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

    Neuronpedia

    INDEX
    Explanations

    patterns related to formatting and structure in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legg
    -0.17
    literal
    -0.15
    /extensions
    -0.15
    ords
    -0.14
     tertiary
    -0.14
     Sharma
    -0.14
    atters
    -0.13
    itian
    -0.13
     tarn
    -0.13
    ì§Ī
    -0.13
    POSITIVE LOGITS
    utow
    0.17
    icha
    0.16
    chia
    0.15
    ÌĨ
    0.15
    reff
    0.15
     Annunci
    0.15
    nid
    0.14
     Bilim
    0.14
    .sock
    0.14
     Leone
    0.14
    Act Density 0.018%

    No Known Activations