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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals and their usage in identified contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÑģоÑĩ
    -0.15
    æİĽ
    -0.15
    enum
    -0.14
    anz
    -0.14
    ÑĤеÑĢи
    -0.14
    ãģŁãĤĬ
    -0.14
    ibbon
    -0.14
     coppia
    -0.14
    umpt
    -0.14
     è»
    -0.14
    POSITIVE LOGITS
    epy
    0.17
    997
    0.15
    agens
    0.15
    849
    0.14
    wed
    0.14
    aud
    0.13
    inks
    0.13
    .Tile
    0.13
     wed
    0.13
    ussy
    0.13
    Act Density 0.023%

    No Known Activations