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

    Neuronpedia

    INDEX
    Explanations

    the word "shown," indicating references to presented data or results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jefus
    -0.68
     Majefty
    -0.65
     Aza
    -0.63
     ſtate
    -0.61
     Monfieur
    -0.61
    !*\
    -0.58
     houſe
    -0.58
     ftate
    -0.56
    या
    -0.56
     depositphotos
    -0.56
    POSITIVE LOGITS
     AssemblyCulture
    0.81
     متعلقه
    0.78
    Obrázky
    0.75
     Infórmanos
    0.69
    ]-->
    0.65
    Примечания
    0.61
     تعدى
    0.59
    Enlaces
    0.59
     insuffisamment
    0.58
    Sucesor
    0.57
    Act Density 0.003%

    No Known Activations