INDEX

Explanations

stored data

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

CC

0.55

SL

0.55

PH

0.54

 variance

0.54

SE

0.53

 quantitatively

0.52

 stratification

0.52

 landscape

0.52

for

0.51

POSITIVE LOGITS

ismillahirrah

0.57

otro

0.56

蝣

0.54

ى

0.51

éssel

0.49

 یه

0.49

้ย

0.48

 आप

0.48

你就

0.48

 ඉද

0.48

Activations Density 0.000%

This feature has no known activations.