INDEX

Explanations

phrases related to compliance or following rules and standards

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

stadt

-0.07

çıŃ

-0.06

sh

-0.06

ned

-0.06

nes

-0.06

¼

-0.06

tt

-0.06

Ø·ÙĦ

-0.06

ellen

-0.06

spacer

-0.06

POSITIVE LOGITS

 strict

0.09

 strictly

0.09

 closely

0.08

 Stick

0.08

Stick

0.08

 Strict

0.08

azor

0.08

 stick

0.07

stick

0.07

Strict

0.07

Activations Density 0.004%