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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Посилання
    -0.59
     Wicidata
    -0.58
     estimés
    -0.51
    takkan
    -0.51
     Russland
    -0.49
    llac
    -0.48
    nictví
    -0.47
     виправивши
    -0.47
     lenker
    -0.46
    %)$
    -0.46
    POSITIVE LOGITS
     af
    0.64
     uden
    0.63
    ighed
    0.62
     ud
    0.60
    Læs
    0.58
    øj
    0.57
    Hvad
    0.57
     gennem
    0.57
     bliver
    0.56
     mellem
    0.56
    Act Density 0.276%

    No Known Activations