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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bonjour
    0.39
    劫
    0.39
     dissemin
    0.38
     amen
    0.37
     richtige
    0.36
    省级
    0.36
    的学生
    0.36
     Urb
    0.35
     아니다
    0.35
     Amen
    0.35
    POSITIVE LOGITS
    gano
    0.41
    BTW
    0.40
    otin
    0.39
    Training
    0.39
    RMS
    0.39
    Help
    0.38
    ופן
    0.38
    haria
    0.38
    ongan
    0.37
    nesi
    0.36
    Act Density 0.003%

    No Known Activations