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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    metics
    -0.92
    istar
    -0.80
    rencies
    -0.79
    rely
    -0.79
     Despair
    -0.76
    vantage
    -0.69
    iants
    -0.69
    gpu
    -0.68
    icans
    -0.67
    ittens
    -0.67
    POSITIVE LOGITS
     anatomy
    0.72
    orno
    0.69
     mash
    0.64
    english
    0.63
     respectful
    0.63
     satisfactory
    0.62
     revolving
    0.60
     Buch
    0.59
     uninterrupted
    0.59
     undercover
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.