INDEX

Explanations

a graph

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

avy

-0.10

 Coordinates

-0.10

oli

-0.09

 Flor

-0.09

 Nest

-0.09

est

-0.09

 lengthy

-0.08

 Galactic

-0.08

 hitch

-0.08

POSITIVE LOGITS

 graph

0.30

 network

0.29

 networks

0.27

 Network

0.23

network

0.23

Network

0.21

etwork

0.21

 Networks

0.20

 Graph

0.20

 graphs

0.20

Activations Density 0.101%