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

    Neuronpedia

    INDEX
    Explanations

    text related to questioning or seeking information about past events or occurrences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUn
    -0.87
    voy
    -0.71
    rehens
    -0.69
     Uses
    -0.63
    clair
    -0.62
    hari
    -0.62
    à¼
    -0.62
    artisan
    -0.61
    orney
    -0.61
     laun
    -0.61
    POSITIVE LOGITS
    othy
    0.77
     those
    0.73
     them
    0.71
     us
    0.71
     him
    0.71
     innoc
    0.71
     Singer
    0.71
     innocent
    0.67
     mankind
    0.65
     trillions
    0.64
    Act Density 0.053%

    No Known Activations