation+0.810
Bishop
Token Bishop
Feature activation+1.551
of
Token of
Feature activation+0.000
London
Token London
Feature activation+4.028
,
Token,
Feature activation+2.171
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.336
no
Token no
Feature activation+0.000
great
Token great
Feature activation+0.126
Our
Token Our
Feature activation+0.000
Lady
Token Lady
Feature activation+0.571
of
Token of
Feature activation+0.000
L
Token L
Feature activation+0.000
our
Tokenour
Feature activation+0.000
des
Tokendes
Feature activation+3.831
Catholic
Token Catholic
Feature activation+2.580
Church
Token Church
Feature activation+2.438
on
Token on
Feature activation+1.277
Sunday
Token Sunday
Feature activation+2.355
morning
Token morning
Feature activation+2.765
at
Token at
Feature activation+0.821
St
Token St
Feature activation+0.000
Charles
Token Charles
Feature activation+3.298
Bor
Token Bor
Feature activation+0.000
rome
Tokenrome
Feature activation+0.000
o
Tokeno
Feature activation+4.008
sem
Token sem
Feature activation+0.000
inary
Tokeninary
Feature activation+1.832
.
Token.
Feature activation+0.390
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.305
be
Token be
Feature activation+0.000
eline
Tokeneline
Feature activation+0.044
from
Token from
Feature activation+1.978
Mass
Token Mass
Feature activation+0.000
at
Token at
Feature activation+2.224
the
Token the
Feature activation+3.799
Bethesda
Token Bethesda
Feature activation+3.706
church
Token church
Feature activation+2.058
to
Token to
Feature activation+2.240
the
Token the
Feature activation+3.430
gym
Token gym
Feature activation+0.919
Christ
Token Christ
Feature activation+0.000
of
Token of
Feature activation+0.000
Latter
Token Latter
Feature activation+0.108
-
Token-
Feature activation+0.800
day
Tokenday
Feature activation+0.123
Saints
Token Saints
Feature activation+4.143
has
Token has
Feature activation+1.721
sat
Token sat
Feature activation+0.068
next
Token next
Feature activation+1.517
door
Token door
Feature activation+0.522
to
Token to
Feature activation+0.769

INTERVAL 3.213 - 3.749
CONTAINS 0.003%

;
Token;
Feature activation+2.097
Hope
Token Hope
Feature activation+0.743
Fellowship
Token Fellowship
Feature activation+2.570
Church
Token Church
Feature activation+0.791
;
Token;
Feature activation+2.508
Catholic
Token Catholic
Feature activation+3.668
Char
Token Char
Feature activation+0.000
ities
Tokenities
Feature activation+1.612
;
Token;
Feature activation+3.024
the
Token the
Feature activation+3.076
Islamic
Token Islamic
Feature activation+3.041
his
Token his
Feature activation+2.224
church
Token church
Feature activation+1.888
daily
Token daily
Feature activation+0.983
for
Token for
Feature activation+2.643
a
Token a
Feature activation+2.878
free
Token free
Feature activation+3.245
meal
Token meal
Feature activation+1.479
.
Token.
Feature activation+2.154
In
Token In
Feature activation+0.949
one
Token one
Feature activation+2.115
month
Token month
Feature activation+3.393
eline
Tokeneline
Feature activation+0.044
from
Token from
Feature activation+1.978
Mass
Token Mass
Feature activation+0.000
at
Token at
Feature activation+2.224
the
Token the
Feature activation+3.799
Bethesda
Token Bethesda
Feature activation+3.706
church
Token church
Feature activation+2.058
to
Token to
Feature activation+2.240
the
Token the
Feature activation+3.430
gym
Token gym
Feature activation+0.919
.
Token.
Feature activation+1.075
microscope
Token microscope
Feature activation+0.000
when
Token when
Feature activation+0.157
4
Token 4
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.959
its
Token its
Feature activation+3.485
priests
Token priests
Feature activation+0.874
were
Token were
Feature activation+0.080
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.453
abuse
Token abuse
Feature activation+0.000
;
Token;
Feature activation+3.024
the
Token the
Feature activation+3.076
Islamic
Token Islamic
Feature activation+3.041
Society
Token Society
Feature activation+2.254
of
Token of
Feature activation+0.922
Boston
Token Boston
Feature activation+3.646
;
Token;
Feature activation+3.061
the
Token the
Feature activation+3.210
Second
Token Second
Feature activation+0.601
Church
Token Church
Feature activation+2.347
of
Token of
Feature activation+0.419

INTERVAL 2.678 - 3.213
CONTAINS 0.007%

/
Token/
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
IR
TokenIR
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
X
TokenX
Feature activation+0.000
NZ
Token NZ
Feature activation+2.885
The
Token The
Feature activation+1.247
Anglic
Token Anglic
Feature activation+0.000
an
Tokenan
Feature activation+1.543
Church
Token Church
Feature activation+1.976
has
Token has
Feature activation+2.414
church
Token church
Feature activation+0.000
's
Token's
Feature activation+0.942
House
Token House
Feature activation+1.927
of
Token of
Feature activation+0.035
Dep
Token Dep
Feature activation+0.000
uties
Tokenuties
Feature activation+2.994
voted
Token voted
Feature activation+0.302
171
Token 171
Feature activation+0.581
to
Token to
Feature activation+0.000
41
Token 41
Feature activation+0.195
,
Token,
Feature activation+1.710
Church
Token Church
Feature activation+0.190
on
Token on
Feature activation+0.520
Tuesday
Token Tuesday
Feature activation+2.542
became
Token became
Feature activation+0.302
the
Token the
Feature activation+1.398
largest
Token largest
Feature activation+3.102
Christian
Token Christian
Feature activation+3.383
denomination
Token denomination
Feature activation+1.292
in
Token in
Feature activation+1.051
the
Token the
Feature activation+1.610
U
Token U
Feature activation+0.000
Church
Token Church
Feature activation+0.791
;
Token;
Feature activation+2.508
Catholic
Token Catholic
Feature activation+3.668
Char
Token Char
Feature activation+0.000
ities
Tokenities
Feature activation+1.612
;
Token;
Feature activation+3.024
the
Token the
Feature activation+3.076
Islamic
Token Islamic
Feature activation+3.041
Society
Token Society
Feature activation+2.254
of
Token of
Feature activation+0.922
Boston
Token Boston
Feature activation+3.646
in
Token in
Feature activation+0.411
one
Token one
Feature activation+1.465
month
Token month
Feature activation+0.000
.
Token.
Feature activation+2.084
He
Token He
Feature activation+0.092
says
Token says
Feature activation+2.965
hundreds
Token hundreds
Feature activation+0.617
are
Token are
Feature activation+0.710
dying
Token dying
Feature activation+0.000
of
Token of
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000

INTERVAL 2.142 - 2.678
CONTAINS 0.015%

educating
Token educating
Feature activation+1.397
our
Token our
Feature activation+1.413
cons
Token cons
Feature activation+0.000
ci
Tokenci
Feature activation+0.000
ences
Tokenences
Feature activation+0.558
.
Token.
Feature activation+2.360
âĢ
TokenâĢ
Feature activation+0.190
Ŀ
TokenĿ
Feature activation+3.007
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.969
Further
TokenFurther
Feature activation+0.490
Ċ
TokenĊ
Feature activation+0.188
Ch
TokenCh
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
ut
Tokenut
Feature activation+0.937
also
Token also
Feature activation+0.649
says
Token says
Feature activation+2.264
that
Token that
Feature activation+2.232
when
Token when
Feature activation+2.164
the
Token the
Feature activation+1.821
bishops
Token bishops
Feature activation+0.261
urge
Token urge
Feature activation+2.283
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.901
evangelical
Token evangelical
Feature activation+2.274
Lutheran
Token Lutheran
Feature activation+3.008
church
Token church
Feature activation+0.764
who
Token who
Feature activation+0.399
was
Token was
Feature activation+0.159
fired
Token fired
Feature activation+0.000
rightly
Token rightly
Feature activation+0.000
ordering
Token ordering
Feature activation+1.297
the
Token the
Feature activation+1.447
factors
Token factors
Feature activation+0.761
that
Token that
Feature activation+0.034
guide
Token guide
Feature activation+2.409
us
Token us
Feature activation+0.044
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
yet
Token yet
Feature activation+0.551
thick
Token thick
Feature activation+1.353
margin
Token margin
Feature activation+0.000
at
Token at
Feature activation+2.522
the
Token the
Feature activation+2.894
church
Token church
Feature activation+1.106
's
Token's
Feature activation+2.155
tri
Token tri
Feature activation+0.908
ennial
Tokenennial
Feature activation+2.124
General
Token General
Feature activation+1.140
Convention
Token Convention
Feature activation+1.209
in
Token in
Feature activation+0.387

INTERVAL 1.607 - 2.142
CONTAINS 0.035%

âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.441
At
TokenAt
Feature activation+1.215
a
Token a
Feature activation+1.260
time
Token time
Feature activation+0.311
when
Token when
Feature activation+1.727
communities
Token communities
Feature activation+0.000
appear
Token appear
Feature activation+0.060
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.306
divided
Token divided
Feature activation+0.000
,
Token,
Feature activation+1.590
offering
Token offering
Feature activation+1.657
to
Token to
Feature activation+1.416
help
Token help
Feature activation+1.388
by
Token by
Feature activation+1.819
donating
Token donating
Feature activation+1.950
funds
Token funds
Feature activation+0.696
or
Token or
Feature activation+2.571
supplies
Token supplies
Feature activation+0.478
,
Token,
Feature activation+0.902
as
Token as
Feature activation+0.891
The
TokenThe
Feature activation+1.458
monumental
Token monumental
Feature activation+2.231
decision
Token decision
Feature activation+0.000
,
Token,
Feature activation+0.627
approved
Token approved
Feature activation+0.000
by
Token by
Feature activation+1.701
a
Token a
Feature activation+1.487
thick
Token thick
Feature activation+1.353
margin
Token margin
Feature activation+0.000
at
Token at
Feature activation+2.522
the
Token the
Feature activation+2.894
Ċ
TokenĊ
Feature activation+1.674
The
TokenThe
Feature activation+0.984
offic
Token offic
Feature activation+0.000
iant
Tokeniant
Feature activation+0.759
is
Token is
Feature activation+0.921
any
Token any
Feature activation+2.122
District
Token District
Feature activation+1.167
of
Token of
Feature activation+0.000
Columbia
Token Columbia
Feature activation+0.672
Judge
Token Judge
Feature activation+0.430
or
Token or
Feature activation+0.590
parish
Token parish
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
ers
Tokeners
Feature activation+0.649
and
Token and
Feature activation+1.837
300
Token 300
Feature activation+2.945
seniors
Token seniors
Feature activation+1.791
who
Token who
Feature activation+1.666
come
Token come
Feature activation+1.198
to
Token to
Feature activation+2.020
his
Token his
Feature activation+2.224
church
Token church
Feature activation+1.888

INTERVAL 1.071 - 1.607
CONTAINS 0.078%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.354
This
Token This
Feature activation+0.068
is
Token is
Feature activation+0.125
troubling
Token troubling
Feature activation+0.000
because
Token because
Feature activation+1.486
to
Token to
Feature activation+0.841
me
Token me
Feature activation+2.164
it
Token it
Feature activation+0.000
shows
Token shows
Feature activation+1.349
how
Token how
Feature activation+1.157
pastor
Token pastor
Feature activation+0.000
and
Token and
Feature activation+1.083
father
Token father
Feature activation+0.000
of
Token of
Feature activation+0.501
four
Token four
Feature activation+1.844
,
Token,
Feature activation+1.250
was
Token was
Feature activation+0.690
shot
Token shot
Feature activation+0.000
and
Token and
Feature activation+0.000
killed
Token killed
Feature activation+0.000
by
Token by
Feature activation+0.000
scrambled
Token scrambled
Feature activation+0.607
and
Token and
Feature activation+0.488
got
Token got
Feature activation+0.443
access
Token access
Feature activation+0.000
to
Token to
Feature activation+1.278
a
Token a
Feature activation+1.236
back
Token back
Feature activation+0.384
room
Tokenroom
Feature activation+0.853
in
Token in
Feature activation+0.000
the
Token the
Feature activation+1.265
Highland
Token Highland
Feature activation+0.408
will
Token will
Feature activation+0.000
divide
Token divide
Feature activation+0.153
,"
Token,"
Feature activation+1.658
he
Token he
Feature activation+0.000
predicted
Token predicted
Feature activation+0.466
.
Token.
Feature activation+1.153
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.751
Sus
TokenSus
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Le
Token Le
Feature activation+0.000
Family
Token Family
Feature activation+1.226
for
Token for
Feature activation+1.008
the
Token the
Feature activation+1.914
New
Token New
Feature activation+1.348
Evangel
Token Evangel
Feature activation+0.000
ization
Tokenization
Feature activation+1.227
:
Token:
Feature activation+0.387
Ċ
TokenĊ
Feature activation+0.416
Ċ
TokenĊ
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 0.536 - 1.071
CONTAINS 0.166%

spl
Token spl
Feature activation+0.000
o
Tokeno
Feature activation+0.000
og
Tokenog
Feature activation+0.000
ing
Tokening
Feature activation+0.000
on
Token on
Feature activation+0.123
the
Token the
Feature activation+0.712
floor
Token floor
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.122
Look
Token Look
Feature activation+0.000
stein
Tokenstein
Feature activation+0.000
;
Token;
Feature activation+0.109
and
Token and
Feature activation+0.478
for
Token for
Feature activation+0.000
months
Token months
Feature activation+0.570
now
Token now
Feature activation+0.502
,
Token,
Feature activation+0.678
the
Token the
Feature activation+0.257
H
Token H
Feature activation+0.000
ared
Tokenared
Feature activation+0.000
an
Token an
Feature activation+0.000
apology
Token apology
Feature activation+0.000
for
Token for
Feature activation+0.038
the
Token the
Feature activation+0.150
Catholic
Token Catholic
Feature activation+0.307
church
Token church
Feature activation+0.574
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.664
s
Tokens
Feature activation+2.126
inadequate
Token inadequate
Feature activation+2.048
response
Token response
Feature activation+0.000
Church
Token Church
Feature activation+0.000
Key
TokenKey
Feature activation+1.199
near
Token near
Feature activation+0.359
Logan
Token Logan
Feature activation+0.000
Circle
Token Circle
Feature activation+0.767
to
Token to
Feature activation+0.642
down
Token down
Feature activation+0.235
a
Token a
Feature activation+0.900
few
Token few
Feature activation+0.636
drafts
Token drafts
Feature activation+0.310
after
Token after
Feature activation+1.260
predictable
Token predictable
Feature activation+0.000
answer
Token answer
Feature activation+0.000
that
Token that
Feature activation+0.434
she
Token she
Feature activation+0.172
gave
Token gave
Feature activation+0.026
was
Token was
Feature activation+0.878
that
Token that
Feature activation+0.338
she
Token she
Feature activation+0.734
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
just
Tokenjust
Feature activation+0.348

INTERVAL 0.000 - 0.536
CONTAINS 99.695%

volcanic
Token volcanic
Feature activation+0.000
activity
Token activity
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
location
Token location
Feature activation+0.000
is
Token is
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
for
Token for
Feature activation+0.000
predicting
Token predicting
Feature activation+0.000
future
Token future
Feature activation+0.000
we
Token we
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
g
Tokeng
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.000
Unix
Token Unix
Feature activation+0.000
tools
Token tools
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
there
Token there
Feature activation+0.000
and
Token and
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
...
Token...
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
voic
Token voic
Feature activation+0.000
Bastard
Token Bastard
Feature activation+0.000
works
Token works
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Power
Token Power
Feature activation+0.000
crew
Token crew
Feature activation+0.000
during
Token during
Feature activation+0.000
setup
Token setup
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
process
Token process
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
BART
Token BART
Feature activation+0.000
spokesman
Token spokesman
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