hjLabs AI Playground

Starting the on-device runtime…

Watch a masked language model guess the missing word

Fill-mask is the pre-training objective behind BERT and the clearest window into what a language model has actually learned: hide a word, and the model ranks candidates with probabilities. It is genuinely useful for probing bias, testing tokenisation, checking whether a domain term is in-vocabulary, and teaching how transformers work. Type a sentence with [MASK] in it and the top predictions appear with their scores, computed on your GPU.

fill mask demobert masked language modelpredict missing word aimlm playgroundbert bias probingtransformer demo online

Frequently asked questions

What mask token do I type?

BERT-family models use [MASK]; RoBERTa-family models use <mask>. The page inserts the correct token for the model you have selected, so you can click rather than remember.

Why is this useful beyond a demo?

It is a fast way to audit a model before you fine-tune it — whether your jargon survives tokenisation, and what stereotypes the pre-training data baked in.

Models available for this task