On the same slide $4$ "Neural Networks $101",$ what is the output of the softmax function when applied to

the logit $($the L$).$ How does the output of the softmax compares with previous logit functions like the

logistic for example, and what does this output represent $?$ mathematical function softmax and the one we saw in Skansi$).$

mathematical function softmax and the one we saw in Skansi$).$