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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eec
    -0.17
    orda
    -0.15
    ÙĪÙĨد
    -0.15
    ÑĪел
    -0.15
    akers
    -0.14
    edList
    -0.14
    rite
    -0.14
    аÑĢÑĩ
    -0.14
    ENTER
    -0.14
     Wang
    -0.14
    POSITIVE LOGITS
    deb
    0.15
     Campos
    0.14
    ÑĤоÑĢ
    0.14
     pert
    0.14
     CONS
    0.14
    (clone
    0.14
    ë¶Ī
    0.13
    490
    0.13
    öff
    0.13
    Ã
    0.13
    Act Density 0.008%

    No Known Activations