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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Posted" followed by a number, indicating publication dates or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.19
    arily
    -0.19
    rox
    -0.16
    quia
    -0.15
    poster
    -0.15
    annt
    -0.14
    itet
    -0.14
    WARDED
    -0.14
    folk
    -0.14
    à¸ĩาà¸Ļ
    -0.14
    POSITIVE LOGITS
    unga
    0.17
    deki
    0.15
    RAINT
    0.14
    pond
    0.14
    itore
    0.14
    theid
    0.14
    tlement
    0.13
     ÑĤÑĢа
    0.13
    .localization
    0.13
    /generated
    0.13
    Act Density 0.006%

    No Known Activations