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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aido
    -0.77
     bells
    -0.71
    nces
    -0.68
     spur
    -0.65
     hid
    -0.61
     attendant
    -0.59
    erald
    -0.59
    uits
    -0.58
    ulet
    -0.58
    riages
    -0.58
    POSITIVE LOGITS
    à©
    0.92
    MAL
    0.91
    âĹ¼
    0.83
    é¾į
    0.80
    Unknown
    0.77
    âĢ
    0.75
    Shell
    0.70
    partisan
    0.69
    OWN
    0.69
    Prof
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.