INDEX

Explanations

specific entities and proper nouns

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ice

0.79

ó

0.75

不是

0.74

cek

0.74

mut

0.71

ite

0.71

iter

0.70

aa

0.69

ا

0.69

कर

0.68

POSITIVE LOGITS

 filosóf

1.15

 âng

1.09

 sitios

1.08

 pitfalls

1.07

 ändern

1.06

 Wechsler

1.05

 Wszyst

1.05

 aumenta

1.04

 selber

1.04

 Honestly

1.03

Activations Density 0.000%