INDEX

Explanations

10 simple project ideas

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

ï¼¹

-0.10

 trainable

-0.09

_ASSUME

-0.09

ESL

-0.09

MLE

-0.09

 Canter

-0.09

 ?><?

-0.08

 Convenience

-0.08

 Researchers

-0.08

 HttpMethod

-0.08

POSITIVE LOGITS

 projects

0.21

 Projects

0.21

Projects

0.16

projects

0.16

 challenge

0.16

 project

0.15

 ideas

0.14

 ambitious

0.14

 challenges

0.14

 Project

0.13

Activations Density 0.197%