INDEX

Explanations

ratio and division

This neuron detects slash (“/”) characters used in ratio or chemical/formula expressions (e.g., “Na/…”, “O/L”, “L/D”).

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

 المقبل

-1.96

and

-1.63

 they

-1.59

 mówią

-1.58

 kiedyś

-1.58

-1.50

see

-1.45

夙

-1.42

 after

-1.40

 AFTER

-1.40

POSITIVE LOGITS

檍

1.77

ydın

1.63

夘

1.59

嵓

1.58

dij

1.56

ਗ਼

1.56

Ouverture

1.54

 dini

1.53

 イラストレーション

1.53

Buat

1.52

Activations Density 0.056%