INDEX

Explanations

verbs followed by prepositions

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

 donations

0.41

 직접

0.41

 flats

0.39

 fillets

0.39

 predominance

0.38

 canvases

0.38

 antider

0.38

 efficiently

0.38

 Ме

0.37

нению

0.37

POSITIVE LOGITS

ENDAR

0.40

,*

0.39

spring

0.38

 इधर

0.38

iddle

0.38

дав

0.38

чайно

0.37

春秋

0.37

</sup>

0.36

 minded

0.36

Activations Density 0.001%