The InLinks tools has a semantic SEO component, so where we might want to rank for a keyphrase like:
With the InLinks tool the concept is it looks for content that’s semantically relevant, so it might add a link to content like this (some text I copied from Wikipedia):
The Semantic Web takes the solution further. It involves publishing in languages specifically designed for data: Resource Description Framework (RDF), Web Ontology Language (OWL), and Extensible Markup Language (XML). HTML describes documents and the links between them. RDF, OWL, and XML, by contrast, can describe arbitrary things such as people, meetings, or airplane parts.
The link with anchor text It involves publishing in languages specifically designed for data is a semantic type link related to Semantic SEO. Google is probably advanced enough now to understand IT refers to Semantic Web in the earlier part of the paragraph.
With Semantic SEO linking we aren’t looking for an exact match keyword/keyphrase text to link from, but a section of content which probably means the same sort of thing.
I assume the InLinks tool is using a form of machine learning to mimic how recent Google algorithms comprehend content and/or a semantic search API. Google is getting really good at understanding natural language patterns: see Google Hummingbird and RankBrain for where Google is and where it is heading.
I haven’t tested InLinks in enough detail to understand how it works or if it works well, but replicating something like this for free would be HARD. The difficulty is deciding which text is semantically relevant.