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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the Roman numeral "ii" and other similar sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.84
     marsh
    -0.70
     convict
    -0.68
     derailed
    -0.65
    boards
    -0.65
     arresting
    -0.64
    marked
    -0.63
    ainted
    -0.62
    rooms
    -0.61
    hillary
    -0.61
    POSITIVE LOGITS
    ii
    1.48
    iii
    1.40
    FY
    1.01
    II
    0.97
    aeda
    0.95
    ei
    0.92
    ordan
    0.85
    ulia
    0.84
     ii
    0.84
    III
    0.84
    Act Density 0.003%

    No Known Activations