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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Nob
    -0.75
    Adds
    -0.72
    aston
    -0.71
    Helper
    -0.69
    sylvania
    -0.69
    Increases
    -0.67
    ener
    -0.64
    esis
    -0.63
    onis
    -0.61
    ossal
    -0.61
    POSITIVE LOGITS
    ©¶æ
    0.70
    teness
    0.67
    ciples
    0.67
    cies
    0.66
     Blazers
    0.64
    ufact
    0.64
     Meridian
    0.62
    00200000
    0.62
    agin
    0.62
     Pixar
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.