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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "two" or duality in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     createState
    -0.74
    ftagPool
    -0.72
     wireType
    -0.71
     allemaal
    -0.68
     itſelf
    -0.68
    ſelf
    -0.66
     Ephesus
    -0.66
     $(\%)$
    -0.64
     Mongols
    -0.64
    kolwiek
    -0.63
    POSITIVE LOGITS
     two
    1.16
     beiden
    1.09
     Both
    0.99
     both
    0.98
    two
    0.98
     två
    0.95
     ambos
    0.93
    Both
    0.93
    both
    0.91
     Two
    0.91
    Act Density 2.844%

    No Known Activations