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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "AT" followed by a numerical value, specifically with a high activation for "AT 10" and "AT 9"

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "AT" that relate to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perse
    -0.79
    ingen
    -0.71
     Tsukuyomi
    -0.68
    ppelin
    -0.68
    Blade
    -0.67
     Micha
    -0.66
    produ
    -0.64
     MSM
    -0.63
    hold
    -0.62
    vous
    -0.59
    POSITIVE LOGITS
    ICAN
    1.24
    hetically
    1.00
    RON
    0.93
    ainment
    0.91
    terson
    0.90
    ELY
    0.90
    RIC
    0.89
    ORY
    0.89
    itudes
    0.89
    ECH
    0.89
    Act Density 0.014%

    No Known Activations