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

    Neuronpedia

    INDEX
    Explanations

    references to physical boundaries or borders in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ska
    -0.16
    æĸ¹åIJij
    -0.15
    ordes
    -0.15
     TextAlign
    -0.14
    oir
    -0.14
    ç¦ıåĪ©
    -0.14
    edo
    -0.14
    aaS
    -0.14
    ucci
    -0.14
    lis
    -0.14
    POSITIVE LOGITS
    -edge
    0.19
     edge
    0.19
    /end
    0.17
    EDGE
    0.16
    edge
    0.16
    /Gate
    0.16
     edges
    0.16
    /on
    0.15
    (edge
    0.15
    onal
    0.15
    Act Density 0.075%

    No Known Activations