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

    Neuronpedia

    INDEX
    Explanations

    references to individuals involved in politics and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     potential
    -0.38
    lassung
    -0.37
    GOTREF
    -0.35
     disambiguazione
    -0.35
    vy
    -0.35
    oció
    -0.33
    ama
    -0.33
     Felici
    -0.33
    abo
    -0.33
     mož
    -0.32
    POSITIVE LOGITS
    OGND
    0.64
     Infórmanos
    0.62
     kasarigan
    0.62
    NameInMap
    0.60
     autorytatywna
    0.59
    UserScript
    0.57
     ویکی‌پدی
    0.56
     שוליים
    0.56
     saites
    0.49
     وتسجيلات
    0.49
    Act Density 0.371%

    No Known Activations