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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the letter "P" with a following number such as "P 9" or "P 10"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter "P"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebels
    -0.89
     diplom
    -0.82
     GOODMAN
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    ãĤ´ãĥ³
    -0.71
    ģĸ
    -0.69
     Orche
    -0.68
     Breaking
    -0.68
     EntityItem
    -0.68
     Exodus
    -0.66
    POSITIVE LOGITS
    ardon
    1.24
    aired
    1.23
    ivot
    1.20
    airs
    1.18
    appy
    1.11
    adding
    1.11
    ierce
    1.10
    uls
    1.10
    usher
    1.09
    ainted
    1.08
    Act Density 0.042%

    No Known Activations