INDEX

Explanations

our or we

interesting origins of words

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

вропей

0.51

テイ

0.51

ゼン

0.48

 Kassel

0.48

 forgo

0.46

モー

0.46

徜

0.46

ذا

0.45

ギリス

0.45

 Karg

0.44

POSITIVE LOGITS

if

0.54

we

0.52

 chúng

0.51

 เรา

0.49

 мы

0.47

ığımız

0.46

IndexArray

0.45

 आमच्या

0.45

0.44

 நாம்

0.44

Activations Density 0.001%