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

    Neuronpedia

    INDEX
    Explanations

    the word "pres" followed by a number, possibly indicating precision or prescription

    oai_token-act-pair · gpt-3.5-turbo

    references to prescriptive or authoritative guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TAIN
    -0.83
    cles
    -0.77
    ress
    -0.72
    ISM
    -0.69
    nered
    -0.67
    lett
    -0.66
    itarian
    -0.65
    Bear
    -0.65
    ruary
    -0.64
    beans
    -0.63
    POSITIVE LOGITS
    wow
    0.82
    erver
    0.79
     pres
    0.79
    ervative
    0.77
    acc
    0.74
    olk
    0.74
    ider
    0.70
    ommel
    0.70
    inos
    0.69
    rontal
    0.69
    Act Density 0.029%

    No Known Activations