INDEX
Explanations
occurrences of the letter "y" in various contexts
New Auto-Interp
Negative Logits
raiſ
-0.78
\\
-0.77
himſelf
-0.76
ADRID
-0.76
/');
-0.75
ICAGO
-0.75
\\
-0.73
])));
-0.71
%";
-0.71
ſee
-0.71
POSITIVE LOGITS
y
1.78
Y
1.58
Y
1.30
y
1.26
getY
1.10
getY
1.09
x
0.94
Ys
0.93
yPos
0.89
setY
0.88
Activations Density 0.114%