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

    Neuronpedia

    INDEX
    Explanations

    phrases related to business and finance

    oai_token-act-pair · gpt-3.5-turbo

    phrases or symbols related to various topics or concepts presented in a fragmented way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     misunder
    -0.77
     satell
    -0.74
    anmar
    -0.70
     attorney
    -0.69
     incorpor
    -0.68
    hran
    -0.67
    inous
    -0.65
     encount
    -0.65
     condem
    -0.65
     aven
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.15
     etc
    0.98
    which
    0.94
    Secondly
    0.92
    âĻ
    0.92
     Similarly
    0.91
    STEM
    0.89
     whereas
    0.88
     Likewise
    0.88
    âĢł
    0.87
    Act Density 0.313%

    No Known Activations