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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "FF" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product or service labeled as "FF"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.76
    hee
    -0.76
     Emin
    -0.73
    Parameters
    -0.73
    ging
    -0.71
    arcer
    -0.68
    ifact
    -0.68
    ogy
    -0.66
    ittle
    -0.66
     Lump
    -0.66
    POSITIVE LOGITS
    ORTS
    0.76
    thur
    0.72
     Tire
    0.72
    ero
    0.71
    adan
    0.69
    ieri
    0.69
    omon
    0.67
    oute
    0.66
    HM
    0.66
    asher
    0.66
    Act Density 0.032%

    No Known Activations