INDEX

Explanations

similarity between concepts

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

 Completely

0.43

 recharged

0.40

 ሙሉ

0.38

 completamente

0.38

แต่ละ

0.38

 Meanwhile

0.37

 individuale

0.37

 completely

0.37

 Equipped

0.37

 volledig

0.36

POSITIVE LOGITS

类似的

0.65

 similar

0.60

 вообще

0.58

 비슷한

0.56

similar

0.55

 مشابه

0.54

 hasonló

0.53

类似

0.50

something

0.50

 подоб

0.50

Activations Density 0.461%