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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     widths
    0.42
    #[
    0.42
    蟎
    0.40
    widths
    0.40
    平时
    0.40
    鄔
    0.39
     valleys
    0.39
    _{\|
    0.39
    房間
    0.39
     인생
    0.38
    POSITIVE LOGITS
    ami
    0.40
    rou
    0.38
    dec
    0.38
    anner
    0.38
    wan
    0.38
    ha
    0.37
    elize
    0.37
    グ
    0.36
    button
    0.35
    layout
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.