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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or areas described as "spots."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.85
    egis
    -0.77
    íncia
    -0.77
    Hydra
    -0.76
    DoubleQuotes
    -0.76
    culosis
    -0.76
     Maier
    -0.74
    InputModule
    -0.72
    Hauptartikel
    -0.71
    ology
    -0.71
    POSITIVE LOGITS
     spot
    1.89
     SPOT
    1.86
     Spot
    1.86
    Spot
    1.66
    spot
    1.65
     Spots
    1.62
    SPOT
    1.58
     spots
    1.56
    spots
    1.51
    Spots
    1.27
    Act Density 0.068%

    No Known Activations