INDEX

Explanations

recent trends

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

 Courtyard

-0.87

dillas

-0.79

 circumference

-0.79

liffe

-0.78

desliz

-0.77

 conversely

-0.76

statusBar

-0.76

Tecnología

-0.75

CIV

-0.75

lize

-0.75

POSITIVE LOGITS

 trend

1.39

 recent

1.38

 previous

1.25

trend

1.23

 Trend

1.12

Recent

1.05

recent

1.03

 recente

1.02

Trend

0.97

 prior

0.93

Activations Density 0.016%