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

    Neuronpedia

    INDEX
    Explanations

    themes related to satire and social commentary

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

    satire and protest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.64
    balleur
    -0.61
     autorytatywna
    -0.51
    Портали
    -0.51
    gbaar
    -0.50
     FetchType
    -0.49
    GBT
    -0.47
    دانشنامهٔ
    -0.45
     }{@
    -0.45
    Datuak
    -0.45
    POSITIVE LOGITS
     satirical
    0.58
     warning
    0.52
     satire
    0.51
     mocking
    0.46
    warning
    0.43
     scold
    0.42
     accusing
    0.41
     sarcasm
    0.41
     sarcastic
    0.40
     warned
    0.40
    Act Density 0.022%

    No Known Activations