# LLMs are Interpretable

DevFeed: [LLMs are Interpretable](<https://devfeed.tech/articles/llms-are-interpretable-33420.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2023/10/01/interpretability>)

Published: 2023-10-01T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [LLMs](<https://devfeed.tech/topics/llms.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [llms](<https://devfeed.tech/tags/llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [trust](<https://devfeed.tech/tags/trust.md>)

## AI overview

The author argues that large language models are among the most interpretable forms of machine learning in broad use. Drawing on research about explanation in psychology and sociology, the article presents interpretability as a complex, human-centered concept tied to trust and explains why the author considers LLMs such as ChatGPT and Claude capable of providing useful explanations of their behavior.

## Source excerpt

Shockingly, LLMs are the most interpretable form of machine learning that I've seen so far, in that it's very compatible with an end user's needs for trust and explanation of behavior.