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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Samara
    -0.85
    %>
    -0.81
    mento
    -0.81
    CharArray
    -0.76
    ):
    -0.74
     Samaritan
    -0.73
    舎
    -0.72
    iato
    -0.71
    态度
    -0.71
     Lacy
    -0.71
    POSITIVE LOGITS
    IRMED
    0.83
    ocusing
    0.83
    Cooking
    0.80
     upd
    0.79
     видно
    0.75
     реакции
    0.74
    Mari
    0.73
    orance
    0.72
     φα
    0.72
    systemctl
    0.72
    Act Density 0.010%

    No Known Activations