Attribution graph comparison

clinicaloff-targetstructuralnode size = attribution masscurve width/opacity = |attribution weight|red curve = negativehover 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”) = 0.04embL0L5L10L15L20L25logit⋮“gym” · prob 0.18“doctor” · prob 0.18“hospital” · prob 0.14“pharmacy” · prob 0.04“cardio” · prob 0.04<bos>EverytimeIbeclimbingthemstairsIfeeltachycardia,sothisafternoonIbeheadingtothe407471 weakest edges omittedRegister shift Δ (B → D): —shared circuit dimmed: 1128 features in both · 260 only in B · 313 only in DD · 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”embL0L5L10L15L20L25logit⋮“gym” · prob 0.29“top” · prob 0.12“doctor” · prob 0.07“hospital” · prob 0.03“beach” · prob 0.02<bos>EverytimeIbeclimbingthemstairsIfeelmyheartracing,sothisafternoonIbeheadingtothe400483 weakest edges omitted