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

    Neuronpedia

    INDEX
    Explanations

    references to security in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sauvages
    -0.61
     MainAxisSize
    -0.60
     confezione
    -0.59
     unto
    -0.59
     religieuses
    -0.57
    fromnode
    -0.57
    -0.56
    XmlAccessorType
    -0.55
     sexuales
    -0.55
     notizia
    -0.54
    POSITIVE LOGITS
     safety
    1.75
     security
    1.45
     Safety
    1.38
    safety
    1.34
    Safety
    1.30
     SAFETY
    1.09
    security
    1.09
     Security
    1.06
     stability
    1.06
     welfare
    1.06
    Act Density 0.101%

    No Known Activations