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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic papers and research submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.17
    اض
    -0.15
    ovnÃŃ
    -0.15
    anoia
    -0.14
     Regents
    -0.14
    alles
    -0.14
    ilik
    -0.14
     Cler
    -0.14
    armac
    -0.14
    ucc
    -0.14
    POSITIVE LOGITS
    Ĥæķ°
    0.16
    topic
    0.14
    topics
    0.14
    pany
    0.14
    -alist
    0.14
     topics
    0.14
    .topic
    0.14
    iland
    0.14
    /includes
    0.14
    审
    0.13
    Act Density 0.044%

    No Known Activations