Your entire argument is derived from a pseudoscientific field without any peer-reviewed research. Mechanistic interpretability is a joke invented by AI firms to sell chatbots.
And apparently you think peer reviewed papers presented at NeurIPS or other conferences are considered pseudoscience. (For the people not versed in ML, NeurIPS is where the 2017 paper "Attention is All You Need" that started the modern ML revolution was presented)
https://neurips.cc/virtual/2023/poster/72666
https://jmlr.org/beta/papers/v26/23-0058.html