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

    Neuronpedia

    INDEX
    Explanations

    references to "elements" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("~/
    -0.88
    ükemmel
    -0.86
     Chry
    -0.82
    cuses
    -0.80
     Sopho
    -0.79
    XtraGrid
    -0.79
    unny
    -0.79
    UpInside
    -0.77
     sentimos
    -0.76
    ggior
    -0.76
    POSITIVE LOGITS
     element
    2.10
     elements
    2.07
    Element
    1.96
     Element
    1.95
     Elements
    1.93
    element
    1.84
    Elements
    1.81
     ELEMENT
    1.76
    elements
    1.74
     ELEMENTS
    1.69
    Act Density 0.038%

    No Known Activations