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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to controversial or sensitive topics, potentially skewed towards medical or political subjects

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and cultural sensitivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luster
    -0.52
     Nare
    -0.50
    farious
    -0.50
    sylv
    -0.48
    Ire
    -0.47
     withd
    -0.47
    orage
    -0.46
    anon
    -0.46
    nesota
    -0.46
    nesday
    -0.45
    POSITIVE LOGITS
    )?
    0.77
    ?)
    0.70
    )</
    0.68
    )/
    0.66
    ?).
    0.65
    )
    0.65
    !)
    0.64
    !).
    0.63
    -)
    0.63
    !),
    0.62
    Act Density 1.105%

    No Known Activations