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

    Neuronpedia

    INDEX
    Explanations

    specific programming and coding terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antemano
    -0.53
     vuestros
    -0.50
     setempat
    -0.47
     Gegend
    -0.46
     Gegenteil
    -0.44
     kaupung
    -0.42
     tää
    -0.41
     satisfecho
    -0.41
     aislado
    -0.40
     perfección
    -0.40
    POSITIVE LOGITS
     Cabernet
    0.83
     cocaine
    0.82
     diphtheria
    0.82
     Diesel
    0.79
    dafx
    0.79
     iPad
    0.79
     polio
    0.79
     Chardonnay
    0.79
     measles
    0.78
     Hepatitis
    0.78
    Act Density 7.429%

    No Known Activations