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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    safe / safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yarnpkg
    -0.60
     AssemblyTitle
    -0.53
    FontOfSize
    -0.50
     wireType
    -0.50
    initializeApp
    -0.49
    masalahan
    -0.49
     MainAxisSize
    -0.49
    ksom
    -0.48
    writerow
    -0.48
     Fournier
    -0.48
    POSITIVE LOGITS
     safety
    1.61
    safety
    1.58
    Safety
    1.58
     Safety
    1.55
     SAFETY
    1.49
     Safe
    1.46
    Safe
    1.45
    safe
    1.43
     safe
    1.43
    SAFETY
    1.40
    Act Density 0.025%

    No Known Activations