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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and their risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     giả
    -0.16
    ÑĪев
    -0.15
    帯
    -0.14
    ÙĨاÙħ
    -0.14
    .Expect
    -0.14
    XHR
    -0.14
    775
    -0.13
    ë°ķ
    -0.13
    breadcrumbs
    -0.13
    ADO
    -0.13
    POSITIVE LOGITS
    panse
    0.19
    owi
    0.16
     Peer
    0.15
    Peer
    0.15
    parity
    0.15
     Morav
    0.15
     peer
    0.15
    .IContainer
    0.14
    pollo
    0.14
     slack
    0.14
    Act Density 0.028%

    No Known Activations