INDEX
Explanations
elements that represent numerical data and associated metadata
New Auto-Interp
Negative Logits
aku
-0.15
пÑĢеÑģÑĤ
-0.15
nucle
-0.15
Vaughan
-0.14
äch
-0.14
GIN
-0.13
DEX
-0.13
ako
-0.13
наб
-0.13
old
-0.13
POSITIVE LOGITS
conde
0.15
unga
0.14
Forg
0.14
borderline
0.14
ãģĦãģĨ
0.14
rating
0.14
Stuart
0.13
°E
0.13
Dlg
0.13
.Tick
0.12
Activations Density 0.043%