INDEX
Explanations
the name "Khi" in various contexts
the mention of a specific name or individual
New Auto-Interp
Negative Logits
lain
-0.81
swick
-0.77
ividual
-0.77
nesday
-0.72
mented
-0.72
ktop
-0.71
ication
-0.71
tle
-0.68
detail
-0.68
inelli
-0.67
POSITIVE LOGITS
pper
0.98
yy
0.93
ya
0.93
kson
0.91
yah
0.91
emi
0.89
0.86
ploma
0.84
pping
0.83
Pradesh
0.81
Activations Density 0.023%