INDEX

Explanations

initial character sequences and following parts

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

 mosaics

0.25

 precursors

0.25

 linkages

0.24

 curving

0.24

 incorporation

0.24

 submer

0.24

кування

0.23

BIUM

0.23

 coatings

0.23

ци

0.23

POSITIVE LOGITS

 OpenAI

0.37

 ChatGPT

0.32

 tiktok

0.32

GPT

0.31

 Nvidia

0.30

 Goku

0.30

 cutest

0.29

 openai

0.29

 맛있

0.29

可爱

0.28

Activations Density 0.027%