INDEX

Explanations

@ annotations and code elements

This neuron detects programming‐language function or method declarations (e.g. the “void” return type) and associated annotation markers (“@…”).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-1.55

and

-1.52

 הוא

-1.45

是

-1.40

也在

-1.40

 он

-1.39

は

-1.37

也

-1.36

 Songtext

-1.36

から

-1.34

POSITIVE LOGITS

 היי

1.57

いっ

1.55

providedIn

1.55

焄

1.53

荭

1.53

モバイル

1.52

ﾎ

1.52

 pandémie

1.52

ícias

1.48

太多的

1.48

Activations Density 0.001%