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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment and evaluation regarding experiences and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.58
     danger
    -0.50
    EndProject
    -0.48
    threat
    -0.48
    enetrable
    -0.48
     démon
    -0.47
     dangerous
    -0.47
    toxicity
    -0.47
     olev
    -0.47
    dangerous
    -0.46
    POSITIVE LOGITS
    endregion
    0.69
     صوتيه
    0.65
    XmlAccessorType
    0.63
    endpush
    0.62
    //});
    0.59
    ValueGenerated
    0.59
    jalá
    0.59
     Савезне
    0.58
     škoda
    0.58
    tdessen
    0.57
    Act Density 0.325%

    No Known Activations