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

    Neuronpedia

    INDEX
    Explanations

    symbolic representations of concepts and their relationships in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.63
    éges
    -0.51
     the
    -0.45
     her
    -0.43
     […]
    -0.42
     Na
    -0.42
     Sauer
    -0.41
     "";
    -0.41
     The
    -0.41
     su
    -0.40
    POSITIVE LOGITS
    verwijspagina
    1.04
    تقاوى
    0.94
     חיצוניים
    0.89
    出版年
    0.88
    +#+
    0.84
    脚注の使い方
    0.83
     pinulongan
    0.81
    homonymie
    0.81
     незавершена
    0.81
     Dummies
    0.80
    Act Density 0.593%

    No Known Activations