INDEX

Explanations

variable or value types

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

Negative Logits

 Vita

-0.09

 forms

-0.09

 nameof

-0.09

=value

-0.09

 Calif

-0.08

ä¹ĭä¸Ģ

-0.08

 Pavel

-0.08

 demographics

-0.08

yb

-0.08

ä¸ĢçĤ¹

-0.08

POSITIVE LOGITS

 type

0.46

type

0.35

 tipo

0.33

 typu

0.32

 ÑĤÐ¸Ð¿Ð°

0.32

(type

0.32

-type

0.31

.type

0.31

ç±»åŀĭ

0.30

_type

0.30

Activations Density 0.137%

No Known Activations