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

    Neuronpedia

    INDEX
    Explanations

    references to labels and labeling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofil
    -0.16
    IGHL
    -0.15
    /Linux
    -0.15
    ib
    -0.14
    ailles
    -0.14
    angler
    -0.14
    ara
    -0.14
    à¸ĩาà¸Ļ
    -0.14
    earable
    -0.14
    alls
    -0.14
    POSITIVE LOGITS
    sonian
    0.18
    ourcem
    0.17
    оÑĤоÑĢ
    0.17
    ging
    0.17
    coon
    0.16
    ged
    0.16
    иÑĢÑĥ
    0.15
    /tag
    0.15
    utomation
    0.15
    LETED
    0.15
    Act Density 0.034%

    No Known Activations