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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and rhetorical questions indicating sarcasm or irony

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

    opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.53
    webElementXpaths
    -0.50
    ValueStyle
    -0.50
    Personendaten
    -0.49
    HasAnnotation
    -0.48
    ChildScrollView
    -0.47
    queryInterface
    -0.46
    typeorm
    -0.43
    jspb
    -0.43
    Diwedd
    -0.41
    POSITIVE LOGITS
     harsh
    0.46
     angry
    0.42
    TextInputLayout
    0.40
    ⮕
    0.39
    Fucking
    0.39
     pinulongan
    0.39
    ViewFeatures
    0.39
     angrily
    0.38
    Same
    0.37
    same
    0.37
    Act Density 0.086%

    No Known Activations