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

    Neuronpedia

    INDEX
    Explanations

    themes related to imminent danger and risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekim
    -0.14
    beros
    -0.13
    532
    -0.13
     khúc
    -0.13
    _firestore
    -0.13
    Leaks
    -0.13
    ç¸
    -0.13
    iny
    -0.13
    559
    -0.13
    ickets
    -0.13
    POSITIVE LOGITS
     danger
    1.00
     dangers
    0.83
     Danger
    0.80
     threat
    0.78
     risk
    0.75
    danger
    0.75
     dangerous
    0.73
    -danger
    0.72
     hazard
    0.70
    åį±
    0.68
    Act Density 0.560%

    No Known Activations