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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases involving technological aspects or security measures

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly those related to specific themes or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manhattan
    -0.73
     Queens
    -0.66
     Yon
    -0.64
     Pilgrim
    -0.64
     Mun
    -0.64
     Mous
    -0.64
     Somerset
    -0.63
     Shattered
    -0.63
     Whit
    -0.63
     Aster
    -0.63
    POSITIVE LOGITS
    ¬
    1.53
    ľ
    1.36
    Ĵ
    1.32
    ı
    1.29
    ĸ
    1.28
    Ķ
    1.27
    ĺ
    1.27
    ©
    1.22
    ij
    1.22
    ¡
    1.21
    Act Density 0.165%

    No Known Activations