INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 grandparent

0.45

Parent

0.43

 Cousin

0.42

 grandfather

0.42

Brother

0.41

 Grandmother

0.41

Papa

0.41

ister

0.40

👵

0.40

Mode

0.39

POSITIVE LOGITS

 acquaintances

0.44

 Technically

0.41

 заранее

0.41

 znale

0.40

 Lloyds

0.40

洖

0.40

 algebraica

0.39

 travellers

0.38

 złot

0.38

 musically

0.38

Activations Density 0.007%

No Known Activations