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

    Neuronpedia

    INDEX
    Explanations

    numeric references related to scientific measurements or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resse
    -0.19
    readcr
    -0.17
    manent
    -0.16
    æĿIJ
    -0.15
    utherland
    -0.15
    ока
    -0.15
    thic
    -0.15
    èŃľ
    -0.15
    nowledge
    -0.15
    haven
    -0.14
    POSITIVE LOGITS
    0.19
    imals
    0.16
    à§įà¦
    0.15
    thood
    0.15
    rage
    0.15
    ron
    0.14
    aisy
    0.14
    ร
    0.14
    osing
    0.14
    eker
    0.14
    Act Density 0.350%

    No Known Activations