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

    Neuronpedia

    INDEX
    Explanations

    words and expressions from various languages, particularly focused on proper nouns and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.71
    almaz
    -0.66
    umlu
    -0.60
    وردار
    -0.58
    pena
    -0.57
     Fast
    -0.57
     похо
    -0.57
     vind
    -0.57
     *****
    -0.57
    csolódó
    -0.56
    POSITIVE LOGITS
    Portail
    0.94
     Nestlé
    0.91
    acán
    0.90
     Beyoncé
    0.89
     Erdoğan
    0.87
    Rüyada
    0.87
    })`
    0.85
     Citroën
    0.83
    ]='\
    0.83
    Pokémon
    0.83
    Act Density 0.821%

    No Known Activations