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

    Neuronpedia

    INDEX
    Explanations

    references to formal documents and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sumpay
    -0.45
     acceptez
    -0.45
    RectangleBorder
    -0.38
     Dean
    -0.37
    écou
    -0.35
     géographique
    -0.34
     Vermögen
    -0.32
     current
    -0.32
     college
    -0.31
     aceptas
    -0.30
    POSITIVE LOGITS
    Manbalar
    0.71
    exitRule
    0.66
    fromnode
    0.63
    TypedDataSet
    0.60
    -------
    0.58
    +#+#
    0.56
    transQ
    0.56
    forChild
    0.55
    ніципалі
    0.55
    intios
    0.55
    Act Density 2.668%

    No Known Activations