Responsible AI / Safety · Level 2 of 5
Interpretability
The extent to which a person can understand a model or its behavior.
Interpretability depends on the audience and the question being asked.
Example
A small decision tree exposes the tests leading to a label.
Listen to the definition and example
Audio transcript
Interpretability. The extent to which a person can understand a model or its behavior. Interpretability depends on the audience and the question being asked. For example: A small decision tree exposes the tests leading to a label.
Explore this concept
Why it matters
This helps you identify a concrete failure mode or evaluate the limits of a proposed control.
Start with
Related concepts
Quick recall question
Try answering before looking back at the definition.