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

    Neuronpedia

    INDEX
    Explanations

    references to acts of honoring or showing respect towards someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to tributes or commemorations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucket
    -0.72
    lower
    -0.65
     Aden
    -0.65
    techn
    -0.64
    confidence
    -0.64
    handle
    -0.63
    iHUD
    -0.62
     Kers
    -0.62
    absolute
    -0.62
    FO
    -0.61
    POSITIVE LOGITS
     tribute
    0.93
     honors
    0.87
    giving
    0.85
    ribute
    0.85
    ributes
    0.84
     honoring
    0.84
    oise
    0.82
     appreciation
    0.76
     mourn
    0.75
     album
    0.75
    Act Density 0.018%

    No Known Activations