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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atable
    -0.85
     Norn
    -0.69
    fork
    -0.69
     TBD
    -0.69
    Tam
    -0.69
    Broad
    -0.65
    moderate
    -0.65
     Nun
    -0.64
     Bethesda
    -0.64
    onom
    -0.64
    POSITIVE LOGITS
     ..........
    0.75
    SHIP
    0.72
    ertodd
    0.70
    ×ŀ
    0.69
     {\
    0.68
     lett
    0.67
    uries
    0.67
    ]}
    0.67
     VIDEOS
    0.67
    =-=-
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.