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

    Neuronpedia

    INDEX
    Explanations

    uncertainties and questions about knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    凰
    -0.48
    Finally
    -0.48
     Finally
    -0.46
    ={`
    -0.46
     Ex
    -0.46
     упа
    -0.45
    新
    -0.45
     Newly
    -0.45
     Previously
    -0.45
    Emer
    -0.45
    POSITIVE LOGITS
     unknow
    0.85
     unknown
    0.84
     Unknown
    0.80
     desconhe
    0.79
     dunno
    0.77
    我不知道
    0.76
    unknown
    0.71
     AssemblyCulture
    0.71
     unclear
    0.70
     unsure
    0.70
    Act Density 0.304%

    No Known Activations