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

    Neuronpedia

    INDEX
    Explanations

    questions about quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning the quantity or extent of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.97
    Ń·
    -0.85
    ATURES
    -0.83
    zek
    -0.80
    swick
    -0.80
    zech
    -0.78
    idon
    -0.77
    èĢ
    -0.77
    jac
    -0.75
    emy
    -0.74
    POSITIVE LOGITS
     attention
    0.81
     money
    0.79
     invested
    0.78
     elapsed
    0.78
     fun
    0.76
     firepower
    0.76
     interest
    0.76
     else
    0.75
     owed
    0.74
     faith
    0.74
    Act Density 0.019%

    No Known Activations