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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.80
    ĸļ
    -0.67
     species
    -0.67
     exped
    -0.65
     reservation
    -0.65
     inclusive
    -0.64
    NetMessage
    -0.63
    CLASS
    -0.63
    OPLE
    -0.63
    BOX
    -0.62
    POSITIVE LOGITS
    ittens
    0.90
    ernels
    0.79
    oshenko
    0.77
    Downloadha
    0.77
    bral
    0.75
    atos
    0.73
    leigh
    0.72
    iller
    0.71
    hest
    0.71
    ritz
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.