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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or recollection

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.80
    utenberg
    -0.80
    english
    -0.76
    luaj
    -0.75
    BuyableInstoreAndOnline
    -0.73
    acco
    -0.72
    aez
    -0.70
    indal
    -0.66
    arthed
    -0.63
    rang
    -0.62
    POSITIVE LOGITS
    terday
    0.83
     WHAT
    0.82
     what
    0.78
     how
    0.69
    what
    0.67
     why
    0.66
    ledged
    0.66
     whats
    0.65
    ees
    0.63
     imagine
    0.61
    Act Density 0.015%

    No Known Activations