Attribution graph comparison

clinicaloff-targetstructuralnode size = attribution masscurve width/opacity = |attribution weight|red curve = negativehover or tap any node for details
C · Patient-derived language + standard morphosyntax (register shift only)“Every time I climb the stairs I feel my heart racing, so this afternoon I am heading to the”embL0L5L10L15L20L25logit⋮“gym” · prob 0.35“doctor” · prob 0.09“local” · prob 0.03“physio” · prob 0.03“top” · prob 0.03<bos>EverytimeIclimbthestairsIfeelmyheartracing,sothisafternoonIamheadingtothe441601 weakest edges omittedVariety shift Δ (C → D): —shared circuit dimmed: 1093 features in both · 364 only in C · 348 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