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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     consequential
    -0.75
    olin
    -0.70
    POSE
    -0.69
    istani
    -0.65
    FORE
    -0.64
     overrun
    -0.62
     inhal
    -0.62
     fetch
    -0.61
     prem
    -0.61
     conditional
    -0.60
    POSITIVE LOGITS
    ãĥķãĤ¡
    0.74
     Blocks
    0.68
     Badge
    0.66
    stals
    0.65
     Clever
    0.64
    illy
    0.62
    Truth
    0.61
    anooga
    0.61
    ounces
    0.61
     Fair
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.