INDEX

Explanations

quoted keywords introducing concepts

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

<bos>

2.94

arakat

2.80

یع

2.63

তী

2.53

יות

2.43

hut

2.41

tsó

2.41

hu

2.39

irti

2.37

기고

2.36

POSITIVE LOGITS

̧

3.51

ﮄ

3.29

DEFGHIJKLMNOP

3.09

ल्पनिक

3.05

incinn

2.97

œur

2.94

asionally

2.91

entric

2.84

DEFG

2.72

ंग्रे

2.64

Activations Density 2.029%