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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Fox
    -0.07
     pimp
    -0.07
     pills
    -0.07
     Scalar
    -0.07
    blings
    -0.07
    وضوع
    -0.07
     Devils
    -0.07
    (pb
    -0.07
    (dialog
    -0.07
     Nylon
    -0.07
    POSITIVE LOGITS
     WAN
    0.08
    商学院
    0.07
    ętr
    0.07
    etrain
    0.07
     catchError
    0.07
     extra
    0.07
    受影响
    0.07
    #ab
    0.07
    הצלחת
    0.07
    🔑
    0.07
    Act Density 0.005%

    No Known Activations