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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of the word "at" and related phrases indicating location or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sebuah
    -0.21
    æĺ¯ä¸Ģ个
    -0.19
    —an
    -0.19
    ä¸ĢåĢĭ
    -0.19
     einer
    -0.18
    ä¸Ģç§į
    -0.17
    æĺ¯ä¸Ģ
    -0.17
     someone
    -0.16
     somebody
    -0.16
    someone
    -0.15
    POSITIVE LOGITS
     a
    0.27
    	a
    0.18
    anken
    0.16
    a
    0.16
    _a
    0.15
    BB
    0.14
    uso
    0.14
    buz
    0.14
     а
    0.13
    676
    0.13
    Act Density 0.180%

    No Known Activations