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

    Neuronpedia

    INDEX
    Explanations

    sections or divisions in text, particularly relating to parts or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.49
    astră
    -0.47
    </table>
    -0.42
    LEncoder
    -0.38
     defaultstate
    -0.36
    南浔
    -0.36
     ویکی‌آمباردا
    -0.36
    onicus
    -0.34
    ebilir
    -0.34
     financieras
    -0.34
    POSITIVE LOGITS
    ridges
    0.66
    cular
    0.66
     integrante
    0.63
    ridge
    0.62
    cipation
    0.61
    way
    0.57
    cip
    0.56
    oredCriteria
    0.47
    ícula
    0.47
    IALLY
    0.46
    Act Density 0.160%

    No Known Activations