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

    Neuronpedia

    INDEX
    Explanations

    symbols or formatting elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of symbols or representations of political or social movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manz
    -0.64
     dod
    -0.64
     Jeanne
    -0.64
     Izan
    -0.64
     Bris
    -0.62
     shroud
    -0.61
    sters
    -0.61
     Shelter
    -0.61
     ABE
    -0.61
     sacrific
    -0.61
    POSITIVE LOGITS
    ª
    1.45
    Ĵ
    1.39
    IJ
    1.33
    «
    1.24
    ¹
    1.20
    ı
    1.20
    ĸ
    1.18
    ³
    1.17
    ij
    1.17
    Ķ
    1.17
    Act Density 0.090%

    No Known Activations