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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    scale
    -0.67
    ize
    -0.65
    isations
    -0.65
     scale
    -0.64
    cale
    -0.64
    æ©
    -0.62
    oided
    -0.62
     Maduro
    -0.61
     Cald
    -0.61
    izations
    -0.61
    POSITIVE LOGITS
     sul
    0.85
    AU
    0.79
    gart
    0.73
    asley
    0.72
    eps
    0.71
    taboola
    0.71
    acker
    0.71
    azing
    0.70
    Quotes
    0.67
    atis
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.