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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals and their associated references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.19
    M
    -0.16
    άλ
    -0.15
    C
    -0.15
    ãģŁãĤĬ
    -0.15
    E
    -0.15
    MING
    -0.15
    isser
    -0.15
    ĩ
    -0.14
    elling
    -0.14
    POSITIVE LOGITS
    inois
    0.19
    IB
    0.17
    bero
    0.16
    ly
    0.15
    Äįin
    0.15
    iii
    0.15
    OLUME
    0.15
    wis
    0.15
    ÎĻ
    0.14
    wed
    0.14
    Act Density 0.032%

    No Known Activations