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

    Neuronpedia

    INDEX
    Explanations

    references to notable individuals and their contributions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attending
    -0.16
    anner
    -0.15
    à¸ĩาà¸Ļ
    -0.14
    _NB
    -0.14
    267
    -0.14
    olit
    -0.14
     Guest
    -0.14
    ozÃŃ
    -0.14
    egment
    -0.14
     induction
    -0.14
    POSITIVE LOGITS
     Direct
    0.17
     specialist
    0.15
     direct
    0.15
    دÛĮگر
    0.15
     Respons
    0.15
    cky
    0.15
     vice
    0.15
     chef
    0.15
    Direct
    0.15
     delegate
    0.15
    Act Density 0.017%

    No Known Activations