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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms ending in 'AS' or 'AS' followed by numerical values with the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AS" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozyg
    -0.83
    ows
    -0.79
    oting
    -0.74
    arty
    -0.73
    ogue
    -0.70
    ité
    -0.67
    naires
    -0.66
    atically
    -0.64
    ysis
    -0.63
    uci
    -0.61
    POSITIVE LOGITS
    TER
    1.04
    ADA
    0.99
    TERN
    0.97
    HA
    0.92
    ENA
    0.90
    IER
    0.89
    daq
    0.88
    OAD
    0.88
    DAQ
    0.88
    PER
    0.87
    Act Density 0.015%

    No Known Activations