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

    Neuronpedia

    INDEX
    Explanations

    names of countries and regions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     영
    -0.52
     ***!
    -0.46
    RenderAtEndOf
    -0.45
     DbSet
    -0.44
     rød
    -0.43
     sov
    -0.43
    iomanip
    -0.43
     hängt
    -0.43
    delà
    -0.42
    AfterClass
    -0.41
    POSITIVE LOGITS
    ⓘ
    0.72
    UserScript
    0.70
     Roskov
    0.66
    цездатний
    0.65
    Rüyada
    0.64
    expandindo
    0.63
    OGND
    0.63
     незавершена
    0.61
    dersfield
    0.60
    GeneratedMessage
    0.59
    Act Density 0.256%

    No Known Activations