INDEX

Explanations

author or source attribution

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

 Momente

-1.19

 любого

-1.07

Beskrivning

-1.06

写真は

-1.05

pekte

-1.05

Приготовление

-1.05

全都

-1.02

もちろん

-1.01

 모든

-1.00

我們的

-1.00

POSITIVE LOGITS

 нашла

1.18

 brilhante

1.16

 zicht

1.12

 reactie

1.12

 response

1.12

 risico

1.11

 gikk

1.09

 pagado

1.09

ográfica

1.09

गत

1.08

Activations Density 0.078%