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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kat
    -0.73
     Palest
    -0.71
     Chou
    -0.66
     Baz
    -0.65
     ATP
    -0.65
    cart
    -0.65
    escap
    -0.65
    kefeller
    -0.65
     simultane
    -0.65
     Leban
    -0.65
    POSITIVE LOGITS
    otten
    0.75
    ioxide
    0.69
     Insect
    0.68
    ptic
    0.66
    ĨĴ
    0.66
    ipel
    0.65
     Nebula
    0.65
    ylum
    0.64
    INESS
    0.62
    oths
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.