INDEX

Explanations

python code definitions

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

 tandis

0.27

 mentre

0.26

 بنائے

0.26

 earphones

0.25

 während

0.24

곧

0.23

 دوم

0.22

 സൃ

0.22

笥

0.22

 bioavailability

0.21

POSITIVE LOGITS

Move

0.26

 Debug

0.23

THE

0.22

Un

0.22

Example

0.22

 Unlock

0.22

Model

0.21

Challenges

0.21

Res

0.21

Identity

0.21

Activations Density 0.019%