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

    Neuronpedia

    INDEX
    Explanations

    the letter 'O' when it is used as a standalone character, often in acronyms

    oai_token-act-pair · gpt-4-turbo

    the letter "O" appearing with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'O' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥķ
    -0.90
    ãĥ¼ãĥĨãĤ£
    -0.90
    ÑĮ
    -0.85
    ãĤ©
    -0.79
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    ãĥķãĤ©
    -0.78
     PLA
    -0.76
     PID
    -0.76
    ãĤ¶
    -0.76
    ãĥĨãĤ£
    -0.74
    POSITIVE LOGITS
    tto
    1.13
    vernight
    1.09
    lymp
    1.06
    culus
    1.03
    OT
    1.02
    scill
    1.02
    VERT
    1.01
    zzy
    0.99
    ogie
    0.98
    oga
    0.98
    Act Density 0.021%

    No Known Activations