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

    Neuronpedia

    INDEX
    Explanations

    references to structured organization or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zug
    -0.17
    ESS
    -0.17
    Į¨
    -0.15
    114
    -0.14
    662
    -0.14
    enu
    -0.14
    928
    -0.14
    ним
    -0.14
    ero
    -0.14
    920
    -0.14
    POSITIVE LOGITS
     Ñģел
    0.14
    addon
    0.14
    ingham
    0.14
     cool
    0.14
     TMPro
    0.13
    agner
    0.13
     بÙĨ
    0.13
    еноÑĹ
    0.13
    _subplot
    0.13
    agra
    0.13
    Act Density 0.002%

    No Known Activations