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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or instructions related to decision-making and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    égor
    -0.16
    åIJ¾
    -0.15
     sho
    -0.15
    ):?>↵
    -0.15
    leck
    -0.14
    GGLE
    -0.14
    _Util
    -0.14
     exponential
    -0.14
    áj
    -0.13
    ynn
    -0.13
    POSITIVE LOGITS
    .Spring
    0.17
    ovel
    0.16
     pÅĻesnÄĽ
    0.15
    ä¼łå¥ĩ
    0.15
    ToDo
    0.15
    arat
    0.15
    lesc
    0.14
    оÑĩно
    0.14
    izi
    0.14
    agram
    0.14
    Act Density 0.102%

    No Known Activations