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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate classification or categorization of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    поÑĢ
    -0.16
    idor
    -0.16
    iere
    -0.16
    ypes
    -0.15
    serter
    -0.15
    awl
    -0.14
     Sher
    -0.14
     sut
    -0.14
    Įĵ
    -0.14
    ÑħÑĥ
    -0.14
    POSITIVE LOGITS
    MI
    0.14
     bore
    0.14
    à¸Ńà¸ķ
    0.13
    ayet
    0.13
    ohana
    0.13
    émon
    0.13
    inea
    0.13
    nost
    0.13
    forums
    0.13
    rum
    0.13
    Act Density 0.001%

    No Known Activations