INDEX

Explanations

reads settings from xml

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

 funcs

-0.09

uv

-0.09

ingo

-0.09

åĭ

-0.09

TypeEnum

-0.09

igo

-0.08

 Hebrew

-0.08

pur

-0.08

 depress

-0.08

FUNCTION

-0.08

POSITIVE LOGITS

 config

0.29

 conf

0.29

 configuration

0.28

 settings

0.25

 Configuration

0.25

config

0.23

.config

0.22

 Config

0.22

@Configuration

0.21

 ÐºÐ¾Ð½ÑĦ

0.21

Activations Density 0.115%