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

    Neuronpedia

    INDEX
    Explanations

    references to essays and contextual elements in written works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inand
    -0.15
    ald
    -0.14
     sür
    -0.14
    xca
    -0.13
    _soc
    -0.13
    amon
    -0.13
    Äħd
    -0.13
    iš
    -0.13
    deal
    -0.12
    ieg
    -0.12
    POSITIVE LOGITS
     explanation
    0.20
     explaining
    0.19
     explanations
    0.18
     explains
    0.17
     interpret
    0.17
     interpretation
    0.16
    oad
    0.16
     Explanation
    0.16
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.16
     history
    0.16
    Act Density 0.128%

    No Known Activations