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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or data related to mathematical operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.68
     McClure
    -0.68
    }>;
    -0.65
    Frosty
    -0.65
    oirs
    -0.62
    ORIAL
    -0.61
    CopyWith
    -0.60
     Artur
    -0.60
    pto
    -0.59
    ();*/
    -0.59
    POSITIVE LOGITS
    AccessorTable
    0.79
     Wicidata
    0.68
    Eres
    0.68
     Unidas
    0.66
    :✨
    0.64
     Réponses
    0.64
     Lég
    0.57
    Datuak
    0.57
    MessageOf
    0.57
    elemField
    0.54
    Act Density 0.113%

    No Known Activations