INDEX
Explanations
instances where things are being described as having certain attributes
specific symbols or character sequences that appear frequently in certain contexts
New Auto-Interp
Negative Logits
guiName
-0.75
Solitaire
-0.69
scattering
-0.67
Waves
-0.64
ACTIONS
-0.64
etheless
-0.63
DRAG
-0.62
Marshal
-0.62
Roc
-0.62
theless
-0.61
POSITIVE LOGITS
*)
1.49
>)
1.44
.).
1.43
?).
1.42
!).
1.41
!)
1.40
).
1.38
?)
1.36
)."
1.31
.)
1.29
Activations Density 0.107%