INDEX

Explanations

since indicating past

weeks since

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

 Потому

0.50

改めて

0.43

ையிலும்

0.40

 потому

0.38

 diye

0.37

 করলে

0.37

次は

0.37

是因為

0.37

 그래서

0.36

 எல்லாம்

0.36

POSITIVE LOGITS

 since

4.75

since

4.47

 منذ

4.13

 Since

3.95

Since

3.95

 sejak

3.92

 seit

3.91

 depuis

3.84

 sinds

3.39

 desde

3.11

Activations Density 0.435%