INDEX
Explanations
blocks of text or special characters commonly used in formatting or coding syntax
New Auto-Interp
Negative Logits
ais
-0.66
----------------
-0.66
-
-0.62
amb
-0.60
---------------
-0.60
legi
-0.59
Eton
-0.57
состо
-0.56
say
-0.54
b
-0.54
POSITIVE LOGITS
////////////////
1.64
################
1.41
']))
1.15
])):
1.14
}>;
1.07
"]]
1.05
})));
1.04
"])
1.03
}))
1.01
##
0.96
Activations Density 0.001%