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-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.04
    2:0.02
    3:0.06
    4:0.13
    5:0.09
    6:0.08
    7:0.04
    8:0.07
    9:0.07
    10:0.03
    11:0.08
    Negative Logits
     terrestrial
    -1.65
    lished
    -1.61
    etheless
    -1.57
     accredited
    -1.56
     athlet
    -1.53
     unrecogn
    -1.50
    rehensive
    -1.49
    ificantly
    -1.46
     academ
    -1.45
    theless
    -1.44
    POSITIVE LOGITS
     ingredients
    2.14
    Ingredients
    1.83
    iso
    1.82
     recipe
    1.78
    Optional
    1.70
    ć
    1.69
     cloves
    1.68
     mixture
    1.63
     ½
    1.63
     sugars
    1.63
    Act Density 0.016%

    No Known Activations