INDEX

Explanations

vehicles and their contexts

vehicles and their use

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

 Extending

0.42

 Ships

0.42

 elucidated

0.41

 речо

0.41

듬

0.39

 сущ

0.39

 Walking

0.39

Intensity

0.38

Walking

0.38

 feedback

0.38

POSITIVE LOGITS

 parked

1.49

驶

1.05

輛

1.04

 chở

1.03

行驶

1.02

驾驶

0.91

 moored

0.89

に乗

0.88

fahrer

0.88

 पार्किंग

0.88

Activations Density 0.283%