INDEX

Explanations

linguistic terms and researchers

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

 primers

0.41

 relational

0.40

 integrand

0.39

лан

0.38

 cond

0.37

 input

0.36

 primer

0.36

lan

0.36

 epic

0.36

 geometries

0.36

POSITIVE LOGITS

 lingu

1.00

 Lingu

0.95

 Linguistic

0.95

lingu

0.94

 linguistic

0.91

 Linguistics

0.91

 lingü

0.88

 linguistique

0.86

 linguistics

0.85

 ling

0.79

Activations Density 0.012%