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

    Neuronpedia

    INDEX
    Explanations

    recipes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Violon
    -0.79
     konserv
    -0.74
     Senat
    -0.71
     Examen
    -0.69
     solidar
    -0.68
     Mühl
    -0.67
     Fase
    -0.67
     Wikisource
    -0.66
     €)
    -0.65
     fuit
    -0.65
    POSITIVE LOGITS
     recipe
    1.29
    recipe
    1.15
     recipes
    1.13
     Recipe
    1.03
     formula
    0.97
     Recipes
    0.95
    Recipe
    0.95
    recipes
    0.95
     RECIPE
    0.90
    formula
    0.88
    Act Density 0.098%

    No Known Activations