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

    Neuronpedia

    INDEX
    Explanations

    greeting-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to greetings and welcoming interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    negie
    -0.78
    cano
    -0.70
    proxy
    -0.66
    moral
    -0.65
    ulz
    -0.64
    Gray
    -0.64
    criminal
    -0.64
    anyon
    -0.63
     inhibitor
    -0.62
    gur
    -0.61
    POSITIVE LOGITS
     greet
    1.07
     greeting
    1.02
    enance
    0.89
     greets
    0.86
    issance
    0.85
    eering
    0.83
     politely
    0.81
     greeted
    0.81
     goodbye
    0.80
    reetings
    0.78
    Act Density 0.038%

    No Known Activations