INDEX

Explanations

names followed by initials or last names

names with initials or middle names

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

 akka

0.42

 Vicky

0.42

和一个

0.42

 sẵn

0.39

 glorified

0.38

 नव्ह

0.38

<unused1033>

0.37

 τόσο

0.36

 χώρα

0.36

 রক্ত

0.36

POSITIVE LOGITS

1.31

 डब्ल्यू

1.06

 एच

1.04

 Дж

1.03

 এইচ

1.02

1.01

Ｊ

0.99

0.96

0.95

Activations Density 0.446%