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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or terms denoting absence or low values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -1.08
    liesslich
    -0.94
    ING
    -0.90
    $
    -0.87
     оригіналу
    -0.82
    "]
    -0.82
    Rana
    -0.77
    ']
    -0.77
     mall
    -0.76
    ]}{
    -0.76
    POSITIVE LOGITS
    –
    0.90
    teenth
    0.87
    gogo
    0.85
     Mā
    0.83
     Westport
    0.81
     Kō
    0.81
     Maas
    0.80
    .–
    0.80
    SOT
    0.79
     Benito
    0.78
    Act Density 0.190%

    No Known Activations