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

    Neuronpedia

    INDEX
    Explanations

    references to academic or research papers and their associated citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     هيا
    -0.52
     face
    -0.51
    ://$
    -0.51
     none
    -0.48
     though
    -0.47
    onais
    -0.47
    arai
    -0.47
    <u>
    -0.46
    ✨:
    -0.46
     well
    -0.45
    POSITIVE LOGITS
     contextLoads
    0.91
     متعلقه
    0.85
    RectangleBorder
    0.83
    ConstraintMaker
    0.82
    0.82
     الرياضيه
    0.79
    ftagPool
    0.79
     photolibrary
    0.78
    WritableDatabase
    0.78
    __':
    0.77
    Act Density 0.000%

    No Known Activations