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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and security concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    يكب
    -0.57
    ⓧ
    -0.57
    ➟
    -0.56
    kloped
    -0.56
     chi̍t
    -0.55
    äude
    -0.55
     kasarigan
    -0.55
    Климат
    -0.53
    antum
    -0.52
    Diwedd
    -0.52
    POSITIVE LOGITS
    EndContext
    0.63
     typelib
    0.53
    routeProvider
    0.52
     Económica
    0.52
     Vrij
    0.50
     Sociales
    0.47
     Shakspeare
    0.47
     soils
    0.46
    FlatAppearance
    0.46
     Soil
    0.46
    Act Density 0.546%

    No Known Activations