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

    Neuronpedia

    INDEX
    Explanations

    logical operators and constant declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poème
    -0.59
    complexContent
    -0.59
     ennemi
    -0.59
     étranger
    -0.55
     temprana
    -0.55
     trône
    -0.54
     llorar
    -0.54
     chrétien
    -0.54
     royaume
    -0.54
     vœ
    -0.53
    POSITIVE LOGITS
     union
    0.67
     Union
    0.59
    union
    0.54
     Uni
    0.53
     Mini
    0.51
     mass
    0.50
     mono
    0.50
     Col
    0.50
     Continent
    0.50
     unilateral
    0.49
    Act Density 0.291%

    No Known Activations