INDEX
Explanations
occurrences of function calls and data structure initialization in coding contexts
New Auto-Interp
Negative Logits
"
-0.83
"
-0.75
"[
-0.67
"[
-0.66
Wagner
-0.65
("-0.63
$
-0.62
"<
-0.60
''
-0.59
</b>
-0.59
POSITIVE LOGITS
`,
1.22
}`,
1.22
}`).
1.18
}`)
1.12
itſelf
1.10
>`;
1.08
`;
1.08
myſelf
1.06
ſelf
1.02
""".
1.02
Activations Density 0.169%