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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and methodological limitations in research

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

    errors, inaccuracies, and modeling assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.47
    новниш
    -0.38
    anniversaire
    -0.36
     Offisielt
    -0.35
    المناصب
    -0.35
     borbo
    -0.34
    Beauty
    -0.33
    Spoljašnje
    -0.33
     graça
    -0.32
     Cardinale
    -0.32
    POSITIVE LOGITS
    TargetException
    0.56
     виправивши
    0.54
    әрмәләр
    0.53
    StructEnd
    0.50
    BagConstraints
    0.49
    }-*/;
    0.49
     المعيارى
    0.48
    ModelBuilder
    0.48
    లాలు
    0.45
    Дереккөздер
    0.45
    Act Density 0.200%

    No Known Activations