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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    names or terms associated with individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulators
    -0.79
    fram
    -0.78
    sburgh
    -0.75
    inventoryQuantity
    -0.73
    itudes
    -0.71
    ulatory
    -0.69
    ocene
    -0.68
    ãģĻ
    -0.68
    âĸĪâĸĪ
    -0.67
    ][/
    -0.66
    POSITIVE LOGITS
    hyde
    0.84
    ynamic
    0.81
    cember
    0.75
    rolet
    0.75
    ynam
    0.73
     Mub
    0.73
    backs
    0.72
    ennes
    0.70
    VID
    0.69
    onna
    0.66
    Act Density 0.240%

    No Known Activations