Tokens
https://learn.microsoft.com/en-us/semantic-kernel/prompt-engineering/tokens
Here is a website that has a more advanced definition for Tokens!
Here is an excerpt:
“Tokens are the basic units of text or code that an LLM AI uses to process and generate language. Tokens can be characters, words, subwords, or other segments of text or code, depending on the chosen tokenization method or scheme.
Tokens are assigned numerical values or identifiers, and are arranged in sequences or vectors, and are fed into or outputted from the model. Tokens are the building blocks of language for the model.”
“Tokenization is the process of splitting the input and output texts into smaller units that can be processed by the LLM AI models. Tokens can be words, characters, subwords, or symbols, depending on the type and the size of the model. Tokenization can help the model to handle different languages, vocabularies, and formats, and to reduce the computational and memory costs. “
Prompts
Prompts are instructions or commands given to the bot to guide the direction of the conversation/role-play scenario. They serve as the starting point for the bot to generate relevant and contextually appropriate responses. By analyzing the prompts, the bot can understand the user's intentions and generate content accordingly.
OOC
OOC stands for "Out of Character." It refers to communication or actions that occur outside the established character or role that one is portraying. In the context of role-play or storytelling, going OOC means temporarily stepping away from the character to discuss matters unrelated to the narrative. It allows participants to clarify intentions, or provide guidance without breaking the immersion of the role-play itself.
Context Length
"Context length", measured in tokens, is the maximum amount of information the model can use at once when generating a reply.