INDEX

Explanations

everything means that

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

 đang

0.93

 நேற்று

0.93

 রকম

0.89

 estaban

0.89

водства

0.89

推动

0.88

已

0.88

 estavam

0.87

 estaba

0.85

 있었

0.85

POSITIVE LOGITS

 oftentimes

1.63

 once

1.44

if

1.43

 sometimes

1.40

you

1.35

 depending

1.34

 your

1.32

 often

1.27

 selecting

1.26

如果你

1.25

Activations Density 1.004%