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

    Neuronpedia

    INDEX
    Explanations

    references to specific parts or components of an object

    oai_token-act-pair · gpt-3.5-turbo

    references to components or parts of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Predators
    -0.82
     blockers
    -0.62
    elsius
    -0.60
     raids
    -0.60
    âĸ¬
    -0.59
    quickShipAvailable
    -0.59
    iant
    -0.57
     footh
    -0.57
     blat
    -0.55
    qus
    -0.55
    POSITIVE LOGITS
    meal
    1.79
     piece
    0.85
    holder
    0.85
    work
    0.84
    ridges
    0.82
    glass
    0.82
    horn
    0.77
     Piece
    0.75
    parts
    0.75
    wise
    0.74
    Act Density 0.021%

    No Known Activations