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

    Neuronpedia

    INDEX
    Explanations

    instances of backticks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    σθαι
    -0.84
     "");
    -0.83
    •••
    -0.79
     Ratna
    -0.79
    )";
    -0.79
    er
    -0.79
    '},
    -0.75
    葩
    -0.74
    yorum
    -0.74
     rootReducer
    -0.74
    POSITIVE LOGITS
     `
    1.65
    =`
    1.64
    :`
    1.62
    .`
    1.54
    {`
    1.52
    (`
    1.50
     (`
    1.49
     `{
    1.39
     `/
    1.38
     `<
    1.34
    Act Density 0.077%

    No Known Activations