INDEX

Explanations

code endpoints and parameters

This neuron identifies numeric literals—tokens composed of digits (optionally with decimals)—in code, queries, and markup.

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

话音

-1.68

꜆

-1.66

 betrek

-1.59

 samenwerking

-1.59

 ""));

-1.55

ACIONAL

-1.52

in

-1.48

ȶ

-1.48

-1.46

ekš

-1.46

POSITIVE LOGITS

</h2>

1.73

</b>

1.60

 dessas

1.59

1.53

1.50

1.44

以免

1.41

苼

1.39

 spezi

1.39

Activations Density 0.003%