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

    Neuronpedia

    INDEX
    Explanations

    specific academic or scientific terminology and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.94
    SBATCH
    -0.91
    Datuak
    -0.90
     مشين
    -0.87
    ValueStyle
    -0.84
    rungsseite
    -0.83
     Савезне
    -0.81
    IntoConstraints
    -0.78
     فريبيس
    -0.78
     AssemblyTitle
    -0.76
    POSITIVE LOGITS
     VALUES
    0.51
    optarg
    0.50
     transversal
    0.49
     Coton
    0.49
    Urb
    0.48
     Substances
    0.48
    argo
    0.48
    perger
    0.47
    para
    0.47
     gal
    0.47
    Act Density 1.073%

    No Known Activations