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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ske
    -0.83
    ¿½
    -0.76
    ãĤ¦ãĤ¹
    -0.74
    Ĥª
    -0.74
     Curve
    -0.72
     grading
    -0.68
     Celsius
    -0.67
    cale
    -0.67
     gradient
    -0.67
     biases
    -0.66
    POSITIVE LOGITS
    emp
    0.95
    fred
    0.78
    nar
    0.74
    INS
    0.74
    inson
    0.72
    anos
    0.70
    ern
    0.70
    uay
    0.69
    azon
    0.68
    ctors
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.