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

    Neuronpedia

    INDEX
    Explanations

    numbers represented in a specific format or structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.57
    mappedBy
    -0.53
     zufolge
    -0.49
    InstrumentedTest
    -0.49
    "..."
    -0.48
    Литература
    -0.48
    KommentareTeilen
    -0.48
     محفوظة
    -0.47
    demi
    -0.45
    apunov
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.88
     Paglinawan
    0.67
    parsedMessage
    0.65
     "..\..\
    0.64
     Италијани
    0.63
    +#+#
    0.61
     Roskov
    0.59
    dafx
    0.58
    mergeFrom
    0.57
    AutoScale
    0.56
    Act Density 0.016%

    No Known Activations