INDEX

Explanations

configuration files and settings

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

inge

-0.10

ries

-0.10

 prol

-0.10

 Hayes

-0.09

 Morse

-0.09

ocker

-0.09

 util

-0.08

Spy

-0.08

 shin

-0.08

 continuity

-0.08

POSITIVE LOGITS

 Cors

0.12

 settings

0.12

 conf

0.11

 setting

0.10

 INST

0.10

 ãĢī

0.10

paths

0.10

 General

0.10

SplitOptions

0.10

 CORS

0.10

Activations Density 0.060%