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

    Neuronpedia

    INDEX
    Explanations

    references and labels associated with sections in academic or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensa
    -0.17
    alach
    -0.15
    hton
    -0.14
     Dek
    -0.14
    pto
    -0.14
    abella
    -0.14
     obec
    -0.13
    оÑģÑĮ
    -0.13
    assignment
    -0.13
    ÙĤÛĮ
    -0.13
    POSITIVE LOGITS
     (!((
    0.14
    olves
    0.14
    ien
    0.14
    eden
    0.14
    ain
    0.14
    iev
    0.14
    edia
    0.13
    ylie
    0.13
    getDoctrine
    0.13
     gre
    0.13
    Act Density 0.013%

    No Known Activations