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

    Neuronpedia

    INDEX
    Explanations

    reference to the moon or lunar concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.94
    SourceChecksum
    -0.66
     Hilde
    -0.66
     Vasco
    -0.65
     Hartman
    -0.65
     Berber
    -0.64
    boldsymbol
    -0.63
     Berna
    -0.63
    Birmingham
    -0.63
    %)$
    -0.63
    POSITIVE LOGITS
     moon
    2.02
     Moon
    1.92
     MOON
    1.89
     moons
    1.77
    Moon
    1.76
    moon
    1.73
     Moons
    1.70
    MOON
    1.70
    moons
    1.54
    Moons
    1.52
    Act Density 0.012%

    No Known Activations