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

    Neuronpedia

    INDEX
    Explanations

    mathematical constants and symbols, particularly related to π (pi)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tung
    -0.49
    tung
    -0.49
    a
    -0.49
    kund
    -0.48
    jose
    -0.48
    QG
    -0.47
    ında
    -0.46
     Kön
    -0.46
     aux
    -0.46
    őség
    -0.46
    POSITIVE LOGITS
    pi
    2.97
     pi
    2.72
     Pi
    2.31
    Pi
    2.19
    PI
    2.17
    π
    2.15
     PI
    2.10
     π
    1.94
     pips
    1.48
     Pierson
    1.44
    Act Density 0.109%

    No Known Activations