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

    Neuronpedia

    INDEX
    Explanations

    phrases related to descriptions or characterizations of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Amicalement
    -0.75
     οποία
    -0.72
    thenReturn
    -0.72
    Theorem
    -0.70
     Guel
    -0.69
    britanni
    -0.68
    andaş
    -0.67
     Theorem
    -0.67
    woli
    -0.67
     alve
    -0.65
    POSITIVE LOGITS
     descriptions
    1.50
     description
    1.46
     descrip
    1.35
     descri
    1.25
     Description
    1.23
    getDescription
    1.22
    Description
    1.22
    descriptions
    1.18
    desc
    1.18
     DESCRIPTION
    1.18
    Act Density 0.082%

    No Known Activations