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

    Neuronpedia

    INDEX
    Explanations

    references to nationalities and their associated professions or roles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StringCopy
    -0.85
    OGND
    -0.84
     Paglinawan
    -0.82
    webElementXpaths
    -0.73
    posedge
    -0.71
     nakalista
    -0.71
    quelize
    -0.70
    RegressionTest
    -0.70
     referenties
    -0.69
    hlungen
    -0.69
    POSITIVE LOGITS
     eminent
    0.45
    Activités
    0.45
     متعلقه
    0.44
    kec
    0.42
     Pegasus
    0.42
     Maltese
    0.40
     Fø
    0.40
    KURZBESCHREIBUNG
    0.40
     zweif
    0.39
    filter
    0.39
    Act Density 0.072%

    No Known Activations