INDEX

Explanations

configuration options and labels

The neuron fires on dotted or namespaced identifier strings (like configuration keys or translation/message keys) composed of multiple parts separated by periods.

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

 there

-1.91

at

-1.50

 There

-1.45

who

-1.38

 никогда

-1.35

 during

-1.34

↵

-1.34

-------

-1.23

"",

-1.22

on

-1.20

POSITIVE LOGITS

 minOccurs

1.52

鵙

1.45

឵

1.44

ほとんど

1.36

こいつ

1.34

</

1.34

rifugal

1.33

 vieilles

1.30

 règles

1.29

Utiliz

1.29

Activations Density 0.025%