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

    Neuronpedia

    INDEX
    Explanations

    references to privilege, particularly in legal or social contexts

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

    privilege against "self-incrimination" or "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manson
    -0.43
     NSCoder
    -0.43
    China
    -0.41
     seabed
    -0.41
     Vaticano
    -0.40
     dataSnapshot
    -0.39
    SNA
    -0.38
     Cassini
    -0.38
     Sankt
    -0.38
     Lunar
    -0.38
    POSITIVE LOGITS
     privilege
    2.33
    privilege
    2.11
     Privilege
    2.08
    Privilege
    1.80
     privileges
    1.76
     Privile
    1.52
     privilegio
    1.43
    privile
    1.42
    Privile
    1.36
     privil
    1.32
    Act Density 0.007%

    No Known Activations