Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    STAR
    -0.74
     collaborators
    -0.63
     Awards
    -0.63
     externalToEVAOnly
    -0.59
     HERO
    -0.59
    Star
    -0.57
     distinctions
    -0.57
     applause
    -0.57
    Cele
    -0.57
    Sad
    -0.57
    POSITIVE LOGITS
    ioxide
    0.86
    ravel
    0.80
    phalt
    0.78
    venture
    0.76
     guiActive
    0.72
    ization
    0.71
    iffe
    0.70
    edin
    0.69
    oided
    0.69
    olphin
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.