INDEX
Explanations
instances of the date "March 9"
New Auto-Interp
Negative Logits
munt
-0.77
Tugend
-0.72
pidou
-0.65
gout
-0.61
Hadley
-0.60
Hidalgo
-0.59
HINT
-0.59
munt
-0.59
"*
-0.59
yi
-0.59
POSITIVE LOGITS
Mar
1.98
Mar
1.86
MAR
1.81
mar
1.71
mar
1.62
MAR
1.61
Martel
1.39
Marston
1.38
Marlowe
1.37
Maru
1.37
Activations Density 0.065%