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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or complexity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittal
    -0.17
    off
    -0.16
     sag
    -0.15
     automáticamente
    -0.14
    PLUGIN
    -0.14
    okane
    -0.14
     duct
    -0.14
    lander
    -0.14
    (sender
    -0.14
    äºľ
    -0.13
    POSITIVE LOGITS
    swick
    0.17
     jspb
    0.17
    uns
    0.16
    ÏģÏĮÏĤ
    0.15
    IFF
    0.14
    opot
    0.14
    ÛĮات
    0.14
    icut
    0.14
    /cat
    0.14
    Occurred
    0.13
    Act Density 0.136%

    No Known Activations