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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusions or limits in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ola
    -0.15
    ÃĸL
    -0.15
    ullo
    -0.14
    ography
    -0.14
    οÏĤ
    -0.14
    æŁľ
    -0.14
    639
    -0.14
    orge
    -0.14
    éro
    -0.14
    ëŀ
    -0.14
    POSITIVE LOGITS
    illas
    0.17
    оÑħ
    0.15
    ather
    0.15
    渡
    0.15
    lett
    0.15
    dued
    0.15
    iglia
    0.14
    мини
    0.14
    lee
    0.14
    LEE
    0.14
    Act Density 0.018%

    No Known Activations