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

    Neuronpedia

    INDEX
    Explanations

    The neuron seems to activate for sentences starting with "I know I", with varying levels of certainty and emotional tones

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal knowledge or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.74
    etheus
    -0.63
     Âł Âł
    -0.60
     Cancel
    -0.60
    opes
    -0.59
    rex
    -0.58
     resume
    -0.58
    anship
    -0.57
    arantine
    -0.57
    eworthy
    -0.56
    POSITIVE LOGITS
    )</
    0.72
    sb
    0.71
    PLA
    0.70
     firsthand
    0.67
    CLA
    0.64
    stadt
    0.63
     plenty
    0.61
    anza
    0.61
    ById
    0.60
    %);
    0.59
    Act Density 0.271%

    No Known Activations