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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sensibilities
    -0.72
    enegger
    -0.70
     referen
    -0.64
    iates
    -0.63
    osate
    -0.61
     spokes
    -0.60
    ufact
    -0.59
     philos
    -0.59
     drones
    -0.58
     indo
    -0.58
    POSITIVE LOGITS
    anza
    0.75
    quart
    0.71
    ASH
    0.71
    bid
    0.70
    Search
    0.68
    irc
    0.66
    Ļ½
    0.66
    aughlin
    0.66
    ashing
    0.64
    acio
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.