INDEX

Explanations

code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BoxFit

-0.50

سطس

-0.44

.*")]

-0.44

chromedriver

-0.43

geladen

-0.42

Brainz

-0.41

dungen

-0.41

ToProps

-0.40

@",

-0.40

הערות

-0.40

POSITIVE LOGITS

0.94

 cause

0.70

cause

0.70

haz

0.68

 Paglinawan

0.67

risk

0.65

hazard

0.64

elemField

0.63

 للاسماء

0.61

 beginnetje

0.60

Activations Density 0.002%