INDEX

Explanations

structured data or code

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

&nbsp

-0.10

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

-0.09

&amp

-0.08

 TMPro

-0.08

esa

-0.08

::::::::

-0.08

çı

-0.08

çĥ§

-0.08

 Radar

-0.08

 affection

-0.08

POSITIVE LOGITS

 null

0.13

("

0.10

null

0.09

oplayer

0.09

 trop

0.09

ÌĨ

0.09

âĶģâĶģ

0.09

izza

0.09

engu

0.08

Activations Density 0.032%