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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty, requests for assistance, and affirmative responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackbar
    -0.17
    unless
    -0.16
    oucher
    -0.16
    onec
    -0.15
    zte
    -0.15
    depending
    -0.15
    ÑĭÑĪ
    -0.15
    zek
    -0.14
     whats
    -0.14
    ingu
    -0.14
    POSITIVE LOGITS
    à¸ĸ
    0.17
    ï¸ı
    0.15
    ÅĤÄħ
    0.14
    esper
    0.14
    //{{
    0.14
    ha
    0.14
    æł
    0.13
    ãģİ
    0.13
     sÃŃ
    0.13
    oud
    0.13
    Act Density 0.116%

    No Known Activations