INDEX
    Explanations

    UI affordances

    New Auto-Interp
    Negative Logits
    Manager
    -0.09
     Bloomberg
    -0.08
    Overview
    -0.07
    Snapshot
    -0.07
    _MANAGER
    -0.07
     kosong
    -0.07
    Detail
    -0.07
    _MAIN
    -0.07
    Scheduler
    -0.07
    _connect
    -0.07
    POSITIVE LOGITS
     unfamiliar
    0.10
     escond
    0.09
     kennt
    0.09
     recognizable
    0.09
     Know
    0.09
    عليم
    0.09
     ubicación
    0.09
    Know
    0.09
     deceptive
    0.08
     seas
    0.08
    Act Density 0.010%

    No Known Activations