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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ة
    0.95
    É
    0.93
    一批
    0.93
     Aller
    0.89
     excit
    0.88
    Été
    0.88
     oce
    0.85
    Ｅ
    0.85
     energetically
    0.84
    黾
    0.83
    POSITIVE LOGITS
    ſelf
    1.16
    zelf
    1.13
    lined
    1.09
    ्स
    1.00
    ाइब
    0.98
    packer
    0.98
    ss
    0.97
    it
    0.96
    hline
    0.95
    lihat
    0.92
    Act Density 0.000%

    No Known Activations