Decision on Charging Renee Good and Alex Pretti’s Killers Looms Over Minneapolis DA Race
Read the original article at The Intercept →
What the model flagged
Analyzed 2026-09-20 04:07 UTC. Articles are sometimes updated after publication — if a quote below isn't in the current version, the piece has changed since.
Findings may include language the outlet is quoting rather than asserting. We flag manipulation techniques wherever they appear, including inside quotations — so check each quote against the original before drawing a conclusion about the outlet.
Loaded Language 95%
The phrase 'full-on authoritarian takeover' uses emotionally charged, extreme language designed to trigger alarm rather than describe a specific policy or action — for example: 'authoritarian takeover'
“full-on authoritarian takeover”
Exaggeration/hyperbole 85%
Describing current events as a complete 'takeover' of the entire U.S. government is an extreme overstatement that goes well beyond what any specific evidence presented could support — for example: 'full-on authoritarian takeover of the U.S. government'
“full-on authoritarian takeover of the U.S. government”
False Urgency 72%
The phrase 'right now' creates a sense of immediate crisis designed to provoke an urgent emotional response rather than careful deliberation — for example: 'right now'
“right now”
Name Calling 89%
Derogatory labels used to discredit a person or group rather than address their arguments.
Conspiracy Appeal 95%
Hidden plots, secret coordination, or shadowy actors invoked to explain away evidence.
Appeal To Fear 75%
The image of billionaires 'rebuilding the information environment to their liking' implies a dire, coordinated threat to public access to truth, designed to provoke anxiety — for example: 'rebuilding the information environment to their liking'
“rebuilding the information environment to their liking”
Analyzed automatically with Semblen's fine-tuned model. These are manipulation techniques, not political tilt — and finding one is not a claim that the article is false. The model has known false positives on strong-but-legitimate language, so treat each finding as a prompt to read closely, not a verdict. How articles are chosen →