INDEX

Explanations

specializing in English 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

and

-1.05

usura

-0.96

ülete

-0.93

゚

-0.90

たび

-0.89

 homophobic

-0.88

вна

-0.87

 آلمان

-0.86

Gypsy

-0.85

smell

-0.85

POSITIVE LOGITS

 Gelände

1.08

StandardCharsets

0.97

 пальто

0.94

 видом

0.93

é

0.92

0.91

 error

0.91

 default

0.91

 глоба

0.91

error

0.90

Activations Density 0.107%