INDEX

Explanations

code syntax elements

The neuron detects numeric literals (both integers and floats) in code.

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

-1.82

It

-1.58

梅雨

-1.48

This

-1.45

久しぶりの

-1.43

 朝食

-1.38

為什麼

-1.33

 ángel

-1.32

 questões

-1.30

POSITIVE LOGITS

 abiertas

1.69

 Øst

1.52

 już

1.44

 Cach

1.43

遑

1.42

'}}

1.41

 Sør

1.38

'}}>

1.38

からず

1.37

{?>

1.35

Activations Density 0.009%