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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of the "real world."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    real-world contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.48
     propOrder
    -0.48
    //
    -0.48
     tartalomajánló
    -0.44
     AssemblyTitle
    -0.42
    multer
    -0.40
    /*
    -0.39
    DrawerToggle
    -0.38
     transfieras
    -0.37
    %"),
    -0.36
    POSITIVE LOGITS
    现实
    0.86
    現實
    0.79
    reality
    0.79
    現実
    0.79
     reality
    0.76
    Real
    0.72
    real
    0.71
     real
    0.69
     IRL
    0.69
     реаль
    0.68
    Act Density 0.006%

    No Known Activations