INDEX

Explanations

protecting vulnerable or critical

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

প

0.58

 exploración

0.52

0.49

zné

0.48

 terug

0.48

 lần

0.47

ch

0.46

 oprav

0.46

 pamoja

0.46

的基础

0.46

POSITIVE LOGITS

 protect

1.26

 protecting

1.22

 protects

1.13

 protection

1.12

 보호

1.11

 protected

1.08

 melindungi

1.06

保护

1.05

 safeguard

1.04

保護

1.01

Activations Density 0.251%