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

    Neuronpedia

    INDEX
    Explanations

    references to Belgium and its cities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Babcock
    -0.64
     tinta
    -0.61
     BoxFit
    -0.60
     progresso
    -0.58
    RenderAtEndOf
    -0.57
     estimés
    -0.56
     granite
    -0.56
    ammans
    -0.56
    foglio
    -0.54
    nebago
    -0.54
    POSITIVE LOGITS
     Belgian
    1.38
     Belgium
    1.31
    Belgium
    1.25
    Belgian
    1.25
     Belgi
    1.16
     Belgien
    1.11
     Leuven
    1.09
     Bélgica
    1.08
     belg
    1.07
     belga
    1.04
    Act Density 0.212%

    No Known Activations