INDEX

Explanations

into table, inplace execution

This neuron detects numeric literal tokens (especially floating‐point numbers) in code or data.

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

-1.83

</em>

-1.76

Something

-1.46

↵

-1.39

उ

-1.38

 lika

-1.30

厹

-1.27

Does

-1.25

typically

-1.23

摃

-1.23

POSITIVE LOGITS

1.64

 zmieni

1.46

the

1.46

 stratég

1.45

 uiteindelijk

1.38

 disfraz

1.34

 baterie

1.31

питан

1.30

 băr

1.30

 szczeg

1.29

Activations Density 0.019%