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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cultures
    -0.65
     broadcasts
    -0.63
     lengths
    -0.61
     Seah
    -0.61
     Wake
    -0.61
    amins
    -0.61
     Flare
    -0.60
     clicks
    -0.60
     Mosque
    -0.59
     payday
    -0.59
    POSITIVE LOGITS
    ihar
    0.98
    leeve
    0.91
    enum
    0.85
    oi
    0.81
    itu
    0.79
    olulu
    0.78
    uple
    0.77
    ainers
    0.76
    urga
    0.74
    acio
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.