Skip to content
AIMODEL
RACE
Races
Models
Agents
Prompting
Learn
News
Search models, races, prompts…
⌘
K
Compare
Start here
Quizzes
LLM Internals
Expert · 8 questions
LLM Internals
1 / 8
Core
What does self-attention compute?
A
The probability of every word in the vocabulary
B
How much each token should draw on every other token in the context
C
The model's training loss
D
The number of tokens in a prompt
1
–
4
answer ·
Enter
next
Next question
Want to brush up first? This quiz covers
AI Engineer
.