INDEX

Explanations

enclosing quotes

This neuron responds to tokens containing a dot (e.g. file names, extensions, or domain names).

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

 складу

-1.05

arão

-1.00

 明治

-0.99

 destinées

-0.93

 étr

-0.91

είο

-0.91

 ſte

-0.91

fromLTRB

-0.88

 réguli

-0.88

她说

-0.87

POSITIVE LOGITS

、「

1.27

."

1.09

 enchufe

0.98

of

0.94

}$.

0.91

太多了

0.91

 campañas

0.90

 файлов

0.89

aknya

0.87

Activations Density 0.092%