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

    Neuronpedia

    INDEX
    Explanations

    sentences related to examining or exploring different topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to books and their critical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.75
     Izan
    -0.74
    Anyway
    -0.71
    ãĤ¨ãĥ«
    -0.69
     Presumably
    -0.69
     Anyway
    -0.67
    Associated
    -0.64
     externalToEVAOnly
    -0.64
    uez
    -0.63
     anyway
    -0.61
    POSITIVE LOGITS
     curated
    0.79
     innovative
    0.75
    ersive
    0.74
     immersive
    0.73
     premier
    0.72
    eaturing
    0.71
     challeng
    0.71
     uncover
    0.69
     showcasing
    0.68
     groundbreaking
    0.66
    Act Density 0.816%

    No Known Activations