INDEX

Explanations

names and titles used in naming

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

 including

-1.71

see

-1.55

out

-1.52

 example

-1.38

 through

-1.34

 diferite

-1.31

via

-1.30

 like

-1.29

 following

-1.29

use

-1.28

POSITIVE LOGITS

 parfüm

1.57

 parfü

1.48

 bús

1.44

boleh

1.41

 câmera

1.38

kunjung

1.34

 entretenimiento

1.32

lewati

1.31

 amables

1.29

 joyería

1.28

Activations Density 0.227%