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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "described" and its variants in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.69
     يتيمه
    -0.66
    Kapp
    -0.65
     GenerationType
    -0.61
     تضيفلها
    -0.61
     realisation
    -0.61
     realization
    -0.58
     actionTypes
    -0.57
     Justification
    -0.57
     AssemblyProduct
    -0.56
    POSITIVE LOGITS
     describe
    2.27
     describes
    2.06
     described
    1.97
     describing
    1.92
     Describe
    1.83
     DESCR
    1.77
    describe
    1.64
     Describes
    1.62
    Describe
    1.62
     describir
    1.61
    Act Density 0.105%

    No Known Activations