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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anto
    -0.90
    iw
    -0.85
    igr
    -0.78
    udeb
    -0.78
    jew
    -0.75
    displayText
    -0.75
    achi
    -0.74
    istine
    -0.74
    ander
    -0.72
    FOX
    -0.72
    POSITIVE LOGITS
     Persona
    0.65
     Petr
    0.64
     Presence
    0.64
     airspace
    0.62
     compos
    0.62
    senal
    0.62
    etheless
    0.61
     Candle
    0.61
     Masquerade
    0.60
     Byz
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.