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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and numerical phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.17
    ouse
    -0.16
     Sed
    -0.15
    æŀ
    -0.15
     Jar
    -0.15
    kees
    -0.14
    isches
    -0.14
    chemes
    -0.14
     ones
    -0.14
    ennen
    -0.14
    POSITIVE LOGITS
    /blue
    0.18
     ÐŁÑĢод
    0.16
    ãģ¤ãģ¶
    0.16
    bou
    0.16
    ÑĢод
    0.16
    TECTED
    0.15
    uraa
    0.15
    antwort
    0.15
    arton
    0.14
    UiThread
    0.14
    Act Density 0.012%

    No Known Activations