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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific sequences and patterns in names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </table>
    -0.58
    #>
    -0.53
    Tó
    -0.52
    :<
    -0.51
    ]}\
    -0.50
    googleapis
    -0.50
    "}")
    -0.49
    Soci
    -0.49
     Nacho
    -0.49
    \}^{
    -0.49
    POSITIVE LOGITS
     ร์
    0.63
     prêtre
    0.60
     désert
    0.58
     oreille
    0.57
     edades
    0.56
     ältere
    0.56
     borboleta
    0.56
    rer
    0.56
     autorytatywna
    0.54
     dureza
    0.54
    Act Density 2.448%

    No Known Activations