INDEX

Explanations

programming code snippets

This neuron detects statement terminators, i.e. semicolons at the ends of lines.

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

of

-1.88



-1.48

 парке

-1.48

Etc

-1.41

 .........

-1.36

etc

-1.34

reszcie

-1.32

 Sociale

-1.30

 ........

-1.29

这时候

-1.26

POSITIVE LOGITS

one

2.02

 because

1.69

 about

1.56

and

1.52

its

1.39

 apto

1.38

as

1.38

 would

1.36

 four

1.36

 bebes

1.34

Activations Density 0.006%