INDEX

Explanations

terms related to data protection and regulations

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

plx

-0.07

Î¹ÏĥÏĦÎ®

-0.06

ruc

-0.06

alian

-0.06

affer

-0.06

aggregate

-0.06

 ÙħÙĪØ±

-0.06

pile

-0.06

executable

-0.06

Ø¯Ùħ

-0.06

POSITIVE LOGITS

 Protection

0.16

 protection

0.16

Protection

0.13

 subjects

0.13

 controller

0.12

 Subjects

0.12

 controllers

0.12

 Controller

0.11

 subject

0.11

 Controllers

0.11

Activations Density 0.009%