INDEX

Explanations

to judge

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

<|begin_of_text|>

-0.12

.LoggerFactory

-0.10

.printStackTrace

-0.08

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.08

olumn

-0.08

 Ø¨ÙĪØ§Ø¨Ø©

-0.08

.Today

-0.08

ÅĦ

-0.08

ÑģÑĤÐ°

-0.08

POSITIVE LOGITS

iyon

0.09

cth

0.09

subcategory

0.09

IVEN

0.08

anio

0.08

DataStream

0.08

ilogy

0.08

SharedPtr

0.08

pons

0.08

 face

0.08

Activations Density 0.019%