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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    holes
    -0.81
     warr
    -0.80
    hole
    -0.76
    bub
    -0.71
    usage
    -0.70
    tz
    -0.70
     Mub
    -0.69
    verse
    -0.68
     grievances
    -0.66
    izzard
    -0.65
    POSITIVE LOGITS
    hyde
    0.69
    icity
    0.63
     Norn
    0.60
     2020
    0.60
     redesign
    0.60
     Silva
    0.58
     Trend
    0.58
    aryl
    0.58
     Samoa
    0.57
    ij士
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.