Attribution graph comparison clinical off-target structural node size = attribution mass curve width/opacity = |attribution weight|red curve = negative hover or tap any node for details
B · Medical lexicon + nonstandard morphosyntax (variety shift only) “Every time I be climbing them stairs I feel tachycardia, so this afternoon I be heading to the” prob(“cardio”) = 0.04 emb L0 L5 L10 L15 L20 L25 logit ⋮ “gym” · prob 0.18 “doctor” · prob 0.18 “hospital” · prob 0.14 “pharmacy” · prob 0.04 “cardio” · prob 0.04 <bos> Every time I be climbing them stairs I feel tachycardia, so this afternoon I be heading to the 407471 weakest edges omitted Register shift Δ (B → D): — shared circuit dimmed: 1128 features in both · 260 only in B · 313 only in D D · Patient-derived language + nonstandard morphosyntax (both axes shifted) “Every time I be climbing them stairs I feel my heart racing, so this afternoon I be heading to the” emb L0 L5 L10 L15 L20 L25 logit ⋮ “gym” · prob 0.29 “top” · prob 0.12 “doctor” · prob 0.07 “hospital” · prob 0.03 “beach” · prob 0.02 <bos> Every time I be climbing them stairs I feel my heart racing, so this afternoon I be heading to the 400483 weakest edges omitted