Update README.md

README.md

@@ -23,4 +23,4 @@ This model is trained on the labels extracted with GPT-4.1, these labels were co
 about 0.83(Pearson).
 
 In 10-fold cross-validation the model scored f1,precision and recall of about 93%, the model uploaded here was 1 fold from a 40-fold split, and obtained 90% (f1,prec,rec).
-Note: this scoring was obtained with the stand 0.5 proba threshold.
+Note: this scoring was obtained with the default 0.5 proba threshold.