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

    Neuronpedia

    INDEX
    Explanations

    references to posts and reviews, particularly those indicating visibility or accessibility of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.98
    UnsafeEnabled
    -0.94
     незавершена
    -0.91
    InjectAttribute
    -0.90
    Jeografia
    -0.89
    دانشنامهٔ
    -0.86
     مشين
    -0.81
    +#+#
    -0.79
    MigrationBuilder
    -0.78
     newBuilder
    -0.78
    POSITIVE LOGITS
     Athenian
    0.54
     ampoule
    0.48
     Turin
    0.47
     Meu
    0.46
     Ratu
    0.46
     umbi
    0.44
     domes
    0.43
     oars
    0.41
     Florentine
    0.41
     Vasco
    0.41
    Act Density 0.478%

    No Known Activations