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

    Neuronpedia

    INDEX
    Explanations

    references to adversaries or opponents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .synthetic
    -0.15
    osten
    -0.15
    taire
    -0.15
    sent
    -0.14
    UPI
    -0.14
    رÛĮز
    -0.14
    ittings
    -0.14
    ãĤ¯ãĥ©ãĥĸ
    -0.14
    Unhandled
    -0.14
    swer
    -0.13
    POSITIVE LOGITS
    ÏĦÏī
    0.16
    aney
    0.16
    mony
    0.15
    asha
    0.14
    .contentType
    0.14
    877
    0.14
     reife
    0.13
    .opensource
    0.13
     symp
    0.13
    rok
    0.13
    Act Density 0.003%

    No Known Activations