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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific number

    oai_token-act-pair · gpt-3.5-turbo

    numerical references or identifiers related to data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shape
    -0.67
    ardless
    -0.66
    ifully
    -0.66
    fare
    -0.64
    liga
    -0.64
    iful
    -0.62
    orem
    -0.62
    velt
    -0.61
    fall
    -0.61
    urus
    -0.59
    POSITIVE LOGITS
    00
    0.93
     Sins
    0.75
    th
    0.71
    mm
    0.70
    rd
    0.70
    olog
    0.69
    acht
    0.69
    oche
    0.68
    åĤ
    0.68
     Thieves
    0.67
    Act Density 0.033%

    No Known Activations