INDEX

Explanations

locations and proper nouns

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

实的

-0.84

水分

-0.84

Оста

-0.84

 Američ

-0.83

 estrela

-0.83

 résist

-0.81

nser

-0.80

 Composer

-0.80

 manipulator

-0.79

天文

-0.78

POSITIVE LOGITS

 there

1.09

had

0.93

၉

0.89

ddd

0.86

 both

0.82

,”

0.81

 each

0.81

Љ

0.79

to

0.79

logías

0.78

Activations Density 0.004%