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

    Neuronpedia

    INDEX
    Explanations

    ingredients and cooking instructions in recipes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     churrasco
    -0.94
     tortas
    -0.91
     cammin
    -0.90
     piña
    -0.83
     monaster
    -0.82
     gubern
    -0.80
     barbacoa
    -0.80
     pican
    -0.80
     pandan
    -0.79
     trion
    -0.78
    POSITIVE LOGITS
     clayey
    0.84
     spice
    0.81
     friable
    0.81
     spices
    0.71
     pepper
    0.67
     flavor
    0.64
    🌶
    0.61
     anhyd
    0.61
     seasoning
    0.61
     blackish
    0.61
    Act Density 0.149%

    No Known Activations