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

    Neuronpedia

    INDEX
    Explanations

    references to experimental conditions or settings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.48
     (
    -0.46
     otherwise
    -0.43
     chá
    -0.40
     rowspan
    -0.40
    ب
    -0.40
    äuser
    -0.40
    ite
    -0.39
    bon
    -0.38
    (.
    -0.38
    POSITIVE LOGITS
     contextLoads
    0.82
    '],
    0.79
     ويكيميديا
    0.75
    esterday
    0.74
    ).}
    0.74
    ">:
    0.74
    ']],
    0.74
    ➟
    0.73
    ']))
    0.73
     BoxDecoration
    0.72
    Act Density 0.093%

    No Known Activations