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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.88
    pecabe
    -0.83
     snippetHide
    -0.80
    awtextra
    -0.79
     Numerade
    -0.77
     ब्रेकडाउन
    -0.75
    ſelves
    -0.74
     zuſammen
    -0.73
    <unused42>
    -0.73
    <unused43>
    -0.72
    POSITIVE LOGITS
    <td>
    0.69
    {
    0.65
    }{*}{
    0.64
     "
    0.63
    |}{
    0.62
    <strong>
    0.61
    <b>
    0.60
     (
    0.59
    ="
    0.57
    [toxicity=0]
    0.56
    Act Density 0.232%

    No Known Activations