INDEX
Explanations
numerical comparisons and values
New Auto-Interp
Negative Logits
3
-0.61
0
-0.61
7
-0.57
8
-0.56
twimg
-0.56
9
-0.56
5
-0.55
6
-0.54
2
-0.53
1
-0.53
POSITIVE LOGITS
PreferredItem
0.94
Roskov
0.78
utafitiHapana
0.76
Tembelea
0.72
CURIAM
0.68
windowFixed
0.67
sidemargin
0.67
SpringBootTest
0.65
Enlaces
0.65
HtmlAttribute
0.64
Activations Density 0.301%