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

    Neuronpedia

    INDEX
    Explanations

    references to locations, particularly the word "Cape" and related geographical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.52
     táctil
    -0.51
     anteriore
    -0.46
    standes
    -0.44
     magnética
    -0.44
     Grüsse
    -0.44
     Reparatur
    -0.44
     esmal
    -0.43
    cías
    -0.42
     instrucción
    -0.42
    POSITIVE LOGITS
     Cape
    0.91
    Cape
    0.83
     cape
    0.82
    AddTagHelper
    0.81
     CAPE
    0.77
     fur
    0.69
    CAPE
    0.57
     capes
    0.57
    ric
    0.56
    ford
    0.56
    Act Density 0.683%

    No Known Activations