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

    Neuronpedia

    INDEX
    Explanations

    symbols or numeric representations, particularly in a Japanese context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Спољашње
    -0.56
    namely
    -0.52
     bowiem
    -0.52
    ########.
    -0.52
    ruckt
    -0.51
    jalá
    -0.50
    titleMargin
    -0.49
    bunal
    -0.48
    стоин
    -0.47
     repose
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.71
     بيها
    0.56
    ∭
    0.56
     فريبيس
    0.55
     AssemblyCulture
    0.54
    EndContext
    0.52
    ̀
    0.52
    +#+
    0.52
    itemBuilder
    0.52
    Hentet
    0.50
    Act Density 0.000%

    No Known Activations