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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bathrooms
    -0.72
     restrooms
    -0.72
    ospace
    -0.70
     extermination
    -0.66
     transitioned
    -0.65
     understatement
    -0.63
    ONSORED
    -0.62
     keyboards
    -0.62
     amusement
    -0.60
    Changing
    -0.60
    POSITIVE LOGITS
    sels
    0.73
    burg
    0.71
    ports
    0.70
    bil
    0.68
    errors
    0.68
     Ley
    0.65
    stal
    0.65
     CFR
    0.65
    eters
    0.64
    sever
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.