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

    Neuronpedia

    INDEX
    Explanations

    locations or people's names, specifically the surname "Ende" and the name "Michele"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ende" and various names or terms related to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.76
    rooms
    -0.68
    hip
    -0.68
    istically
    -0.67
    itarian
    -0.66
    Lewis
    -0.64
    loss
    -0.62
    killers
    -0.62
    raq
    -0.62
    igraph
    -0.62
    POSITIVE LOGITS
    ende
    0.98
    ña
    0.86
    bris
    0.82
    ñ
    0.72
    jas
    0.72
    avor
    0.71
    anie
    0.71
    leted
    0.71
    qual
    0.69
    Å¡
    0.68
    Act Density 0.013%

    No Known Activations