INDEX

Explanations

open weights and transparency

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 utilizar

0.39

 మూడు

0.38

 മറ്റൊരു

0.38

 delicate

0.37

 nutzen

0.36

 Calyce

0.35

 Aloe

0.35

 بط

0.35

 elegante

0.35

>[

0.35

POSITIVE LOGITS

 transparency

1.09

Transparency

1.04

 openly

1.00

 Transparency

0.99

公开

0.98

 transparence

0.98

 transparencia

0.95

 transparent

0.93

 पारदर्शिता

0.92

 공개

0.91

Activations Density 0.355%

No Known Activations