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

    Neuronpedia

    INDEX
    Explanations

    structural elements of written text or programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     […]
    -1.28
    […]
    -1.01
     …
    -1.00
    </em>
    -0.83
     [...]
    -0.83
    </strong>
    -0.80
    …"
    -0.78
     ..."
    -0.77
    ."
    -0.76
    .”
    -0.74
    POSITIVE LOGITS
     Савезне
    1.07
    :✨
    0.87
    Personensuche
    0.85
    <bos>
    0.85
     autorytatywna
    0.81
    ніципа
    0.79
    twimg
    0.76
     Roskov
    0.75
     Numerade
    0.73
     Administrativna
    0.72
    Act Density 0.081%

    No Known Activations