INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

Semif

0.42

спери

0.36

 कोल्ड

0.36

 صدی

0.35

usters

0.34

ProjectId

0.34

 реконструк

0.34

˨

0.34

 chall

0.33

eri

0.33

POSITIVE LOGITS

 Introduction

0.52

Introduction

0.49

Master

0.46

introduction

0.45

 Fundamentals

0.44

Fundamentals

0.41

 microscopic

0.40

 Fundamental

0.40

Everything

0.40

 Secrets

0.40

Activations Density 0.000%

No Known Activations