INDEX

Explanations

entity attributes or descriptions

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

برای

0.27

 aiuta

0.26

 empêcher

0.25

 onları

0.25

 aident

0.25

 savent

0.25

 ajuda

0.24

 mencegah

0.24

 ayudan

0.24

 sugiere

0.24

POSITIVE LOGITS

 being

0.45

being

0.35

has

0.34

 have

0.34

被

0.33

 undergoing

0.32

 should

0.31

 received

0.31

 имеет

0.31

 underwent

0.31

Activations Density 0.551%