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

    Neuronpedia

    INDEX
    Explanations

    concepts related to controversy and disputes in various contexts

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

    disagreement or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    questions of controversy and debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.71
    tanleria
    -0.62
    gestellt
    -0.61
    Données
    -0.61
    lgari
    -0.60
     }{@
    -0.58
     وتسجيلات
    -0.58
    roppo
    -0.57
     ")";
    -0.56
     ?>>
    -0.56
    POSITIVE LOGITS
     whether
    1.08
     debate
    1.05
     debated
    0.95
     debates
    0.92
     question
    0.86
     WHETHER
    0.86
     Debate
    0.84
     dispute
    0.83
     controversy
    0.83
    whether
    0.82
    Act Density 0.433%

    No Known Activations