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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or estimates

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "many" to indicate quantities or large numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brav
    -0.73
     Veil
    -0.66
    agher
    -0.65
    ĺħ
    -0.62
    maxwell
    -0.62
     Powered
    -0.61
    Ļ½
    -0.61
    ardo
    -0.60
     Butterfly
    -0.59
    lance
    -0.59
    POSITIVE LOGITS
    azi
    0.68
     KN
    0.66
     AS
    0.63
    antz
    0.63
    assian
    0.62
    theless
    0.61
     copies
    0.61
     digits
    0.61
     Than
    0.60
    ongh
    0.60
    Act Density 0.034%

    No Known Activations