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

    Neuronpedia

    INDEX
    Explanations

    programming-related comments that indicate tasks or improvements needed in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quer
    -0.15
    undler
    -0.14
    IBUTES
    -0.14
    "><!--
    -0.13
    rema
    -0.13
    âĢ¦"↵↵
    -0.13
    ï¼ģ”↵↵
    -0.13
    lettes
    -0.13
     ê¼
    -0.13
    our
    -0.13
    POSITIVE LOGITS
     should
    0.19
    .should
    0.18
     future
    0.18
     perhaps
    0.18
     need
    0.17
    eday
    0.17
     ought
    0.17
     McGill
    0.17
    .TODO
    0.17
    .todo
    0.16
    Act Density 0.018%

    No Known Activations