INDEX

Explanations

programmatic constants and types

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

 fluorine

-1.30

 fluoride

-1.15

 Firefox

-1.03

 fentanyl

-1.02

 federation

-0.99

 fiets

-0.99

 Fiji

-0.98

 fluorescence

-0.96

Firefox

-0.96

 Finney

-0.96

POSITIVE LOGITS

fun

0.93

 joka

0.82

fu

0.81

fy

0.81

 parietal

0.77

 Instagram

0.75

found

0.75

֣

0.75

Fun

0.75

 wieder

0.74

Activations Density 0.257%