INDEX

Explanations

explaining structured formats

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Edelstahl

0.56

看到了

0.46

 vitesses

0.46

PEL

0.41

 meisjes

0.41

出了

0.41

 szeret

0.40

WAB

0.40

CHE

0.40

 compteur

0.40

POSITIVE LOGITS

자의

0.49

 тексту

0.45

scales

0.44

ttet

0.43

eren

0.43

urry

0.43

ું

0.42

ımı

0.42

ító

0.42

òm

0.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.