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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conditional phrases indicating uncertainty or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.81
    styleType
    -0.76
    DOCTYPE
    -0.74
    érience
    -0.70
    rimônio
    -0.66
    }]);
    -0.64
    >[]
    -0.64
    обходимо
    -0.64
    /**
    -0.64
    __':
    -0.64
    POSITIVE LOGITS
     sekal
    0.83
     even
    0.69
     Even
    0.65
    Even
    0.65
     וגם
    0.64
    とはいえ
    0.60
     spite
    0.58
    even
    0.55
    Trotz
    0.55
    Даже
    0.54
    Act Density 0.177%

    No Known Activations