INDEX
Explanations
references to the name "Rub" with varying levels of relevance
mentions of the word "rub."
New Auto-Interp
Negative Logits
Span
-0.67
GDDR
-0.63
orthy
-0.63
Hurricanes
-0.61
ufact
-0.60
embr
-0.60
Scots
-0.59
HERO
-0.58
velength
-0.57
plays
-0.57
POSITIVE LOGITS
bish
1.43
bing
1.27
bery
1.26
instein
1.23
idium
1.12
bers
1.10
bles
1.09
rics
1.08
elbows
1.06
ric
1.00
Activations Density 0.022%