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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fame
    -0.69
     Played
    -0.64
     Aly
    -0.64
     redemption
    -0.63
     opener
    -0.63
     champ
    -0.62
    rium
    -0.61
    imaru
    -0.61
     mir
    -0.60
    vati
    -0.60
    POSITIVE LOGITS
    %-
    0.90
    th
    0.88
     percent
    0.88
    %"
    0.87
     CFR
    0.82
     Percent
    0.81
    %
    0.79
    %.
    0.76
     Deg
    0.76
    CDC
    0.76
    Act Density 0.347%

    No Known Activations