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

    Neuronpedia

    INDEX
    Explanations

    the word "Hi" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    greetings or variations of "hi."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.87
     Awakens
    -0.85
    */(
    -0.79
     rall
    -0.69
    lain
    -0.69
    Dialogue
    -0.67
    parts
    -0.65
    女
    -0.65
     destro
    -0.64
     Gleaming
    -0.64
    POSITIVE LOGITS
    earch
    0.97
    Fi
    0.88
    pped
    0.81
    pping
    0.80
    dden
    0.79
    roy
    0.75
    Bs
    0.73
    ya
    0.72
    kson
    0.72
    ature
    0.71
    Act Density 0.015%

    No Known Activations