INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ģç¼ķ

-0.06

 humble

-0.06

izu

-0.06

 democ

-0.06

echa

-0.06

agak

-0.06

koz

-0.06

 yourselves

-0.06

ìĤ¶

-0.06

epas

-0.06

POSITIVE LOGITS

 ÑĢÐ°Ð²Ð½Ð¾

0.05

æľŁå¾ħ

0.05

 Expect

0.05

Expect

0.05

chang

0.05

 advantageous

0.04

 Mari

0.04

 schem

0.04

åĤ¬

0.04

ator

0.04

Activations Density 0.000%

No Known Activations