INDEX
Explanations
words related to health and medical conditions
New Auto-Interp
Negative Logits
#+#
-0.64
caoutchouc
-0.57
aryti
-0.56
Samuels
-0.55
yadh
-0.54
geschlossen
-0.54
Ế
-0.53
culturale
-0.52
GraphicsUnit
-0.51
encre
-0.51
POSITIVE LOGITS
airy
0.82
lightness
0.74
breezy
0.69
BeginInit
0.68
defaultstate
0.63
frivol
0.59
verano
0.58
summer
0.58
thin
0.57
Thin
0.57
Activations Density 0.670%