INDEX

Explanations

code definition contexts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 when

-1.23

 cuando

-0.82

when

-0.82

beten

-0.82

 đồng

-0.82

cuando

-0.79

tividad

-0.79

 When

-0.73

 which

-0.72

頂いた

-0.72

POSITIVE LOGITS

跤

0.86

 toString

0.81

Segments

0.79

icating

0.77

to

0.76

 segments

0.74

 samot

0.73

teilte

0.73

 anaerobic

0.73

 olarak

0.72

Activations Density 0.012%