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

    Neuronpedia

    INDEX
    Explanations

    sections of bold or emphasized text in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Miy
    -0.89
     rhestr
    -0.87
     Miy
    -0.84
    belt
    -0.81
    windowFixed
    -0.80
     Hilde
    -0.77
    thra
    -0.77
     UITextField
    -0.76
     McKin
    -0.75
    IVAS
    -0.73
    POSITIVE LOGITS
    </strong>
    1.80
    </em>
    1.50
    </b>
    1.35
    </u>
    1.35
    </s>
    1.21
    </sub>
    1.20
    </code>
    1.19
    )])
    1.10
    )});
    1.09
    </sup>
    1.09
    Act Density 0.002%

    No Known Activations