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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or important structural elements within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.96
    ViewFeatures
    -0.83
     estekak
    -0.72
    esgue
    -0.70
     BoxFit
    -0.69
     surla
    -0.69
     BorderRadius
    -0.67
    AxisAlignment
    -0.67
    Хро
    -0.65
     fVar
    -0.65
    POSITIVE LOGITS
     propOrder
    0.63
     @"/
    0.60
    ↵↵
    0.56
     tane
    0.55
    <bos>
    0.54
     Coelho
    0.50
     caballero
    0.49
    <eos>
    0.48
    Wheeler
    0.47
    ValueStyle
    0.46
    Act Density 1.088%

    No Known Activations