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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pun
    0.70
     acer
    0.70
     darg
    0.68
     private
    0.67
     manger
    0.67
     prest
    0.66
    ierten
    0.66
     professional
    0.65
    まぁ
    0.65
     vanity
    0.64
    POSITIVE LOGITS
    덟
    0.92
    ണ്ട്
    0.90
     газо
    0.87
     Falcons
    0.84
     vasodilator
    0.84
     hipótesis
    0.83
    嵃
    0.82
    ḕ
    0.82
    డి
    0.81
    శ్
    0.80
    Act Density 0.000%

    No Known Activations