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

    Neuronpedia

    INDEX
    Explanations

    table headers and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.63
    PasswordEncoder
    -0.62
    ✨:
    -0.62
     الدولى
    -0.59
     оригіналу
    -0.59
    Alfa
    -0.55
     Интер
    -0.55
     Milán
    -0.54
    lanta
    -0.54
    ifornia
    -0.54
    POSITIVE LOGITS
    th
    2.24
    TH
    1.26
    ths
    0.92
    Th
    0.88
     th
    0.88
    thu
    0.87
    thm
    0.86
    thd
    0.86
    thly
    0.85
    thand
    0.81
    Act Density 0.030%

    No Known Activations