INDEX

Explanations

attribution and citation

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

 entrusted

0.39

 cancelación

0.39

PhysicalDevice

0.38

 gravit

0.38

 विशेषज्ञ

0.38

 definição

0.37

 conflictos

0.37

മാനം

0.37

filt

0.36

 противоре

0.36

POSITIVE LOGITS

 citation

1.22

 citations

1.10

 cite

1.09

 Citation

1.08

 attribution

1.01

 citing

1.00

 Cite

0.98

Citation

0.92

Cite

0.90

cite

0.88

Activations Density 0.007%