INDEX

Explanations

planet and planets

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

 Cosmic

-0.12

aurus

-0.11

 astronaut

-0.11

 Astr

-0.11

 Basil

-0.10

meteor

-0.10

Meteor

-0.10

 Astronomy

-0.10

 cosmic

-0.10

 Meteor

-0.10

POSITIVE LOGITS

 planet

0.35

 planets

0.30

 Planet

0.25

 habit

0.25

 Ð¿Ð»Ð°Ð½

0.24

oplan

0.24

planet

0.24

 worlds

0.23

Planet

0.21

 PLAN

0.21

Activations Density 0.071%