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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority or control roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.83
    wyn
    -0.79
    hynch
    -0.73
    <blockquote>
    -0.70
    ES
    -0.70
    ernalia
    -0.69
    𝗲
    -0.68
     sjø
    -0.68
    czaj
    -0.66
    ̀n
    -0.66
    POSITIVE LOGITS
    ator
    1.41
    ators
    1.16
    vator
    1.13
    ATOR
    1.09
    urator
    1.04
     ator
    1.02
    icator
    1.01
    strator
    0.98
     Ziegler
    0.97
    Locator
    0.95
    Act Density 0.066%

    No Known Activations