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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     started
    0.79
     initial
    0.79
     tapered
    0.73
     dreaded
    0.67
     board
    0.66
     start
    0.66
     plane
    0.66
     vivi
    0.66
    인데
    0.65
     void
    0.64
    POSITIVE LOGITS
    ة
    0.81
    speakers
    0.73
     Laufe
    0.73
    Superhero
    0.70
    jsonplaceholder
    0.70
    membre
    0.69
    անդ
    0.69
    льных
    0.68
    ளை
    0.68
    <0xD4>
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.