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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with different parameters or configurations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.78
     Nie
    -0.60
    mindedness
    -0.59
    Ό
    -0.59
     mattino
    -0.58
    Obrázky
    -0.58
    Personensuche
    -0.57
    WebVitals
    -0.57
    IntoConstraints
    -0.57
     unicórnio
    -0.56
    POSITIVE LOGITS
     发表于
    0.83
    "])
    0.81
    ">)</
    0.81
     }}$}
    0.81
    -</
    0.78
    ++
    0.77
    ,</
    0.76
    "],
    0.76
    +</
    0.75
    )}</
    0.75
    Act Density 0.025%

    No Known Activations