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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.76
     Cæsar
    -0.73
    iconque
    -0.69
     rabbi
    -0.69
    lujah
    -0.68
     Urbano
    -0.62
     Shakspeare
    -0.60
     Moslem
    -0.59
     constancy
    -0.59
     Majefty
    -0.59
    POSITIVE LOGITS
    <eos>
    0.71
    ↵
    0.70
    0.59
    abestanden
    0.52
     }{@
    0.51
     

    0.51
    Datuak
    0.51
    setcounter
    0.51
    قایناق‌لار
    0.49
    ↵↵↵
    0.48
    Act Density 0.000%
    No Known Activations
    This feature has no known activations.