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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with regulations and criteria in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategories
    -0.17
    ural
    -0.15
    plevel
    -0.14
    atura
    -0.14
    -INF
    -0.14
    Ư
    -0.14
    EEE
    -0.13
    eyse
    -0.13
    adden
    -0.13
    atus
    -0.13
    POSITIVE LOGITS
    inel
    0.17
     Donovan
    0.13
    tog
    0.13
     accommod
    0.13
     ultimately
    0.13
     ÑģобÑĭ
    0.12
    .link
    0.12
     Nine
    0.12
     ;č↵
    0.12
    usi
    0.12
    Act Density 0.086%

    No Known Activations