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

    Neuronpedia

    INDEX
    Explanations

    data structure definitions and attributes in a JSON-like format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ")
    -0.86
    ”
    -0.79
    ”)
    -0.76
    =")
    -0.75
    "
    -0.75
    )
    -0.74
    "")
    -0.74
     []
    -0.74
    ')
    -0.74
    ")
    -0.71
    POSITIVE LOGITS
    `,
    1.23
    ",
    1.19
    ',
    1.16
    »,
    1.14
    ?",
    1.12
     »,
    1.11
    ?,
    1.10
    '',
    1.10
    .},
    1.08
    ”,
    1.08
    Act Density 0.599%

    No Known Activations