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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical appearances and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to human-like appearances or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sources
    -0.82
    nesday
    -0.80
    liga
    -0.79
    ciplinary
    -0.73
    piracy
    -0.73
    Fund
    -0.72
    Free
    -0.70
    ETF
    -0.70
     Mandatory
    -0.69
    Ô
    -0.69
    POSITIVE LOGITS
     attire
    1.63
     complexion
    1.62
     hairst
    1.61
     facial
    1.59
     silhouette
    1.57
     appearance
    1.55
     likeness
    1.55
     physique
    1.55
     demeanor
    1.54
     tattoos
    1.49
    Act Density 0.516%

    No Known Activations