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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é»Ĵ
    -0.78
    EAR
    -0.64
    ious
    -0.62
    ahah
    -0.62
     Graves
    -0.61
    FFFF
    -0.60
    helm
    -0.60
    locks
    -0.60
     Destruction
    -0.59
     Baal
    -0.59
    POSITIVE LOGITS
    iary
    0.81
    iaries
    0.71
    izons
    0.70
    cart
    0.69
    pez
    0.66
    unal
    0.64
    azeera
    0.63
    egal
    0.62
     vitro
    0.61
    phthal
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.