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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     musical
    -0.07
    auté
    -0.07
    (Code
    -0.07
    מרה
    -0.07
     Müller
    -0.07
     specifications
    -0.07
    <Model
    -0.07
    .Protocol
    -0.07
     dance
    -0.07
     JL
    -0.07
    POSITIVE LOGITS
    겤
    0.07
     tạo
    0.07
    Ҝ
    0.07
    _None
    0.07
     privileged
    0.07
    괭
    0.06
    面临的
    0.06
    幣
    0.06
    qc
    0.06
     potentially
    0.06
    Act Density 0.016%

    No Known Activations