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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rosenberg
    0.68
     ایست
    0.67
     Entering
    0.66
     Hei
    0.65
     Lamar
    0.65
     Arthur
    0.64
    ようになった
    0.64
     begonnen
    0.64
     Coal
    0.63
     Marguerite
    0.63
    POSITIVE LOGITS
    我
    0.80
    破損
    0.71
    ॓
    0.69
    আমি
    0.68
     ১
    0.66
     cuisson
    0.66
    款式
    0.66
    甜蜜
    0.65
    ло
    0.64
    де
    0.64
    Act Density 0.047%

    No Known Activations