INDEX

Explanations

own noun

The neuron fires on the main topic noun of a sentence—that is, it picks out the central concept or subject term (e.g. “bathroom,” “class,” “database,” “audio,” etc.).

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

my

-1.62

 voetballer

-1.54

its

-1.52

-1.40

-1.35

 altro

-1.34

はいけない

-1.34

-1.31

 last

-1.31

-1.30

POSITIVE LOGITS

 kategorii

1.33

 Tycoon

1.32

own

1.32

lierung

1.30

 negru

1.30

 voluntad

1.29

一二

1.29

système

1.27

立

1.25

vernight

1.24

Activations Density 0.051%