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

    Neuronpedia

    INDEX
    Explanations

    contexts related to vulnerability or susceptibility, particularly in relation to external threats or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.15
    otty
    -0.14
    ãĥĥãĤ¯
    -0.14
    atsby
    -0.14
    orde
    -0.14
    ond
    -0.14
    abwe
    -0.14
    aji
    -0.14
    /umd
    -0.13
    artner
    -0.13
    POSITIVE LOGITS
    çīĻ
    0.15
    hangi
    0.14
    ัà¸ģ
    0.14
    urum
    0.14
    braska
    0.14
     PoÄįet
    0.14
    tdown
    0.13
    845
    0.13
    æĬĵ
    0.13
    bage
    0.13
    Act Density 0.020%

    No Known Activations