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

    Neuronpedia

    INDEX
    Explanations

    mentions of formal declarations or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -scalable
    -0.18
    sey
    -0.18
    bell
    -0.18
    iting
    -0.17
    bill
    -0.17
    Ñģлов
    -0.15
    zig
    -0.15
    hey
    -0.15
    ongan
    -0.15
    usu
    -0.15
    POSITIVE LOGITS
    uration
    0.16
    ellite
    0.16
    utory
    0.16
    -of
    0.16
    dio
    0.15
    åij¨æľŁ
    0.15
    edly
    0.15
    μα
    0.15
    hood
    0.15
    utor
    0.15
    Act Density 0.028%

    No Known Activations