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

    Neuronpedia

    INDEX
    Explanations

    string keys and associated values in a JSON-like format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entanto
    -0.81
     Fergus
    -0.75
     Furman
    -0.73
     Gier
    -0.73
    ajur
    -0.72
    ghijkl
    -0.71
    𝐱
    -0.71
    likle
    -0.70
    aData
    -0.70
    prav
    -0.70
    POSITIVE LOGITS
    '",
    1.07
    ",
    1.05
    )".
    1.01
    )",
    1.00
    __*/
    1.00
    '".
    0.96
    )":
    0.92
    ']").
    0.92
     Walpole
    0.92
    ]",
    0.89
    Act Density 0.132%

    No Known Activations