INDEX

Explanations

specifying emission targets or standardization

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

ka

0.48

 Qué

0.46

Ō

0.46

Psy

0.46

 Juda

0.43

0.42

 Pourquoi

0.42

 Zeit

0.42

 Thé

0.41

 Thời

0.41

POSITIVE LOGITS

Safety

0.40

Sampling

0.38

representing

0.37

แกรม

0.37

Aggregate

0.36

>().

0.36

asena

0.36

Facades

0.36

워

0.36

 caderno

0.35

Activations Density 0.002%