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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iqueness
    -0.78
    riv
    -0.73
    onda
    -0.71
    nce
    -0.71
    iction
    -0.69
    deals
    -0.68
    oped
    -0.67
    efe
    -0.66
    ictions
    -0.66
    uthor
    -0.64
    POSITIVE LOGITS
    prototype
    0.73
     Interstellar
    0.73
    frames
    0.71
     onset
    0.70
    _>
    0.67
     horizon
    0.64
    leigh
    0.63
     seas
    0.61
     stages
    0.61
     ESA
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.