INDEX

Explanations

open-weights vs closed source

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

 deformity

0.44

மிழ்

0.42

િવ

0.41

<unused532>

0.41

 secundaria

0.41

ミン

0.41

 topographical

0.40

CheckingType

0.40

َب

0.40

 bottomLeft

0.40

POSITIVE LOGITS

 proprietary

1.87

 Propri

1.70

propri

1.54

 propriet

1.31

 Propriet

1.09

 closed

1.09

 Closed

1.05

Closed

1.02

 propri

0.97

 propriety

0.97

Activations Density 0.007%