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

    Neuronpedia

    INDEX
    Explanations

    references to high-quality or high-performance attributes across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.54
    tent
    -0.51
    opsis
    -0.49
    lun
    -0.49
    GeneratedCode
    -0.49
     Cordero
    -0.47
    agenda
    -0.47
     '\\;'
    -0.47
    erjee
    -0.46
    trn
    -0.46
    POSITIVE LOGITS
     high
    1.57
     High
    1.54
    High
    1.48
    high
    1.41
     HIGH
    1.34
    HIGH
    1.28
    高
    1.02
     yüksek
    1.00
     tinggi
    0.97
     vysok
    0.96
    Act Density 0.203%

    No Known Activations