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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    WARE
    -0.81
     spoilers
    -0.71
     actionGroup
    -0.69
    ails
    -0.65
    mage
    -0.62
     testers
    -0.62
    uitous
    -0.61
     flyers
    -0.61
    CLASSIFIED
    -0.60
    hare
    -0.60
    POSITIVE LOGITS
    1
    0.87
    erald
    0.74
    vana
    0.73
    Attach
    0.72
    cht
    0.71
    abc
    0.71
    daq
    0.69
    2
    0.68
    ño
    0.68
    0
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.