INDEX

Explanations

end of phrase or sentence

detecting direct quoted speech or short utterances (lines of dialogue/captions).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 pulsations

0.25

ើង

0.24

 disturbing

0.24

 trillions

0.24

 fillets

0.24

 harmonics

0.24

 principles

0.23

 varieties

0.23

 acidity

0.23

 configurations

0.22

POSITIVE LOGITS

 অথবা

0.36

强调

0.33

 Emphasis

0.33

 강조

0.31

 ইত্যাদি

0.29

 emphasis

0.29

这句话

0.28

 ಎಂದು

0.28

強調

0.28

这话

0.27

Activations Density 0.147%