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

    Neuronpedia

    INDEX
    Explanations

    occurrences of emotionally charged descriptors and comparisons

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

    negative or missing context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.56
     EconPapers
    -0.47
     BoxDecoration
    -0.47
    RotationOrder
    -0.46
    routeProvider
    -0.43
     المعيارى
    -0.42
    QMetaType
    -0.42
     خل
    -0.42
    HttpFoundation
    -0.41
    PositiveButton
    -0.40
    POSITIVE LOGITS
     tampoco
    0.56
    ējās
    0.45
     وتسجيلات
    0.44
     fehlt
    0.43
     too
    0.42
     TAMBIÉN
    0.41
     serius
    0.41
    tanleria
    0.40
     lenker
    0.40
     demasi
    0.40
    Act Density 0.299%

    No Known Activations