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

    Neuronpedia

    INDEX
    Explanations

    statistical comparisons and significance in research data

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

    statistical significance p < 0.001

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.70
    -0.70
     createState
    -0.67
    fjspx
    -0.62
    AnchorTagHelper
    -0.62
    verwijspagina
    -0.59
    TypedDataSet
    -0.57
    ſelves
    -0.56
     ब्रेकडाउन
    -0.56
    ancers
    -0.56
    POSITIVE LOGITS
     δια
    0.39
     Bartlett
    0.38
     overwhelmingly
    0.36
     gap
    0.35
     underscored
    0.34
     universally
    0.34
     hugely
    0.33
     yli
    0.32
    assertj
    0.32
     heavily
    0.32
    Act Density 0.083%

    No Known Activations