INDEX

Explanations

service states and types

The neuron fires most strongly on code identifiers (type/enum/class names and the like), i.e. CamelCase or all-caps tokens.

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

and

-2.84

or

-1.54

 this

-1.48

為に

-1.45

 brachten

-1.42

 gedachten

-1.41

 größe

-1.38

 beberapa

-1.28

 zeggen

-1.27

早晨

-1.24

POSITIVE LOGITS

ignée

1.48

<bos>

1.47

着的

1.45

は

1.44

 мебели

1.43

骉

1.38

arschijnlijk

1.35

檻

1.34

过去了

1.34

くれます

1.34

Activations Density 0.016%