descriptive adjectives followed by nouns

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

-2.03

-1.98

-1.82

-1.73

-1.72

 السيارات

-1.64

zunehmen

-1.57

єю

-1.54

腘

-1.52

 heathen

-1.45

POSITIVE LOGITS

2.39

теля

1.91

↵↵↵

1.84

'''

1.84

</h1>

1.68

 ajusta

1.66

 actualiza

1.63

 adapting

1.57

 piensa

1.56

 büyük

1.49

Activations Density 0.079%