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

    Neuronpedia

    INDEX
    Explanations

    greetings and introductions in written communication

    oai_token-act-pair · gpt-3.5-turbo

    conversational greetings and informal introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilitarian
    -0.87
     endif
    -0.75
     divest
    -0.68
    unning
    -0.66
     dehuman
    -0.65
    VERTISEMENT
    -0.65
    conom
    -0.64
    CONCLUS
    -0.63
     shrink
    -0.61
     stunts
    -0.60
    POSITIVE LOGITS
     Welcome
    0.91
    Welcome
    0.90
    thanks
    0.87
    Hello
    0.86
     hello
    0.85
     welcome
    0.83
    reetings
    0.83
    today
    0.77
    Morning
    0.76
    Exc
    0.76
    Act Density 0.259%

    No Known Activations