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

    Neuronpedia

    INDEX
    Explanations

    terms related to descriptions, characterization, and explaining content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     οποία
    -0.76
    Amicalement
    -0.71
    thenReturn
    -0.68
    Theorem
    -0.68
    (&:
    -0.67
    britanni
    -0.64
     Theorem
    -0.64
     Guel
    -0.64
     gặp
    -0.62
    andaş
    -0.61
    POSITIVE LOGITS
     descriptions
    1.43
     description
    1.37
     descrip
    1.33
    getDescription
    1.23
     Description
    1.20
     descri
    1.19
    Description
    1.18
    setDescription
    1.17
    DESCRIPTION
    1.16
     DESCRIPTION
    1.15
    Act Density 0.093%

    No Known Activations