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

    Neuronpedia

    INDEX
    Explanations

    references to risk, safety, and compliance in health-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungle
    -0.16
    ReuseIdentifier
    -0.16
    awan
    -0.15
    auen
    -0.15
     filmer
    -0.14
     Turtle
    -0.14
    uner
    -0.14
     Cush
    -0.14
    çľł
    -0.14
    ietet
    -0.14
    POSITIVE LOGITS
    eln
    0.19
    bach
    0.17
    PD
    0.16
    ofs
    0.16
    icher
    0.15
    اÙĪÛĮ
    0.15
    oft
    0.14
    icion
    0.14
    ERCHANT
    0.14
    pei
    0.14
    Act Density 0.012%

    No Known Activations