INDEX

Explanations

dá-me mais

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

 contato

-0.14

 nuest

-0.14

 equipe

-0.11

esor

-0.10

 IOCTL

-0.09

squ

-0.09

 Incre

-0.09

 Dise

-0.09

 Brazil

-0.09

 pÅĻ

-0.09

POSITIVE LOGITS

 Portugal

0.19

 Portuguese

0.19

 Lisbon

0.15

.pt

0.15

RTP

0.14

 cork

0.13

 direccion

0.12

 afect

0.12

 efect

0.12

Ã³nica

0.12

Activations Density 0.279%