INDEX

Explanations

text, images, audio, speech

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Negative Logits

æĸĩåŃĹ

-0.12

 TMPro

-0.10

ools

-0.10

ibri

-0.10

 textual

-0.10

èĵ

-0.10

Dud

-0.10

 texting

-0.10

_txt

-0.09

ListItemText

-0.09

POSITIVE LOGITS

 audio

0.15

 voice

0.13

 images

0.13

audio

0.12

voice

0.12

 speech

0.12

 graphics

0.12

 music

0.11

 image

0.11

 binary

0.11

Activations Density 0.107%

No Known Activations