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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.62
     AssemblyTitle
    -0.58
     متعلقه
    -0.58
     plenty
    -0.56
    คัญ
    -0.52
     preocupes
    -0.52
    reszcie
    -0.51
     saker
    -0.51
    Тема
    -0.51
    onomía
    -0.51
    POSITIVE LOGITS
     choice
    0.71
     qual
    0.69
     clue
    0.64
     ObjectParameter
    0.58
     filter
    0.58
     basis
    0.57
     CHOICE
    0.57
     recourse
    0.57
     pretense
    0.56
     concept
    0.56
    Act Density 0.211%

    No Known Activations