INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

টিআই

1.23

 podido

1.15

ůže

1.12

 Faktor

1.07

ebilirsiniz

1.06

憶

1.06

 recentemente

1.05

僱

1.02

abilirsiniz

1.01

 vecino

1.01

POSITIVE LOGITS

 PURPOSE

1.41

 intended

1.40

 purpose

1.36

 purposes

1.34

 utter

1.30

 ONLY

1.29

 precision

1.28

 comedic

1.26

粹

1.25

intended

1.24

Activations Density 0.386%

No Known Activations