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

    Neuronpedia

    INDEX
    Explanations

    internet-related terms and actions related to content control and surveillance

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty or unfilled content markers in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.79
     Slay
    -0.73
     Lieutenant
    -0.72
     Rear
    -0.68
    olulu
    -0.66
    hiro
    -0.65
    cki
    -0.64
     Haley
    -0.64
    cific
    -0.64
    ittle
    -0.63
    POSITIVE LOGITS
    Torrent
    1.04
     networks
    0.97
     encryption
    0.90
     piracy
    0.90
     platforms
    0.88
     users
    0.85
     passwords
    0.83
     providers
    0.82
     routers
    0.82
     devices
    0.82
    Act Density 0.277%

    No Known Activations