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

    Neuronpedia

    INDEX
    Explanations

    greetings or welcoming phrases

    oai_token-act-pair · gpt-3.5-turbo

    greetings or welcome messages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificantly
    -0.79
     denies
    -0.76
    rities
    -0.73
    urat
    -0.72
    igion
    -0.72
    Ultimately
    -0.68
    ibles
    -0.67
    lying
    -0.66
     testified
    -0.66
     stunts
    -0.65
    POSITIVE LOGITS
     countdown
    0.90
     roundup
    0.79
     hearty
    0.78
     festive
    0.78
    reetings
    0.77
    Introdu
    0.75
     Episode
    0.75
    Guest
    0.75
     Welcome
    0.73
     installment
    0.73
    Act Density 0.520%

    No Known Activations