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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and constants, particularly those related to the number pi and its applications in equations or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tung
    -0.61
     Fairchild
    -0.51
    Cater
    -0.51
    tung
    -0.50
     Gass
    -0.50
     tarifs
    -0.50
    ah
    -0.50
    セミ
    -0.49
     बाल
    -0.48
    ında
    -0.48
    POSITIVE LOGITS
    pi
    2.08
     pi
    1.99
    π
    1.74
     Pi
    1.66
    PI
    1.50
    Pi
    1.48
     π
    1.48
     PI
    1.46
    1.11
     pips
    1.08
    Act Density 0.144%

    No Known Activations