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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals, particularly the number III

    oai_token-act-pair · gpt-3.5-turbo

    Roman numeral designations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boards
    -0.92
    board
    -0.75
    chant
    -0.75
    д
    -0.74
    cho
    -0.74
     palms
    -0.71
    =-=-=-=-=-=-=-=-
    -0.71
    lands
    -0.70
    feed
    -0.69
    lins
    -0.69
    POSITIVE LOGITS
    III
    1.15
    II
    1.10
    FY
    0.80
    ATA
    0.79
    ACA
    0.76
    IV
    0.74
     III
    0.74
    IC
    0.72
    EC
    0.72
     Centauri
    0.70
    Act Density 0.027%

    No Known Activations