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

    Neuronpedia

    INDEX
    Explanations

    questions being asked within a text

    oai_token-act-pair · gpt-3.5-turbo

    questions or inquiries in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.71
    weights
    -0.71
    fitting
    -0.70
    éĹĺ
    -0.67
     fullest
    -0.64
     hearts
    -0.64
     Lauder
    -0.64
    wagen
    -0.63
    ufact
    -0.63
     readable
    -0.62
    POSITIVE LOGITS
    atar
    0.94
    WER
    0.93
    onga
    0.88
    UE
    0.84
     Expand
    0.84
    addafi
    0.82
    avier
    0.81
    aha
    0.80
    iao
    0.79
    agan
    0.79
    Act Density 0.009%

    No Known Activations