INDEX

Explanations

listing and checking

The neuron fires on words written in non‐Latin scripts—especially Japanese or Chinese character sequences (and similar Unicode 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

was

-1.72

 Если

-1.56

 IBOutlet

-1.54

If

-1.34

ativement

-1.33

 ако

-1.29

expiresIn

-1.26

 если

-1.25

<bos>

-1.25

 BorderLayout

-1.23

POSITIVE LOGITS

 motoru

1.59

isbury

1.53

 doigt

1.34

futbolista

1.32

 mojej

1.32

larım

1.30

 моего

1.30

 vectorielle

1.30

 Inscrivez

1.29

 nôtre

1.27

Activations Density 0.003%