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

    Neuronpedia

    INDEX
    Explanations

    indicators of importance or prominence in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kloped
    -0.74
     newOwner
    -0.69
    +#+#
    -0.68
    ScopeManager
    -0.68
    verwijspagina
    -0.67
    ConstraintMaker
    -0.66
    FunctionFlags
    -0.65
    Jereo
    -0.65
    msgTypes
    -0.63
     ویکی‌پدیا
    -0.62
    POSITIVE LOGITS
    ########.
    0.79
     "..\..\
    0.70
    ::
    0.66
    Rüyada
    0.66
    {}/
    0.60
    __["
    0.56
    ovsk
    0.56
     riks
    0.56
    contentInset
    0.54
     samarbeid
    0.52
    Act Density 0.151%

    No Known Activations