INDEX

Explanations

Elara

English contractions and possessive forms marked with an apostrophe.

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

}=$

0.54

ופ

0.51

 ஆகியவை

0.49

 adherents

0.48

 ophthal

0.47

 цей

0.46

ⴼ

0.46

िन

0.46

OL

0.46

 slats

0.45

POSITIVE LOGITS

 saying

0.53

’

0.53

 Actually

0.52

 Maybe

0.50

 olmadığını

0.49

 શું

0.47

 Aunt

0.46

 hadn

0.46

 wasn

0.46

 That

0.46

Activations Density 0.046%