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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lok
    -0.08
    消防
    -0.07
     strstr
    -0.07
     Pare
    -0.07
    nsic
    -0.07
     rek
    -0.07
    保障
    -0.07
    ,char
    -0.07
    打通
    -0.07
    صبح
    -0.07
    POSITIVE LOGITS
     Contracts
    0.09
     المملكة
    0.07
     المحلي
    0.07
    דמו
    0.07
    LANGUAGE
    0.07
    .TextAlignment
    0.07
    .Primary
    0.07
    .expression
    0.07
     transports
    0.07
     espionage
    0.07
    Act Density 0.001%

    No Known Activations