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

    Neuronpedia

    INDEX
    Explanations

    content related to advanced scientific or mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koz
    -0.70
     Eliz
    -0.65
     trin
    -0.64
     لينك
    -0.62
    lessed
    -0.59
    Pont
    -0.59
    Mann
    -0.58
    grá
    -0.57
     ReSharper
    -0.57
     CLAR
    -0.57
    POSITIVE LOGITS
    </sup>
    2.21
    </sub>
    1.32
    </s>
    1.10
    </u>
    0.95
    )`
    0.89
    >`
    0.89
    rfloor
    0.86
    }`
    0.86
    〕
    0.85
    ⁩
    0.84
    Act Density 0.185%

    No Known Activations