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

    Neuronpedia

    INDEX
    Explanations

    references and citations in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rels
    -0.15
    stav
    -0.15
    asons
    -0.14
     padx
    -0.14
    edo
    -0.14
    leys
    -0.14
    allest
    -0.14
    anga
    -0.14
     dim
    -0.13
     Emin
    -0.13
    POSITIVE LOGITS
    .hxx
    0.14
     Burk
    0.14
     ÎijÏĢ
    0.14
    aw
    0.13
    WithContext
    0.13
    iÅŁleri
    0.13
    izu
    0.13
     Hund
    0.13
    eri
    0.13
    undy
    0.13
    Act Density 0.012%

    No Known Activations