Er, maybe if we get really good at doing patching-style techniques? But there’s definitely not an obvious path—I more see lie detectors as one of the ultimate goals of mech interp, but whether this is actually possible or practical is yet to be determined.
Can this be used as some kind of lie detector?
Er, maybe if we get really good at doing patching-style techniques? But there’s definitely not an obvious path—I more see lie detectors as one of the ultimate goals of mech interp, but whether this is actually possible or practical is yet to be determined.