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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical or coded representations in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hickey
    -0.71
     Cleo
    -0.66
    ugeot
    -0.66
    mitglied
    -0.65
     Molly
    -0.62
     Appel
    -0.61
     DbContext
    -0.61
    mura
    -0.60
    dY
    -0.60
     Crum
    -0.59
    POSITIVE LOGITS
    ↵↵
    1.26
    <h2>
    1.01
    ↵↵↵↵↵
    0.99
    ↵↵↵↵
    0.94
    ↵
    0.92
    ())))
    0.91
    ↵↵↵
    0.90
    ↵↵↵↵↵↵
    0.89
    [toxicity=0]
    0.87
    </tr>
    0.86
    Act Density 0.134%

    No Known Activations