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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to "the planet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    headers
    -0.91
    RFC
    -0.76
    Ô
    -0.75
    DOS
    -0.75
    Es
    -0.72
     largeDownload
    -0.71
    CHA
    -0.69
    Priv
    -0.69
    nyder
    -0.68
    dos
    -0.68
    POSITIVE LOGITS
    arium
    1.26
     Ceres
    0.98
     planet
    0.97
     Earth
    0.92
    ouched
    0.90
    oid
    0.86
     Venus
    0.86
    wide
    0.86
    ogram
    0.85
    eers
    0.85
    Act Density 0.013%

    No Known Activations