INDEX

Explanations

various scripts and punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 egyszer

0.38

 fyra

0.34

 fração

0.32

 जिंदगी

0.31

eyeglasses

0.30

 quatro

0.29

tou

0.29

 ज़िन्दगी

0.29

<unused76>

0.29

फ्र

0.29

POSITIVE LOGITS

eltat

0.33

勖

0.33

riterion

0.33

რის

0.33

 apreciar

0.31

};

0.30

andolo

0.30

 unveil

0.29

 brightness

0.28

ંકી

0.28

Activations Density 0.030%

No Known Activations