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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lia
    -0.75
    inar
    -0.65
     Asc
    -0.64
     pardon
    -0.63
    ori
    -0.62
     lodge
    -0.62
    Pie
    -0.62
    ollywood
    -0.61
    inis
    -0.61
     ashes
    -0.61
    POSITIVE LOGITS
    Downloadha
    0.83
    inventoryQuantity
    0.75
    iencies
    0.69
    Bey
    0.69
    vere
    0.65
    ected
    0.65
    vati
    0.62
     Palestin
    0.60
     Leban
    0.60
    osate
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.