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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <ApplicationUser
    -0.08
    ชา
    -0.08
    _EXTENDED
    -0.07
    _NUMERIC
    -0.07
    详细的
    -0.07
    的办法
    -0.07
    (CL
    -0.07
    .Var
    -0.07
    如实
    -0.07
    ทธ
    -0.07
    POSITIVE LOGITS
    帝国
    0.07
    起飞
    0.07
     orient
    0.07
     kẻ
    0.06
     threats
    0.06
     urz
    0.06
     Una
    0.06
     sabot
    0.06
    matic
    0.06
     הולדת
    0.06
    Act Density 0.008%

    No Known Activations