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

    Neuronpedia

    INDEX
    Explanations

    terms related to global or international contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     religieuses
    -0.67
     rencontr
    -0.66
     tranquille
    -0.63
     vestiti
    -0.62
     étoit
    -0.61
     carreaux
    -0.59
    PropTypes
    -0.58
     intermédiaire
    -0.57
     artig
    -0.57
     défend
    -0.56
    POSITIVE LOGITS
     global
    3.59
    global
    3.12
     Global
    3.10
    Global
    2.91
     GLOBAL
    2.87
    GLOBAL
    2.75
     globally
    2.52
     globales
    2.47
     globale
    2.40
     глоба
    2.24
    Act Density 0.069%

    No Known Activations