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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and the need for clarification or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.73
    aarrggbb
    -0.70
    enterOuterAlt
    -0.66
    Obrázky
    -0.66
     propOrder
    -0.64
    isContained
    -0.63
     ویکی‌پدیا
    -0.62
    wußt
    -0.61
    MENAFN
    -0.60
    ########.
    -0.59
    POSITIVE LOGITS
    スク
    0.43
    一目
    0.42
    UnknownFields
    0.42
    __()
    0.42
    ELINE
    0.40
    Золо
    0.40
    ాని
    0.40
    Fn
    0.40
     experiment
    0.39
     investigation
    0.39
    Act Density 0.400%

    No Known Activations