INDEX

Explanations

phrases introducing examples

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

荭

-1.91

"],

-1.86

 melalui

-1.73

谞

-1.70

但他

-1.69

ğum

-1.65

manera

-1.60

'),

-1.59

鵟

-1.59

("");

-1.55

POSITIVE LOGITS

on

1.60

ate

1.57

1.44

絰

1.37

 изда

1.36

孥

1.34

ak

1.34

HomeAsUpEnabled

1.33

ga

1.32

by

1.31

Activations Density 0.020%