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

    Neuronpedia

    INDEX
    Explanations

    sections of the text that indicate significant data or important differentiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.91
    herjee
    -0.91
    CloseOperation
    -0.90
    esseract
    -0.89
    rrggbb
    -0.83
     Spectre
    -0.83
     Saks
    -0.80
     maca
    -0.79
    Vere
    -0.79
     Heere
    -0.79
    POSITIVE LOGITS
    </h2>
    1.58
    "})
    0.94
    </h1>
    0.91
    "])
    0.90
    </th>
    0.90
    }")
    0.87
    "))
    0.85
    ");
    0.82
    })
    0.82
    ")]
    0.82
    Act Density 0.034%

    No Known Activations