INDEX

Explanations

numbers and punctuation

mathematical notation and symbols

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ुल

0.41

tul

0.40

кха

0.40

toh

0.39

तात

0.39

spiel

0.39

lur

0.38

ноп

0.38

绵

0.38

વાથી

0.36

POSITIVE LOGITS

 agama

0.44

ᇁ

0.43

 administrative

0.43

 Agreements

0.43

 했다

0.42

 Administrative

0.41

ぞれ

0.41

 postures

0.40

ྩ

0.40

 textual

0.39

Activations Density 0.000%