INDEX

Explanations

Photo, He, Serial, <?

The main thing this neuron does is detect long runs of hyphens or divider lines (as used in ASCII-style tables or charts).

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

-1.63

 instead

-1.39

 those

-1.35

Those

-1.35

or

-1.27

if

-1.26

-1.24

but

-1.24

 такими

-1.23

//

-1.23

POSITIVE LOGITS

炻

1.84

 dégust

1.73

 méda

1.68

 célè

1.63

 péro

1.59

 mungkin

1.56

 resalt

1.53

 lamenta

1.52

땃

1.50

 demostr

1.48

Activations Density 0.022%