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

    Neuronpedia

    INDEX
    Explanations

    properties related to approximation, projection, and robustness within mathematical structures

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     StatelessWidget
    -0.71
     Properties
    -0.62
    felde
    -0.62
     trùng
    -0.60
    Properties
    -0.59
    properties
    -0.57
     BoxFit
    -0.57
    ArgsConstructor
    -0.57
    osoba
    -0.56
    xodo
    -0.55
    POSITIVE LOGITS
     všem
    0.59
     saken
    0.59
     réguli
    0.57
    DropTable
    0.56
     kepada
    0.56
     citoy
    0.55
     originais
    0.54
    vertible
    0.54
     alberi
    0.53
    Obrigado
    0.52
    Act Density 0.021%

    No Known Activations