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

    Neuronpedia

    INDEX
    Explanations

    uppercase Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    the Roman numeral "ii" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.81
    insula
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    boards
    -0.72
    meyer
    -0.65
    rant
    -0.65
    OTUS
    -0.64
    trigger
    -0.64
    nell
    -0.64
     convict
    -0.63
    POSITIVE LOGITS
    iii
    1.18
    ii
    1.14
    ñ
    0.82
    ye
    0.74
    iking
    0.74
    FY
    0.73
    yah
    0.72
    ysis
    0.70
    ikawa
    0.69
    uner
    0.69
    Act Density 0.012%

    No Known Activations