INDEX

Explanations

references to geographical locations and community identifiers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aeda

-0.07

agini

-0.07

FAG

-0.07

omik

-0.06

Ã³w

-0.06

ãĥ©ãĥĥãĤ¯

-0.06

æĸ

-0.06

pak

-0.06

mil

-0.06

orf

-0.06

POSITIVE LOGITS

Pin

0.12

 Gulf

0.11

 Safety

0.10

Pin

0.10

 Clear

0.10

Safety

0.09

 Treasure

0.09

 Made

0.08

 safety

0.08

.Pin

0.08

Activations Density 0.005%