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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.97
    ]")]
    -0.91
    .*")]
    -0.91
     дописавши
    -0.85
    Hentet
    -0.84
    )))),
    -0.83
    styleType
    -0.79
    انيف
    -0.76
    @[+][
    -0.75
     مشين
    -0.75
    POSITIVE LOGITS
    </strong>
    0.68
    中略
    0.64
    </em>
    0.62
    </u>
    0.60
    </b>
    0.56
    </h2>
    0.55
    hauer
    0.55
    UserScript
    0.54
    0.53
    ant
    0.52
    Act Density 5.341%
    No Known Activations