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

    Neuronpedia

    INDEX
    Explanations

    quantifiable data points and their respective parameters in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inan
    -0.16
    ARSER
    -0.15
    trand
    -0.15
    lod
    -0.15
    tron
    -0.14
    ég
    -0.14
     Slut
    -0.14
    embros
    -0.14
    chor
    -0.14
    ứa
    -0.14
    POSITIVE LOGITS
     Neutral
    0.19
     vice
    0.16
    ellan
    0.16
    rd
    0.15
     ins
    0.15
     neutral
    0.15
    ertz
    0.15
     Vice
    0.14
    ä¸ĺ
    0.14
    vice
    0.14
    Act Density 1.266%

    No Known Activations