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

    Neuronpedia

    INDEX
    Explanations

    references to documents and document-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Konkurrenz
    -0.62
     popularidad
    -0.58
     voordeel
    -0.57
    lewati
    -0.57
     ennemi
    -0.56
     avantage
    -0.54
     Vorteil
    -0.54
    Avantages
    -0.53
     himſelf
    -0.52
    Kariera
    -0.52
    POSITIVE LOGITS
     Document
    1.72
     document
    1.69
    Document
    1.55
    document
    1.48
     documents
    1.44
     Documents
    1.38
     DOCUMENT
    1.30
    DOCUMENT
    1.25
    documents
    1.21
     dokument
    1.18
    Act Density 0.081%

    No Known Activations