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

    Neuronpedia

    INDEX
    Explanations

    in this case, specific measurements of ingredients such as teaspoons and tablespoons

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities related to cooking ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.87
    gdala
    -0.77
    ¥µ
    -0.76
    DragonMagazine
    -0.72
     skelet
    -0.72
     Coliseum
    -0.72
    ocrin
    -0.72
    ĸļ
    -0.71
     halls
    -0.69
    hall
    -0.69
    POSITIVE LOGITS
     tsp
    0.98
     dab
    0.92
     baking
    0.89
     teaspoons
    0.86
    bsp
    0.85
     teaspoon
    0.84
    illin
    0.77
     coating
    0.76
     flakes
    0.75
     vinegar
    0.74
    Act Density 0.017%

    No Known Activations