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

    Neuronpedia

    INDEX
    Explanations

    references to items or concepts that are categorized or selected from a broader set

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tarko
    -0.62
     two
    -0.58
     Cuth
    -0.58
    UND
    -0.56
     élections
    -0.56
     one
    -0.56
    MigrationBuilder
    -0.56
     sää
    -0.53
     PopupWindow
    -0.52
    َي
    -0.51
    POSITIVE LOGITS
    的一些
    0.81
    )"),
    0.74
    一些
    0.73
     Những
    0.72
     Audiodateien
    0.69
     serializers
    0.69
    paravant
    0.67
    Những
    0.66
     mga
    0.65
    keh
    0.65
    Act Density 0.155%

    No Known Activations