INDEX
    Explanations

    references to body parts and sensory experiences

    New Auto-Interp
    Negative Logits
     vechi
    -0.54
    Np
    -0.51
    illots
    -0.50
    itoare
    -0.49
    ǔ
    -0.48
    umn
    -0.48
     brancas
    -0.46
    ThemeOverlay
    -0.46
     indor
    -0.46
    jdk
    -0.46
    POSITIVE LOGITS
    DebuggerNonUser
    0.66
     doorstep
    0.66
     AssemblyTitle
    0.63
    featureID
    0.58
     Delivered
    0.57
    Personensuche
    0.55
     viewType
    0.55
    ifoli
    0.53
    estacks
    0.53
    delivered
    0.53
    Act Density 0.514%

    No Known Activations