INDEX
Explanations
phrases indicating significant features or elements
New Auto-Interp
Negative Logits
ſelf
-0.85
Jefus
-0.85
Efq
-0.77
ſche
-0.75
purpoſe
-0.75
Majefty
-0.74
ſta
-0.73
Conſ
-0.69
beſt
-0.69
poffe
-0.68
POSITIVE LOGITS
orm
0.59
MotionEvent
0.57
reportWebVitals
0.53
BrowserModule
0.53
ürd
0.50
bit
0.50
ork
0.49
Bergman
0.48
.}
0.48
utan
0.48
Activations Density 0.085%