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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hani
    -0.84
    VIDIA
    -0.77
    enegger
    -0.72
    âĺħâĺħ
    -0.71
    Introduced
    -0.68
    ividual
    -0.67
    oln
    -0.64
    DonaldTrump
    -0.64
    liam
    -0.64
    ellar
    -0.62
    POSITIVE LOGITS
    bowl
    0.75
    trap
    0.70
    atra
    0.68
    etus
    0.68
     bureau
    0.68
    fork
    0.66
     Rhythm
    0.66
     Gleaming
    0.65
    Loop
    0.65
     Loop
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.