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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    alco
    0.64
    oros
    0.61
    issati
    0.61
     ✅
    0.60
     admires
    0.60
     часто
    0.59
     Fallon
    0.59
     CAD
    0.58
    ecoin
    0.58
    🪙
    0.58
    POSITIVE LOGITS
    由于
    0.66
    编辑
    0.66
    因为
    0.63
    原因是
    0.61
    １
    0.59
    通过
    0.59
    根据
    0.57
    失去
    0.57
    修改
    0.56
     quand
    0.56
    Act Density 0.000%

    No Known Activations