INDEX

Explanations

scaling models and language

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

 interessant

0.37

პ

0.35

 intriguing

0.34

 interesting

0.33

๑

0.33

interesting

0.33

 तुम्हाला

0.32

 interessante

0.32

 интерес

0.32

 wonderful

0.32

POSITIVE LOGITS

ঠোর

0.34

 শেষ

0.32

ALWAYS

0.31

LEASE

0.31

 सीएचसी

0.31

 этими

0.31

疹

0.30

 depende

0.30

乸

0.30

 ALWAYS

0.29

Activations Density 0.720%