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

    Neuronpedia

    INDEX
    Explanations

    significant historical or biographical information

    oai_token-act-pair · gpt-3.5-turbo

    structured information or lists of facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.89
    alach
    -0.74
    ĪĴ
    -0.72
    oreal
    -0.71
    urated
    -0.71
    20439
    -0.70
    urous
    -0.68
     striving
    -0.68
     bargaining
    -0.67
    unal
    -0.67
    POSITIVE LOGITS
    âĹı
    0.92
     THERE
    0.91
    âĸł
    0.88
    Myth
    0.87
     Firstly
    0.85
    âĺħ
    0.85
     Regarding
    0.81
    âĢ¢
    0.80
     âĹı
    0.80
     WHY
    0.79
    Act Density 0.271%

    No Known Activations