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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and conversational interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Repeated
    -0.15
    овеÑĢ
    -0.15
    ôi
    -0.14
    BarButtonItem
    -0.14
    íĶĮ
    -0.14
    utura
    -0.13
     Warfare
    -0.13
    Å¡it
    -0.13
    iasi
    -0.13
     NDEBUG
    -0.13
    POSITIVE LOGITS
    :↵
    0.28
    :↵↵
    0.24
    ):↵
    0.22
     :↵
    0.21
    ï¼ļ↵
    0.21
    :↵↵↵
    0.20
    ":↵
    0.20
    ]:↵
    0.19
    ':↵
    0.19
     ):↵
    0.19
    Act Density 0.174%

    No Known Activations