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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    R
    0.57
    water
    0.54
    alaman
    0.51
    b
    0.50
    stan
    0.48
    history
    0.48
    book
    0.47
    average
    0.46
    path
    0.46
    div
    0.46
    POSITIVE LOGITS
     Canucks
    0.50
     consid
    0.48
     hunk
    0.48
    这也
    0.48
     العام
    0.47
     kän
    0.47
    𝙮
    0.47
     overhauled
    0.46
     gutes
    0.46
     chcesz
    0.44
    Act Density 0.003%

    No Known Activations