INDEX

Explanations

passion and what follows

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

tle

-0.11

iness

-0.11

¶Į

-0.10

/Dk

-0.10

stones

-0.10

manship

-0.10

Ð¸ÑĤÐ¾ÑĢ

-0.10

liness

-0.10

alist

-0.10

INESS

-0.10

POSITIVE LOGITS

ately

0.18

ate

0.15

fruit

0.14

aten

0.13

 intensity

0.13

ionate

0.13

enger

0.12

istas

0.12

ates

0.12

awan

0.11

Activations Density 0.019%