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

    Neuronpedia

    INDEX
    Explanations

    references to the shape, form, and design of physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sign
    -0.16
    poz
    -0.15
    onet
    -0.15
    anca
    -0.15
    lev
    -0.15
    stra
    -0.15
    ниÑĨа
    -0.14
     ata
    -0.14
    iali
    -0.14
     ни
    -0.14
    POSITIVE LOGITS
    oter
    0.17
     Ø´Ú©ÙĦ
    0.16
    forme
    0.15
    (forms
    0.15
    igu
    0.15
    uling
    0.15
    /forms
    0.15
    CLUDING
    0.14
    ("(%
    0.14
    ÑĮÑı
    0.14
    Act Density 0.069%

    No Known Activations