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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    unciation
    -0.07
     patri
    -0.07
     Jas
    -0.07
    電話
    -0.07
     welche
    -0.07
    Lady
    -0.07
     marty
    -0.06
     nou
    -0.06
    처리
    -0.06
     Vul
    -0.06
    POSITIVE LOGITS
    坡
    0.07
    大型
    0.07
    圾
    0.07
    堐
    0.07
    .Cast
    0.07
     folding
    0.07
    没法
    0.07
    ahir
    0.06
     pits
    0.06
     البنك
    0.06
    Act Density 0.007%

    No Known Activations