INDEX

Explanations

list separator

multi-word concepts linked by "and"

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

 hanging

0.59

 plays

0.57

 explored

0.46

 takže

0.45

 dieser

0.45

 march

0.44

だったので

0.43

 questo

0.43

 które

0.43

 पूरे

0.43

POSITIVE LOGITS

 आणि

1.87

 અને

1.82

 এবং

1.79

 ਅਤੇ

1.75

 और

1.68

и

1.66

và

1.63

 και

1.63

และ

1.61

 และ

1.56

Activations Density 0.184%