INDEX

Explanations

Japanese nouns and phrases

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

 Japan

-0.93

Japan

-0.89

cul

-0.86

மைய

-0.82

 dakika

-0.82

踔

-0.80

Wird

-0.80

 ekst

-0.80

 Houſe

-0.79

店で

-0.77

POSITIVE LOGITS

Validated

0.82

illot

0.81

psons

0.80

tický

0.80

Closeable

0.79

尼斯

0.77

ATS

0.76

valley

0.76

 scaffolding

0.76

wheres

0.75

Activations Density 0.007%