INDEX

Explanations

sharing enjoyment and pleasure

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

Not in Any Lists

No Comments

Negative Logits

gor

-0.10

à¹Ģà¸Ħ

-0.09

 Laud

-0.09

Nag

-0.09

 Hurt

-0.09

 acted

-0.09

 indiv

-0.09

anc

-0.09

erc

-0.09

POSITIVE LOGITS

 spread

0.19

 entertain

0.18

 entertaining

0.18

 spreading

0.17

 entertainment

0.17

 Entertainment

0.17

 entert

0.16

 spreads

0.15

å¨±ä¹Ĳ

0.15

 Spread

0.14

Activations Density 0.112%