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

    Neuronpedia

    INDEX
    Explanations

    sequences of words in a specific language that reflect complex expressions of interconnectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥª
    -0.18
    ë¨
    -0.18
    esch
    -0.17
     Rosenstein
    -0.17
    urch
    -0.17
    neck
    -0.16
    works
    -0.16
    ÑĻ
    -0.16
    gy
    -0.16
    Ñ
    -0.15
    POSITIVE LOGITS
     ÐĶжон
    0.23
     U
    0.21
    Ñįй
    0.21
     ÐĶж
    0.20
    оÑĥ
    0.20
    дж
    0.19
    ÐĶж
    0.18
     ÐĿай
    0.18
    Ñģли
    0.18
    инг
    0.18
    Act Density 0.015%

    No Known Activations