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

    Neuronpedia

    INDEX
    Explanations

    words that indicate relationships or connections between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _contents
    -0.15
    ãĥ¼ãĥ¼
    -0.14
     tam
    -0.14
     Moore
    -0.14
    輪
    -0.14
     gri
    -0.14
    лÑİ
    -0.14
     bis
    -0.14
    ær
    -0.13
    à¸ī
    -0.13
    POSITIVE LOGITS
     automatically
    0.17
    aling
    0.16
     automát
    0.16
    eger
    0.15
    ensch
    0.15
    endale
    0.15
    ÎŁÎ
    0.14
     Kit
    0.14
    automatic
    0.14
     automáticamente
    0.14
    Act Density 0.002%

    No Known Activations