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

    Neuronpedia

    INDEX
    Explanations

    names and numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.68
    natureconservancy
    -0.68
    Shares
    -0.66
     Reborn
    -0.63
    uca
    -0.63
    KEY
    -0.62
    pak
    -0.61
    zynski
    -0.60
    ONEY
    -0.59
    grave
    -0.58
    POSITIVE LOGITS
    tenance
    1.12
    llor
    0.90
    acters
    0.89
    osterone
    0.85
    lihood
    0.83
    quartered
    0.81
    riors
    0.79
    clusive
    0.76
    iste
    0.75
    ruction
    0.75
    Act Density 3.434%

    No Known Activations