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

    Neuronpedia

    INDEX
    Explanations

    references to the letter 'th' and related phonetic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -1.00
    #![
    -0.82
    IPAC
    -0.81
    存于互联网档案馆
    -0.80
     Edy
    -0.79
    WebServlet
    -0.79
     Schoen
    -0.78
    ExecuteReader
    -0.77
    .[/
    -0.76
    بوابة
    -0.75
    POSITIVE LOGITS
     Th
    1.97
    Th
    1.92
     TH
    1.70
     th
    1.68
    TH
    1.55
    th
    1.53
     Tha
    1.23
     Thi
    1.22
     thri
    1.19
    thr
    1.18
    Act Density 0.132%

    No Known Activations