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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming keywords

    oai_token-act-pair · gpt-3.5-turbo

    empty sections or gaps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     breaching
    -0.58
     TBA
    -0.56
    enegger
    -0.54
     undermin
    -0.54
    asca
    -0.54
     judging
    -0.54
     Olympia
    -0.53
    aturdays
    -0.53
     hubs
    -0.53
     Indust
    -0.53
    POSITIVE LOGITS
     :=
    0.97
     isEnabled
    0.96
    operator
    0.91
    array
    0.90
    Array
    0.89
    actionDate
    0.88
    {
    0.88
    seq
    0.86
    String
    0.86
    func
    0.85
    Act Density 0.289%

    No Known Activations