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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    axy
    -0.92
     However
    -0.89
     contains
    -0.86
     what
    -0.86
     should
    -0.86
     in
    -0.85
     their
    -0.84
     within
    -0.83
    結束
    -0.82
     seconda
    -0.81
    POSITIVE LOGITS
    tione
    0.95
     Nineteenth
    0.93
     seront
    0.92
    сибир
    0.90
     prezen
    0.90
     プリント
    0.89
     trente
    0.88
    potentially
    0.87
     formular
    0.86
     murmurs
    0.86
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.