INDEX

Explanations

dictionary attack or idea presented

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

{}'.

0.40

residuals

0.39

 proche

0.39

舖

0.38

ೇಶ

0.36

 españ

0.36

quota

0.36

Fused

0.36

putes

0.36

getResources

0.35

POSITIVE LOGITS

mány

0.42

 Fingers

0.40

ॉर्क

0.39

vány

0.38

 Sadler

0.37

 உத

0.37

 получится

0.37

啄

0.36

 McConnell

0.36

Ghe

0.36

Activations Density 0.001%