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

    Neuronpedia

    INDEX
    Explanations

    various forms of numerical data, including dates, times, and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    13
    -0.24
    12
    -0.24
    åįģäºĮ
    -0.23
    teen
    -0.22
    14
    -0.22
     XII
    -0.21
    15
    -0.20
    åįģä¸ī
    -0.20
     Twelve
    -0.20
    16
    -0.19
    POSITIVE LOGITS
    9
    0.36
    ä¹Ŀ
    0.31
     nine
    0.31
     ninth
    0.28
    8
    0.28
     Nine
    0.27
     IX
    0.26
     Ninth
    0.26
     eight
    0.25
    nine
    0.25
    Act Density 0.084%

    No Known Activations