INDEX

Explanations

python function definitions and decorators

This neuron detects Python source code snippets (e.g., “.py” file references, import statements, decorators, async/await, function definitions, library/class names).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ステン

-1.55

 CHAPITRE

-1.45

虓

-1.41

嘁

-1.38

 Informações

-1.38

 beſt

-1.36

 Início

-1.36

륭

-1.35

 purpoſe

-1.32

 inond

-1.32

POSITIVE LOGITS

any

1.89

1.61

 before

1.59

.”

1.44

((

1.42

1.40

'].

1.39

 goes

1.38

 epitom

1.36

1.35

Activations Density 0.016%