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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     using
    0.59
     in
    0.49
     use
    0.48
     novos
    0.46
     ingeniería
    0.45
    using
    0.43
     menggunakan
    0.42
     nueva
    0.42
     =
    0.41
    ەیە
    0.41
    POSITIVE LOGITS
    ❣️
    0.50
    😖
    0.50
    !।
    0.47
    并没有
    0.47
    ServiceGroupID
    0.47
    มุม
    0.46
    ！
    0.46
     लीजिएगा
    0.45
     потеря
    0.45
    🥺
    0.44
    Act Density 0.019%

    No Known Activations