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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tri
    -0.16
    folk
    -0.14
    ippi
    -0.14
    morgan
    -0.14
    rego
    -0.14
    ắp
    -0.14
    leur
    -0.14
     Minister
    -0.14
    Mountain
    -0.13
     Mountain
    -0.13
    POSITIVE LOGITS
     mock
    0.71
     Mock
    0.65
    mock
    0.62
    Mock
    0.60
    .mock
    0.56
     mocks
    0.55
    _mock
    0.54
    /mock
    0.53
    (mock
    0.53
     mocked
    0.52
    Act Density 0.053%

    No Known Activations