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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    alon
    -0.78
    ozo
    -0.72
    alion
    -0.71
    oad
    -0.71
    auga
    -0.70
    cles
    -0.69
    aukee
    -0.68
    ilon
    -0.68
    ta
    -0.68
    foundland
    -0.66
    POSITIVE LOGITS
    vernment
    0.76
    Introduced
    0.67
    Topic
    0.65
     warr
    0.65
     Pric
    0.65
    Category
    0.64
    earable
    0.64
    channelAvailability
    0.63
    Collection
    0.63
     pept
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.