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

    Neuronpedia

    INDEX
    Explanations

    references to leaves, specifically in the context of nature and biofuels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.88
    cedes
    -0.69
    ICAN
    -0.68
    ENTION
    -0.66
    afort
    -0.65
    duction
    -0.61
    senal
    -0.61
    glomer
    -0.61
    ALLY
    -0.60
    nels
    -0.60
    POSITIVE LOGITS
    leaf
    1.08
    let
    1.07
    lets
    1.06
     leaf
    0.99
    grass
    0.97
     Leaf
    0.88
    cone
    0.87
    ho
    0.86
    flower
    0.85
    wood
    0.85
    Act Density 0.098%

    No Known Activations