Unverified50% confidenceFactExact time
Upon seeing [A][B]...[A], induction heads tend to predict that the next token is [B].
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen a prompt is entered, the model predicts the most likely next token based on context, rather than truly understanding the semantics.63% similarUnverifiedWord-by-word generation is technically called autoregressive generation, where the token generated at each step is appended back to the input sequence as the condition for the next prediction62% similarUnverified反事实解释回答的问题是:最少需要改变输入的哪些特征,才能让模型的预测结果翻转60% similarVerifiedThe core of a ReAct agent is the "reasoning-action-observation" loop, in which the LLM analyzes the problem, decides to call a tool, observes the returned result, and continues reasoning if unsatisfied until it gives a final response59% similarUnverifiedHindsight bias involves a memory reconstruction mechanism: upon learning the outcome, the brain automatically integrates the outcome information into the existing knowledge structure, making cues consistent with the outcome more salient.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/917342API
curl https://kongchang.com/api/v1/knowledge/claims/917342MCP
get_claim(id=917342)