INDEX

Explanations

large language model created

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

 можна

0.43

 можно

0.42

 kunna

0.40

 हाथ

0.38

钰

0.37

 kunnen

0.37

 Cheng

0.36

 Можно

0.36

 można

0.36

льзя

0.36

POSITIVE LOGITS

še

0.39

৫৪

0.39

 Depend

0.38

භාව

0.37

 мне

0.37

 dependen

0.36

DEPENDENCIA

0.35

 dependability

0.35

omorphisms

0.35

 REQUIRE

0.35

Activations Density 0.001%