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

    Neuronpedia

    INDEX
    Explanations

    words related to greetings

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    negie
    -0.78
    ulz
    -0.68
    proxy
    -0.68
    uld
    -0.66
    cano
    -0.65
    aq
    -0.65
    icum
    -0.65
     inhibitors
    -0.63
     inhibitor
    -0.63
    eki
    -0.63
    POSITIVE LOGITS
     greet
    1.20
     greeting
    1.15
     greets
    0.94
     greeted
    0.90
    enance
    0.85
     hello
    0.82
     goodbye
    0.82
    reetings
    0.79
    prise
    0.78
    mallow
    0.78
    Act Density 0.019%

    No Known Activations