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

    Neuronpedia

    INDEX
    Explanations

    references to philosophical themes and critiques within narratives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Gemeinden
    -0.60
    ViewImports
    -0.60
     kasarigan
    -0.57
    definitely
    -0.57
    Rüyada
    -0.52
    ########.
    -0.51
     comuniques
    -0.50
    脚注の使い方
    -0.50
     definitely
    -0.49
    toso
    -0.49
    POSITIVE LOGITS
    oczes
    0.56
    poptosis
    0.50
    unknownFields
    0.50
     básicas
    0.50
     químicas
    0.49
    huriyet
    0.49
    encre
    0.49
    Normal
    0.48
     normais
    0.48
     grossesse
    0.48
    Act Density 0.222%

    No Known Activations