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

    Neuronpedia

    INDEX
    Explanations

    references to website domains and URLs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     الحره
    -1.52
     يتيمه
    -1.34
     Réponses
    -1.05
    Datuak
    -1.04
    -1.02
    LEncoder
    -0.98
     ivelany
    -0.98
     ویکی‌پدیا
    -0.98
    Personendaten
    -0.98
     صوتيه
    -0.96
    POSITIVE LOGITS
    <eos>
    0.58
    com
    0.52
    the
    0.51
    Com
    0.51
    ma
    0.50
    .
    0.50
    ;
    0.50
    Z
    0.50
    me
    0.49
    ();
    0.48
    Act Density 0.010%

    No Known Activations