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

    Neuronpedia

    INDEX
    Explanations

    concepts or ideas presented as "things"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogne
    -0.16
    licht
    -0.15
    thin
    -0.15
    ned
    -0.15
    sites
    -0.15
     æĤ
    -0.15
    lek
    -0.15
     ìĿĺíķ´
    -0.14
    ARSE
    -0.14
    side
    -0.14
    POSITIVE LOGITS
    ummy
    0.26
    ToDo
    0.23
    /people
    0.22
    ummies
    0.22
     happening
    0.20
    /person
    0.17
    am
    0.17
    562
    0.17
     Happ
    0.17
    ìłĢ
    0.16
    Act Density 0.067%

    No Known Activations