INDEX

Explanations

historical changes/construction

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

te

-0.85

 cloud

-0.71

-0.70

er

-0.70

 evolved

-0.69

cloud

-0.65

 fort

-0.61

always

-0.60

 Always

-0.60

 Released

-0.60

POSITIVE LOGITS

lgari

0.63

 برانيه

0.60

:✨

0.57

 Audiodateien

0.57

IndentedString

0.56

كويكب

0.56

 Walkover

0.55

 zufolge

0.53

aneous

0.51

>-->

0.50

Activations Density 0.028%