INDEX

Explanations

comparing things with as

[verb/description] as

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

 lovely

0.52

 impressive

0.46

 인해

0.43

 lawyers

0.39

 ከሆነ

0.39

новить

0.38

]]

0.38

oldown

0.37

ㄣ

0.37

HOUT

0.36

POSITIVE LOGITS

as

3.09

 sebagai

2.17

 ως

1.94

として

1.81

作为

1.73

 както

1.72

 Sebagai

1.70

 као

1.65

作為

1.61

 jako

1.57

Activations Density 1.083%