INDEX

Explanations

descriptions of goods and styles

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 atau

1.23

 eller

1.22

 oder

1.12

 algún

1.11

 preterm

1.10

 अथवा

1.07

 suboptimal

1.07

 scoped

1.04

 ataupun

1.03



1.03

POSITIVE LOGITS

 famoso

1.41

 hermoso

1.35

 sunglasses

1.31

Gorgeous

1.25

 gorgeous

1.25

图案

1.23

 usado

1.21

 краси

1.21

 Использу

1.19

 beautiful

1.18

Activations Density 0.029%