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

    Neuronpedia

    INDEX
    Explanations

    numeric values and symbols related to dates and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     three
    -0.20
    three
    -0.19
    -three
    -0.18
     THREE
    -0.17
    omal
    -0.16
     drei
    -0.16
    ³
    -0.16
     Three
    -0.16
    ä¸īå¹´
    -0.15
    avern
    -0.15
    POSITIVE LOGITS
    8
    0.28
    9
    0.24
    7
    0.23
     ninth
    0.22
    оÑģÑĮ
    0.22
     eighth
    0.21
     Ninth
    0.20
     seventh
    0.20
    10
    0.19
     Eighth
    0.19
    Act Density 0.097%

    No Known Activations