INDEX

Explanations

is original

describing skills and confidence

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

Older

0.55

是一名

0.48

seleccion

0.46

 destinado

0.46

Once

0.46

setSelected

0.45

 âgé

0.44

有望

0.44

 destiné

0.43

 unearthed

0.42

POSITIVE LOGITS

 originally

0.76

 Originally

0.63

originally

0.59

Originally

0.57

 ориги

0.57

 original

0.55

 ursprünglich

0.54

 orijinal

0.50

 oryginal

0.50

 passionate

0.49

Activations Density 0.063%