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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.62
     mû
    -0.49
     eût
    -0.48
     Audiodateien
    -0.46
    penuhi
    -0.45
    kaitan
    -0.45
    abetes
    -0.45
     girls
    -0.44
    holdet
    -0.44
     accél
    -0.43
    POSITIVE LOGITS
    #+#
    0.95
    sizeCache
    0.83
     lenker
    0.78
    :✨
    0.76
     betweenstory
    0.76
    tanleria
    0.75
     Wikimedijinoj
    0.74
    windowFixed
    0.73
    richTextPanel
    0.73
    ]<<"
    0.71
    Act Density 0.143%

    No Known Activations