INDEX

Explanations

percentages and years

numbers followed by units

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

يش

0.41

стта

0.40

 ܗܘ

0.39

 Administ

0.38

Springer

0.38

зова

0.37

ச்சு

0.37

ضي

0.37

0.36

իս

0.36

POSITIVE LOGITS

 นึง

0.76

％

0.64

0.60

%%%%%%%%

0.56

0.54

$\%

0.53

 டிகிரி

0.52

%%%

0.51

 PERCENT

0.51

 percent

0.50

Activations Density 0.038%