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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the methodology of experiments, particularly emphasizing randomized designs

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

    "Randomized" or "separate" followed by "experiment" or "experiments"

    np_acts-logits-general · gemini-2.0-flash

    randomized independent experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.64
     affich
    -0.59
    ThroughAttribute
    -0.58
    enumii
    -0.57
    asyarakat
    -0.56
     Russie
    -0.54
     BoxDecoration
    -0.52
    RectangleBorder
    -0.52
    arXiv
    -0.52
    binaan
    -0.52
    POSITIVE LOGITS
     experiment
    2.31
     experiments
    2.27
     Experiment
    1.97
    experiment
    1.96
     Experiments
    1.91
     experimentation
    1.86
    Experiment
    1.85
     experimental
    1.84
    experiments
    1.83
    Experiments
    1.80
    Act Density 1.037%

    No Known Activations