INDEX

Explanations

constant updating and improvement

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

2.76

نسان

2.74

俣

2.67

ದ್ದು

2.50

ülete

2.49

た

2.47

ὖ

2.47

łem

2.43

ਹ

2.38

}}^

2.37

POSITIVE LOGITS

िक्रमा

3.52

ंपरा

2.56

कर्ता

2.50

 herbs

2.42

搡

2.31

 Vault

2.30

tım

2.30

 smoothed

2.27

स्मै

2.22

বসাইট

2.20

Activations Density 0.023%