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

    Neuronpedia

    INDEX
    Explanations

    discussions about tasks and the completion of work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ermann
    -0.15
    erdale
    -0.15
    egas
    -0.14
    ovel
    -0.14
    ammen
    -0.14
     itself
    -0.14
    ximo
    -0.13
    vic
    -0.13
    ICES
    -0.13
    iske
    -0.13
    POSITIVE LOGITS
    éĤ£éĩĮ
    0.18
    ãģĵãģ¡ãĤī
    0.18
     THAT
    0.18
     Äijó
    0.16
    éĤ£æł·
    0.15
    ully
    0.15
    éĤ£ä¸ª
    0.14
     That
    0.14
    avin
    0.14
     εκεί
    0.14
    Act Density 0.310%

    No Known Activations