Update README.md

README.md

@@ -126,4 +126,5 @@ Given how the duplicated layers seem to have a stabilizing effect, it begs the q
 
 ### Can you replicate this effect on normal models by freezing layers?
 
-### We've so far hypothesized that training 'slowly fills' the duplicated layers. If we intentionally undercook, will the duplicated layers look *underfilled* or can you fill it up with a few steps? In other words, does a single/few updates to the model repair the damage?
+### We've so far hypothesized that training 'slowly fills' the duplicated layers. If we intentionally undercook, will the duplicated layers look *underfilled* or can you fill it up with a few steps? In other words, can a single/few updates to the model reconnect the duplicated layers?
+- Are we really repairing the 'neurons' step-by-step, or have they been significantly rearranged by the first (few?) steps?