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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly last names or full names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals and their last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.81
    ikarp
    -0.80
    uncture
    -0.79
    entious
    -0.76
    ansas
    -0.74
    teenth
    -0.74
    ificial
    -0.74
    owder
    -0.73
    olkien
    -0.73
    haust
    -0.73
    POSITIVE LOGITS
     Plaza
    1.01
     Mellon
    0.84
     Coliseum
    0.73
     Auction
    0.72
     Meadows
    0.68
     Enterprises
    0.68
    baugh
    0.67
     Clarkson
    0.67
     Crosby
    0.66
    abba
    0.66
    Act Density 0.017%

    No Known Activations