INDEX

Explanations

training or data processing

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

abay

-0.07

lav

-0.07

/shared

-0.07

lags

-0.07

³

-0.07

åĿĢ

-0.07

º¼

-0.06

ikle

-0.06

 gÃ¤r

-0.06

çªĴ

-0.06

POSITIVE LOGITS

ocken

0.08

anser

0.07

scaled

0.07

 Ø§ÙĦÙħÙĨØª

0.07

 scaled

0.07

è§Ħæ¨¡ä¸º

0.07

aller

0.07

æľªè¾¾åĪ°

0.07

 Legis

0.07

illos

0.07

Activations Density 0.097%

No Known Activations