INDEX

Explanations

heights

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

 heights

-1.52

 Heights

-1.36

 height

-1.34

Heights

-1.20

heights

-1.16

 Height

-1.08

ce

-0.99

height

-0.91

 HEIGHT

-0.91

 Hauteur

-0.85

POSITIVE LOGITS

IsContent

0.44

Itinerary

0.39

AnchorTagHelper

0.38

 Wiktionnaire

0.38

Leg

0.37

erráneo

0.37

 خورد

0.37

per

0.36

 School

0.36

Activations Density 0.078%