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

    Neuronpedia

    INDEX
    Explanations

    markup annotations and parameters related to functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.86
     propOrder
    -0.81
    UnusedPrivate
    -0.79
    addCriterion
    -0.78
     ['./
    -0.71
     "..\..\..\
    -0.70
     ivelany
    -0.69
    vereignty
    -0.69
     ***!
    -0.69
    +#+#
    -0.68
    POSITIVE LOGITS
     original
    0.58
     {
    0.58
    — 
    0.56
     useful
    0.55
     correctes
    0.54
    atag
    0.53
    omena
    0.52
    fao
    0.52
    magini
    0.52
     Pegasus
    0.51
    Act Density 0.068%

    No Known Activations