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

    Neuronpedia

    INDEX
    Explanations

    greetings and welcoming phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    出版年
    -0.88
    bootstrapcdn
    -0.85
    minecraftforge
    -0.67
     typelib
    -0.60
    ioutil
    -0.56
     itens
    -0.56
    OGND
    -0.55
    EDEFAULT
    -0.55
    Personensuche
    -0.55
    Zdrav
    -0.54
    POSITIVE LOGITS
    ὴν
    0.72
    Welcome
    0.66
     paradise
    0.65
    ῆς
    0.63
     officiellement
    0.63
    наче
    0.58
    Попис
    0.58
     Welcome
    0.57
    bena
    0.56
     Willkommen
    0.55
    Act Density 0.006%

    No Known Activations