INDEX

Explanations

among Vicuna, corpora, Cascadia, trend started

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

1.87

1.81

 that

1.77

1.75

1.69

as

1.64

but

1.58

..

1.56

or

1.46

POSITIVE LOGITS

 souligne

2.26

 μπορεί

2.23

者は

2.23

 può

2.22

 inoltre

2.19

 potrebbe

2.11

氏は

2.04

 relação

2.03

 révèle

2.02

 sarà

2.02

Activations Density 0.578%