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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.81
    ...")
    -0.81
    ...]
    -0.81
    "),
    -0.79
    "],
    -0.79
    '],
    -0.78
    ...",
    -0.75
    ...}
    -0.73
    ..."
    -0.73
    .,"
    -0.73
    POSITIVE LOGITS
    *
    1.06
    **
    0.98
     *
    0.95
    (*
    0.95
     (*
    0.88
     **
    0.81
    8
    0.77
    6
    0.75
    3
    0.73
    (&
    0.68
    Act Density 0.207%

    No Known Activations