INDEX
Explanations
color codes in various formats
New Auto-Interp
Negative Logits
"])
-1.13
()]
-1.08
Baillargeon
-1.04
propOrder
-1.02
ویکیپدی
-0.99
!")
-0.97
AutoScale
-0.97
()]);
-0.95
"]
-0.94
"]);
-0.91
POSITIVE LOGITS
'#
0.98
:'#
0.94
="#
0.93
='#
0.83
"#
0.81
('#0.80
'#
0.78
"#
0.77
:"#
0.75
','#
0.71
Activations Density 0.018%