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

    Neuronpedia

    INDEX
    Explanations

    nutritional information like protein and calcium percentages

    oai_token-act-pair · gpt-3.5-turbo

    nutritional information and percentages related to food content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.58
    hirt
    -0.58
    heit
    -0.58
    lees
    -0.55
    ibal
    -0.54
    wolves
    -0.53
    _>
    -0.53
     Spiel
    -0.52
     Signs
    -0.52
    bugs
    -0.52
    POSITIVE LOGITS
    azo
    0.74
    achev
    0.68
     paddle
    0.62
    ĵĺ
    0.62
     increments
    0.58
     srfAttach
    0.58
     Ukrain
    0.57
    uple
    0.55
    м
    0.55
    axy
    0.54
    Act Density 0.583%

    No Known Activations