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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <Unit
    -0.08
     noticeably
    -0.07
     throwable
    -0.07
     explosion
    -0.07
     כדי
    -0.07
     PLUS
    -0.07
     isVisible
    -0.07
    ﮼
    -0.06
     actionTypes
    -0.06
     ayant
    -0.06
    POSITIVE LOGITS
    forge
    0.07
    وفق
    0.07
    Jessica
    0.07
    (symbol
    0.07
    пон
    0.07
    ilded
    0.07
    format
    0.06
    Виде
    0.06
     ба
    0.06
    咪
    0.06
    Act Density 0.003%

    No Known Activations