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

    Neuronpedia

    INDEX
    Explanations

    instructions for cooking a specific dish

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikisource
    -0.93
     monaster
    -0.92
     prostitu
    -0.77
     Kün
    -0.76
     Contribu
    -0.69
     Mémoires
    -0.69
     jurist
    -0.68
     theolog
    -0.68
     manuten
    -0.68
     Ordre
    -0.68
    POSITIVE LOGITS
     oven
    0.66
     eût
    0.64
     semblait
    0.62
     heating
    0.62
     friable
    0.61
     heat
    0.60
     shenan
    0.58
     ovens
    0.58
     marié
    0.57
     heated
    0.57
    Act Density 0.133%

    No Known Activations