INDEX

Explanations

part of, don't, box, function

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

¶Į

-0.10

iÐ²

-0.09

 Chap

-0.08

ekk

-0.08

sex

-0.08

 entr

-0.08

Spy

-0.08

Ø¨Ø§Ø´

-0.08

ugi

-0.07

ÙĪÙħØ§ÙĨ

-0.07

POSITIVE LOGITS

 é¢

0.10

alm

0.10

 leadership

0.09

Kaz

0.09

rana

0.09

(++

0.08

ëŁŃ

0.08

essler

0.08

 Sant

0.08

HW

0.08

Activations Density 0.092%