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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     квартир
    -0.08
     Intel
    -0.08
     del
    -0.07
    を開
    -0.07
    ;$
    -0.07
    <u
    -0.07
    	dialog
    -0.06
     bureau
    -0.06
    icals
    -0.06
     delim
    -0.06
    POSITIVE LOGITS
    .compute
    0.07
    vect
    0.07
     lest
    0.07
    _attempt
    0.07
    支线任务
    0.07
    agate
    0.07
     decomposition
    0.07
     consectetur
    0.07
    身心
    0.07
    🤥
    0.07
    Act Density 0.433%

    No Known Activations