INDEX

Explanations

name definition

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ә

1.48

uasion

1.40

<unused1918>

1.33

𝐮

1.32

<unused99>

1.31

𝐟

1.30

 sylvis

1.29

<unused922>

1.28

 coveredmethods

1.28

斯的

1.27

POSITIVE LOGITS

쉽

1.51

Transcript

1.39

gesch

1.35

Leet

1.28

ED

1.26

UpdateTime

1.25

Ed

1.25

ed

1.24

Inserted

1.24

Assembly

1.23

Activations Density 0.004%