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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     v
    -0.07
     לב
    -0.07
    泞
    -0.07
    习
    -0.07
    罢
    -0.07
    /plain
    -0.06
     regret
    -0.06
    工人
    -0.06
    はじめ
    -0.06
    م
    -0.06
    POSITIVE LOGITS
     Haupt
    0.08
    HASH
    0.07
    淡淡的
    0.07
    บาคาร
    0.07
     Wohnung
    0.07
     empowered
    0.07
     tamanho
    0.07
    上报
    0.06
     exceeded
    0.06
    㵐
    0.06
    Act Density 0.000%

    No Known Activations