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

    Neuronpedia

    INDEX
    Explanations

    comparisons emphasizing quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jeme
    -0.16
     utmost
    -0.13
     geil
    -0.13
     же
    -0.13
    ãĢħ
    -0.13
    ERTICAL
    -0.13
    ساÙĦ
    -0.13
    à¸Ļà¹Ĩ
    -0.12
    ardy
    -0.12
    izzo
    -0.12
    POSITIVE LOGITS
    thing
    0.15
    ths
    0.15
     ÙħÛĮÙĦادÛĮ
    0.14
    linger
    0.14
    ÂĿ
    0.13
    quires
    0.13
    Ĥ¬
    0.13
     Ung
    0.13
    ãĥ³ãĤº
    0.12
    UGH
    0.12
    Act Density 0.365%

    No Known Activations